CN108564010A - A kind of detection method, device, electronic equipment and storage medium that safety cap is worn - Google Patents
A kind of detection method, device, electronic equipment and storage medium that safety cap is worn Download PDFInfo
- Publication number
- CN108564010A CN108564010A CN201810267214.3A CN201810267214A CN108564010A CN 108564010 A CN108564010 A CN 108564010A CN 201810267214 A CN201810267214 A CN 201810267214A CN 108564010 A CN108564010 A CN 108564010A
- Authority
- CN
- China
- Prior art keywords
- image
- pedestrian
- target pedestrian
- safety cap
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses detection method, device, electronic equipment and storage medium that a kind of safety cap is worn, this method includes：Obtain correspondence at least two images acquired in synchronization mounted at least two image capture devices of different direction；According at least two images, judge whether target pedestrian has worn safety cap；If so, determining that the target pedestrian has worn safety cap；Otherwise, it determines the non-safe wearing cap of target pedestrian.In the present invention image is acquired by least two image capture devices mounted on different direction, pass through the image of multiple angles, it detects whether target pedestrian has worn safety cap, solves the problems, such as that target pedestrian to be detected in image is blocked, improve the accuracy of testing result.
Description
Technical field
A kind of worn the present invention relates to safety devices detection technique field more particularly to safety cap detection method, device,
Electronic equipment and storage medium.
Background technology
The head device of head impact when safety cap is the strike of anti-object and falls, personnel by safe wearing cap, to
Head is protected, from the object injury fallen.By the detection to safety cap positioning and tracking to personnel are realized with tracking,
When being detected safety cap with tracking, grader is related to using statistical pattern recognition method, safety cap inspection is carried out with grader
It surveys, safety cap is tracked in conjunction with Kalman filter and Mean-shift, but above-mentioned can only be directed to has worn safety cap
Personnel position and track, and can not judge whether personnel have worn safety cap.But due to be frequently present of personnel not according to
The case where regulation safe wearing cap, occurs, and is monitored in real time to the wear condition of safety cap, and detect whether according to the rules
Safe wearing cap is most important.
In the detection method that safety cap is worn in the prior art, server obtains live video image, is learnt by training
The position of human body detection model of foundation, is detected to obtain position of human body to the live video image, according to the human body position
It sets and judges whether to wear region in safety cap；If it is, the number of people safety cap joint-detection model established by training study,
The live video image is detected to obtain number of people safety cap united state, it is not verified according to the number of people；If worn
Safety cap, the then safety cap type detection model established by training study, is detected to obtain to the live video image
Safety cap type, judges whether safety cap type meets regulation, if meeting regulation, safety cap is worn through verification, otherwise,
Safety cap is worn not verified.
At that time since practice of construction environment is complicated, such as construction site, coal mine oil field construction environment, construction personnel may
It is blocked by building, construction equipment etc., increases the difficulty of safety cap detection, cause to detect constructor according to live video image
Member whether safe wearing cap when, there is a situation where that detection is inaccurate.
Invention content
The present invention provides detection method, device, electronic equipment and storage mediums that a kind of safety cap is worn, to solve
Safety cap wears the inaccurate problem of detection in the prior art.
The present invention provides a kind of detection method that safety cap is worn, and this method includes：
Obtain the correspondence at least two acquired in synchronization mounted at least two image capture devices of different direction
Image；
According at least two images, judge whether target pedestrian has worn safety cap；
If so, determining that the target pedestrian has worn safety cap；Otherwise, it determines the non-safe wearing of target pedestrian
Cap.
Further, at least two images described in the basis, judge whether target pedestrian has worn safety cap and included：
According to pedestrian region in every image, the first object image for including the target pedestrian is determined；
In the first object image, it will detect that the image that the target pedestrian has worn safety cap is determined as second
Target image；
Judge the second quantity of second target image and the first quantity of the first object image ratio whether
More than preset first fractional threshold, determine whether the target pedestrian has worn safety cap.
Further, at least two images described in the basis, judge whether target pedestrian has worn safety cap and included：
According to pedestrian region in every image, the first object image for including the target pedestrian is determined；
In the first object image, the picture quality for filtering out the target pedestrian meets the third mesh of preset requirement
Logo image；
In the third target image, detect whether the target pedestrian has worn safety cap.
Further, in the target image, it detects the target pedestrian and whether has worn safety cap and include：
According to target pedestrian region, the subgraph of the head zone of the target pedestrian is determined；
The subgraph is input in the grader pre-saved, according to the classification results of the grader, determines institute
Whether the classification for stating head zone belongs to safe wearing cap classification；
If so, determining that the target pedestrian has worn safety cap；If not, determining the non-safe wearing of target pedestrian
Cap；Or
If detecting safety cap in target pedestrian region, it is determined that the header area of the target pedestrian
Domain, judges whether the safety cap is located within the scope of the corresponding predeterminable area of the head zone；
If so, determining that the target pedestrian has worn safety cap；If not, determining that the target pedestrian does not wear peace
Full cap.
Further, described according to pedestrian region in every image, determine the first mesh for including the target pedestrian
Logo image includes：
According to pedestrian region in every image, determine each region in its preset corresponding image capture device
Plane coordinates in plane of delineation coordinate system；
It is reflected according to the plane of delineation coordinate system of the image capture device pre-saved and the world coordinate system of construction scene
Relationship, and the plane coordinates in each region are penetrated, determines that the world of the corresponding pedestrian in each region in the world coordinate system is sat
Mark；
Image comprising the target pedestrian is determined as first object image.
The present invention provides a kind of detection device that safety cap is worn, which includes：
Acquisition module is mounted at least two image capture devices of different direction and acquires in synchronization for obtaining
Corresponding at least two images；
Judgment module judges whether target pedestrian has worn safety cap at least two images according to；
Determining module determines that the target pedestrian has worn safety for being yes when the judging result of the judgment module
Cap；When the judging result of the judgment module is no, the non-safe wearing cap of the target pedestrian is determined.
Further, the judgment module is specifically used for, according to pedestrian region in every image, determining comprising described
The first object image of target pedestrian；In the first object image, it will detect that the target pedestrian has worn safety cap
Image be determined as the second target image；Judge the of the second quantity of second target image and the first object image
Whether the ratio of one quantity is more than preset first fractional threshold, determines whether the target pedestrian has worn safety cap.
Further, the judgment module is specifically used for, according to pedestrian region in every image, determining comprising described
The first object image of target pedestrian；In the first object image, the picture quality for filtering out the target pedestrian meets
The third target image of preset requirement；In the third target image, detect whether the target pedestrian has worn safety cap.
Further, the judgment module is specifically used for, according to target pedestrian region, determining the target line
The subgraph of the head zone of people；The subgraph is input in the grader pre-saved, according to point of the grader
Class is as a result, determine whether the classification of the head zone belongs to safe wearing cap classification；If so, determining the target pedestrian
Safety cap is worn；If not, determining the non-safe wearing cap of target pedestrian；Or in target pedestrian region such as
Fruit detects safety cap, it is determined that the head zone of the target pedestrian judges whether the safety cap is located at the header area
Within the scope of the corresponding predeterminable area in domain；If so, determining that the target pedestrian has worn safety cap；If not, described in determining
The non-safe wearing cap of target pedestrian.
Further, the judgment module is specifically used for, according to pedestrian region in every image, determining each region
Plane coordinates in the plane of delineation coordinate system of its preset corresponding image capture device；It is adopted according to the image pre-saved
Collect the mapping relations of the plane of delineation coordinate system and the world coordinate system of construction scene of equipment, and the plane coordinates in each region,
Determine world coordinates of the corresponding pedestrian in each region in the world coordinate system；Image comprising the target pedestrian is true
It is set to first object image.
The present invention provides a kind of electronic equipment, including：Processor, communication interface, memory and communication bus, wherein place
Device, communication interface are managed, memory completes mutual communication by communication bus；
It is stored with computer program in the memory, when described program is executed by the processor so that the place
Manage the step of device executes any of the above-described the method.
The present invention provides a kind of computer readable storage medium, is stored with the computer journey that can be executed by electronic equipment
Sequence, when described program is run on the electronic equipment so that the electronic equipment executes any of the above-described the method
Step.
The present invention provides detection method, device, electronic equipment and storage medium that a kind of safety cap is worn, this method packets
It includes：Obtain correspondence at least two images acquired in synchronization mounted at least two image capture devices of different direction；
According at least two images, judge whether target pedestrian has worn safety cap；If so, determining that the target pedestrian wears
Safety cap；Otherwise, it determines the non-safe wearing cap of target pedestrian.By mounted on at least two of different direction in the present invention
Image capture device acquires image, is solved by the image of multiple angles to detect whether target pedestrian has worn safety cap
The problem of target pedestrian to be detected is blocked in image, improves the accuracy of testing result.
Description of the drawings
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
Obtain other attached drawings according to these attached drawings.
Fig. 1 is the detection process schematic diagram that a kind of safety cap that present example 1 provides is worn；
Fig. 2 is the detection process schematic diagram that a kind of safety cap that the embodiment of the present invention 2 provides is worn；
Fig. 3 is the detection process schematic diagram that a kind of safety cap that the embodiment of the present invention 3 provides is worn；
Fig. 4 is a kind of safety cap detection mode schematic diagram that the embodiment of the present invention 4 provides；
Fig. 5 is another safety cap detection mode schematic diagram that the embodiment of the present invention 4 provides；
Fig. 6 is the detection process schematic diagram that a kind of safety cap that the embodiment of the present invention 4 provides is worn；
Fig. 7 is the detection process schematic diagram that another safety cap that the embodiment of the present invention 4 provides is worn；
Fig. 8 is the structural schematic diagram for a kind of electronic equipment that the embodiment of the present invention 6 provides；
Fig. 9 is the detection device schematic diagram that a kind of safety cap provided in an embodiment of the present invention is worn.
Specific implementation mode
In order to improve the accuracy that safety cap wears detection, an embodiment of the present invention provides the detections that a kind of safety cap is worn
Mode, device, electronic equipment and storage medium.
To make the objectives, technical solutions, and advantages of the present invention clearer, make into one below in conjunction with the attached drawing present invention
Step ground detailed description, it is clear that described embodiment is only a part of the embodiment of the present invention, rather than whole implementation
Example.Based on the embodiments of the present invention, obtained by those of ordinary skill in the art without making creative efforts
Every other embodiment, shall fall within the protection scope of the present invention.
Embodiment 1：
Fig. 1 is the detection process schematic diagram that a kind of safety cap provided in an embodiment of the present invention is worn, which includes following
Step：
S101：Obtain the correspondence acquired in synchronization mounted at least two image capture devices of different direction at least
Two images.
The detection method that safety cap provided in an embodiment of the present invention is worn is applied to electronic equipment, and electronic equipment can be table
Face computer, portable computer, smart mobile phone, tablet computer, personal digital assistant (Personal Digital
Assistant, PDA), the electronic equipments such as server.
Electronic equipment can obtain the image of image capture device acquisition, and image capture device can be video camera, photography
The equipment that machine etc. can carry out Image Acquisition, image capture device the image collected are usually two dimensional image.
Image capture device can send an image to electronic equipment after collecting image, so that electronic equipment obtains
The image acquired to image capture device；Or electronic equipment actively can obtain image etc. to image capture device.
Image capture device is mounted with that at least two, and at least two image capture devices are installed in the embodiment of the present invention
In different direction, the correspondence that image that electronic equipment obtains, which is at least two image capture device, to be acquired in synchronization is at least
Two images, since at least two image capture device is mounted on different direction, at least two image capture device
In the image that correspondence at least two images of synchronization acquisition are different angle, it is more conducive to construction personnel's safety cap
Wear condition is detected.
In order to reach more preferably Image Acquisition effect, the accuracy in detection of construction personnel's safety cap wearing is further increased,
When different direction installs at least two image capture device, building or construction in image-capture field can be chosen at and set
It is standby that the few corresponding position of shelters is waited to be installed.
At least two image capture devices are installed in construction scene, are acquired generally for image capture device is accurately identified
Image image capture device can be demarcated after image capture device is installed, i.e., to construction scene carry out Three-dimensional Gravity
It builds.
S102：According at least two images, judge whether target pedestrian has worn safety cap, if so, carrying out
S103, if not, carrying out S104.
Electronic equipment gets at least two image capture devices after the correspondence that synchronization acquires at least two images,
It can judge whether target pedestrian has worn safety cap according at least two images.
Target pedestrian can be the arbitrary pedestrian occurred in image, can also be the pedestrian of monitoring personnel selection, target line
The quantity of people can be one or more, of course for the accuracy for realizing detection, preferably, can be every by what is occurred in image
A pedestrian is used as target pedestrian.It is needle when judging whether target pedestrian has worn safety cap if target line is artificially multiple
Each target pedestrian is determined, judges that the process whether each target pedestrian has worn safety cap is identical.
For electronic equipment according at least two images, it can be electronic equipment inspection to judge whether target pedestrian has worn safety cap
Whether the same target pedestrian surveyed in every image has worn safety cap, according to the testing result in every image, determines the mesh
Whether mark pedestrian has worn safety cap, can also be one image of selection, detect selection this at least two images
Whether the target pedestrian in image has worn safety cap, so that it is determined that whether target pedestrian has worn safety cap etc., if it is
An image is chosen at least two images, electronic equipment can be that an image is arbitrarily chosen at least two images, compared with
Goodly, electronic equipment it is preferable can to choose picture quality according to the snapshot preference rule pre-saved at least two images
Preferred snapshot image.
Electronic equipment is different according to the judging result of target pedestrian's safe wearing cap, carries out different steps.
S103：Determine that the target pedestrian has worn safety cap.
If electronic equipment determines that target pedestrian has worn safety cap, it may be considered that currently according at least two images
The case where target pedestrian's safe wearing cap, is normal, without additionally being reminded.
When electronic equipment determines that target pedestrian has worn safety cap, it can be directed to target pedestrian, carry out next round safety cap
The determination process of wear condition.
S104：Determine the non-safe wearing cap of the target pedestrian.
If electronic equipment determines the non-safe wearing cap of target pedestrian, it may be considered that currently according at least two images
The case where target pedestrian's safe wearing cap, is abnormal, in order to ensure the safety of target pedestrian, can be alerted to target pedestrian,
To notify the timely safe wearing cap of target pedestrian.
Being alerted to target pedestrian can broadcast etc. target pedestrian region.
When electronic equipment determines the non-safe wearing cap of target pedestrian, it can be directed to target pedestrian, carry out next round safety cap
The determination process of wear condition.
The detection method that safety cap provided in an embodiment of the present invention is worn has suitable for various complicated under the scene blocked
The detection of target, complicated has scene blocked such as construction, communications and transportation, mining tunnel etc..
Image is acquired by least two image capture devices mounted on different direction in the embodiment of the present invention, by multiple
The image of angle solves target pedestrian to be detected in image and is blocked to detect whether target pedestrian has worn safety cap
The problem of, improve the accuracy of testing result.
Embodiment 2：
In order to further increase the accuracy of testing result, on the basis of the above embodiments, in the embodiment of the present invention, institute
At least two images according to are stated, judge whether target pedestrian has worn safety cap and included：
According to pedestrian region in every image, the first object image for including the target pedestrian is determined；
In the first object image, it will detect that the image that the target pedestrian has worn safety cap is determined as second
Target image；
Judge the second quantity of second target image and the first quantity of the first object image ratio whether
More than preset first fractional threshold, determine whether the target pedestrian has worn safety cap.
According to including the target image of target pedestrian, and detect that target pedestrian has worn the target image of safety cap, really
Whether the pedestrian that sets the goal has worn safety cap, may be implemented to judge whether target pedestrian has worn safety cap according to multiple images,
To further improve the accuracy of detection.
Electronic equipment obtains correspondence at least two images of different direction, first at least two images of different direction
Pedestrian detection is carried out, pedestrian detection can be understood as detecting pedestrian region in every image, i.e., be detected in every image
The pedestrian of appearance, pedestrian detection method can be the method based on machine learning such as Adaboost, SVM etc., can also be to be based on
Method of deep learning such as R-CNN, Fast R-CNN, YOLO etc..
Electronic equipment is by the pedestrian of the every image detected, to identify target pedestrian, according to the target line recognized
People detects whether the target pedestrian in every image has worn safety cap, further according to the testing result in every image, determines mesh
Whether mark pedestrian has worn safety cap.
Specifically, electronic equipment determines the first object image for including target pedestrian according to the target pedestrian recognized,
Detection has the target pedestrian in which first object image to wear safety cap in first object image, will wear safety cap
Image where target pedestrian is determined as the second target image.
Electronic equipment judges the second mesh according to the first quantity of first object image and the second quantity of the second target image
Whether the second quantity of logo image and the ratio of the first quantity of first object image are more than the first fractional threshold, if so, really
The pedestrian that sets the goal has worn safety cap, if not, determining the non-safe wearing cap of target pedestrian.By thus according to including target pedestrian
First object image the first quantity, and detect target pedestrian worn the second target image of safety cap second number
Amount, to determine whether target pedestrian has worn safety cap, it can be understood as carried out respectively to multiple target images of target pedestrian
Safety cap detects, and confidence level ballot has been carried out according to the safety cap testing result of target pedestrian in multiple target images, according to throwing
Ticket result determines whether target pedestrian has worn safety cap.
First fractional threshold pre-saves in the electronic device, and the first fractional threshold is the number not less than 0 and no more than 1
Amount, i.e. the first fractional threshold is between 0 to 1, such as the first fractional threshold can be 0.5 or 0.8 etc..
The embodiment of the present invention is illustrated with a specific embodiment below, as shown in the process of Fig. 2：
S201：Obtain the correspondence acquired in synchronization mounted at least two image capture devices of different direction at least
Two images.
S202：According to pedestrian region in every image, the first object image for including the target pedestrian is determined.
S203：In the first object image, it will detect that the target pedestrian has worn the image determination of safety cap
For the second target image.
S204：Judge the ratio of the second quantity of second target image and the first quantity of the first object image
Whether preset first fractional threshold is more than；If so, carrying out S205；If not, carrying out S206.
S205：It determines that target pedestrian has worn safety cap, returns to S201.
S206：It determines the non-safe wearing cap of target pedestrian, alarms, return to S201.
Since basis includes the target image of target pedestrian in the embodiment of the present invention, and detect that target pedestrian has worn peace
The target image of full cap, determines whether target pedestrian has worn safety cap, therefore may be implemented to judge target according to multiple images
Whether pedestrian has worn safety cap, to further improve the accuracy of detection.
Embodiment 3：
In order to further increase the accuracy of testing result, on the basis of the various embodiments described above, in the embodiment of the present invention,
At least two images described in the basis, judge whether target pedestrian has worn safety cap and included：
According to pedestrian region in every image, the first object image for including the target pedestrian is determined；
In the first object image, the picture quality for filtering out the target pedestrian meets the third mesh of preset requirement
Logo image；
In the third target image, detect whether the target pedestrian has worn safety cap.
Picture quality is screened in the target image comprising target pedestrian and meets the target image of preset requirement, therefore can be with
It realizes according to the preferred snapshot image filtered out, determines whether target pedestrian has worn safety cap, to further improve inspection
The accuracy of survey.
Electronic equipment obtains correspondence at least two images of different direction, is carried out at least two images of different direction
Pedestrian detection, pedestrian detection can be understood as detecting pedestrian region in every image, i.e., detect and occur in every image
Pedestrian, pedestrian detection method can be the method based on machine learning such as Adaboost, SVM etc., can also be based on depth
Method of study such as R-CNN, Fast R-CNN, YOLO etc..Pedestrian detection method used in the embodiment of the present invention with it is above-mentioned
The pedestrian detection method used in embodiment can be identical or different.
Electronic equipment is by the pedestrian of the every image detected, to identify target pedestrian, according to the target line recognized
People chooses an image at least two images, and whether the target pedestrian detected in an image for selection has worn safety
Cap, to determine whether target pedestrian has worn safety cap.
Specifically, electronic equipment determines the first object image for including target pedestrian according to the target pedestrian recognized,
In first object image, the picture quality for filtering out target pedestrian meets the third target image of preset requirement, filters out third
It is preferred that target image can be understood as carrying out snapshot in first object image, due to target in the third target image that filters out
The picture quality of pedestrian is preferable, therefore determines whether target pedestrian has worn the accuracy of safety cap more according to third target image
It is high.The quantity of third target image can be one or more, and safety can be met by usually choosing a third target image
The detection that cap is worn.
The preset requirement of picture quality pre-saves in the electronic device, and the preset requirement of picture quality can be clarity
It is high, noise is small, edge is apparent, area is big etc., third target image can be used as by meeting one of which or multinomial image.
Electronic equipment is in third target image, and whether detection target pedestrian has worn safety cap, if in third target
Detect that target pedestrian has worn safety cap in image, it is determined that target pedestrian has worn safety cap, if in third target figure
The non-safe wearing cap of target pedestrian detected as in, it is determined that the non-safe wearing cap of target pedestrian.
The embodiment of the present invention is illustrated with a specific embodiment below, as shown in the process of Fig. 3：
S301：Obtain the correspondence acquired in synchronization mounted at least two image capture devices of different direction at least
Two images.
S302：According to pedestrian region in every image, the first object image for including the target pedestrian is determined.
S303：In the first object image, the picture quality for filtering out the target pedestrian meets preset requirement
Third target image.
S304：In the third target image, detect whether the target pedestrian has worn safety cap；If so, into
Row S305；If not, carrying out S306.
S305：It determines that target pedestrian has worn safety cap, returns to S301.
S306：It determines the non-safe wearing cap of target pedestrian, alarms, return to S301.
Meet preset requirement due to screening picture quality in the embodiment of the present invention in the target image comprising target pedestrian
Target image determine whether target pedestrian has worn safety cap according to the preferred snapshot image filtered out, to further carrying
The high accuracy of detection.
Embodiment 4：
On the basis of the various embodiments described above, in the embodiment of the present invention, in the target image, detecting the target pedestrian is
No safety cap of having worn includes：
According to target pedestrian region, the subgraph of the head zone of the target pedestrian is determined；
The subgraph is input in the grader pre-saved, according to the classification results of the grader, determines institute
Whether the classification for stating head zone belongs to safe wearing cap classification；
If so, determining that the target pedestrian has worn safety cap；If not, determining the non-safe wearing of target pedestrian
Cap；Or
If detecting safety cap in target pedestrian region, it is determined that the header area of the target pedestrian
Domain, judges whether the safety cap is located within the scope of the corresponding predeterminable area of the head zone；
If so, determining that the target pedestrian has worn safety cap；If not, determining that the target pedestrian does not wear peace
Full cap.
Electronic equipment can be by first detecting pedestrian head region, then detects safety cap, or can be by first detecting peace
Full cap, then pedestrian head region is detected, to realize the detection to target pedestrian's safety cap wear condition.
In the target image, whether target pedestrian when having worn safety cap for detection for electronic equipment, may be used it is following at least
Any mode of two schemes is detected：Scheme one, first detection pedestrian head region, then detect safety cap；Scheme two, elder generation
Safety cap is detected, then detects pedestrian head region.
If electronic equipment is in the target image, when whether detection target pedestrian has worn safety cap, it is using scheme one
First detection pedestrian head region, then detect the mode of safety cap, then electronic equipment is first according to target pedestrian region, detection row
Head part region determines the subgraph of the head zone of target pedestrian, then the subgraph is input to the grader pre-saved
In, according to the classification results of grader, to determine whether the type of head zone belongs to safe wearing cap classification, so that it is determined that
Whether target pedestrian has worn safety cap.
The grader pre-saved can be safety cap grader.
Specifically as shown in figure 4, electronic equipment first detects pedestrian head region, the subgraph in pedestrian head region is inputted
Into safety cap grader.
If electronic equipment according to the classification results of grader, determines that the type of head zone belongs to safe wearing cap class
Not, it is determined that target pedestrian has worn safety cap；If electronic equipment determines head zone according to the classification results of grader
Classification is not belonging to safe wearing cap classification, it is determined that the non-safe wearing cap of target pedestrian.
Electronic equipment carry out pedestrian head region detection method, can be the method based on machine learning such as
Adaboost, SVM etc. can also be method based on deep learning such as R-CNN, Fast R-CNN, YOLO etc..
The sorting technique that electronic equipment is classified the head zone detected by grader can be based on machine
The method of study such as SVM, naive Bayesian, decision tree, Logistic Regression etc., can also be based on deep learning
Method such as CNN classification etc..
If electronic equipment is in the target image, when whether detection target pedestrian has worn safety cap, it is using scheme two
It first detecting safety cap, then detects the mode in pedestrian head region, then electronic equipment first detects safety cap in target pedestrian area,
If not detecting safety cap, it is determined that the non-safe wearing cap of target pedestrian determines target pedestrian when detecting safety cap
Head zone, judge the safety cap whether be located at the corresponding predeterminable area of head zone within the scope of, so that it is determined that target pedestrian
Whether safety cap has been worn.
Specifically as shown in figure 5, electronic equipment first detects safety cap, differentiate the safety cap detected whether in target pedestrian
Head.
Predeterminable area range pre-saves in the electronic device.When safety cap is located at the corresponding predeterminable area model of head zone
In enclosing, it may be considered that safety cap near the head of target pedestrian, determines that target pedestrian has worn safety cap, when safety cap not
Within the scope of the corresponding predeterminable area of head zone, it may be considered that safety cap not near the head of target pedestrian, determines
The non-safe wearing cap of target pedestrian.
The embodiment of the present invention is illustrated by taking Fig. 6 as an example, is included the following steps：
S601：Three-dimensional reconstruction.
S602：Different direction camera obtains several video frame images.
In this step, pair acquired in synchronization mounted at least two image capture devices of different direction is obtained
Answer at least two images.
S603：Pedestrian detector.
In this step, according at least two images, pedestrian region in every image is detected.
S604：The identical pedestrian in spatial position is obtained using three-dimensionalreconstruction.
In this step, it according to pedestrian region in every image, determines target pedestrian, and determines to include target pedestrian
First object image.
S605：Safety cap detection module.
In this step, due to having carried out pedestrian detection after obtaining video frame, safety cap detection module can root
Pedestrian head region is first detected according to scheme one, then detects safety cap or scheme two first detects safety cap, then detects pedestrian head area
Whether any mode in domain, detection target pedestrian have worn safety cap.
It will detect that target pedestrian has worn the image of safety cap and has been determined as the second target image.
S606：Confidence level is voted.
In this step, judging the ratio of the second quantity of the second target image and the first quantity of first object image is
It is no to be more than the first fractional threshold；If so, determining that target pedestrian has worn safety cap, S602 is returned, carries out next round detection；Such as
Fruit is no, determines the non-safe wearing cap of target pedestrian, alarms, and returns to S602, carries out next round detection.
When electronic equipment detects target pedestrian using scheme one whether has worn safety cap, at least two can obtained
After image, head zone can also be directly detected in video camera artwork that is, after three-dimensionalreconstruction without pedestrian detection, judged
Head in different cameras whether safe wearing cap and the space coordinate matching position according to three-dimensional reconstruction, judge same position
People whether wear a safety helmet.Detailed process is as shown in Figure 7：
S701：Three-dimensional reconstruction.
S702：Different direction camera obtains several video frame images.
In this step, pair acquired in synchronization mounted at least two image capture devices of different direction is obtained
Answer at least two images.
S703：Safety cap detection module.
In this step, due to, without progress pedestrian detection, directly having carried out safety cap detection after obtaining video frame, because
Preferably safety cap detection module first detects pedestrian head region according to scheme one for this, then detects the mode of safety cap, detects mesh
Whether mark pedestrian has worn safety cap.
S704：The identical pedestrian in spatial position is obtained using three-dimensionalreconstruction.
In this step, it according to pedestrian region in every image, determines target pedestrian, and determines to include target pedestrian
First object image.
S705：Judge whether the people of same position has worn safety cap；If so, S702 is returned to, if not, being reported
It is alert, return to S702.
The people of same position is determined as same target pedestrian, when determining that the people of same position worn safety cap, then really
The pedestrian that sets the goal has worn safety cap, returns to S702, carries out next round detection；When determining the non-safe wearing of the people of same position
Cap, it is determined that the non-safe wearing cap of target pedestrian is alarmed, and S702 is returned, and carries out next round detection.
Judge whether the people of same position has worn safety cap, can detect that target pedestrian has worn the figure of safety cap
As being determined as the second target image, the ratio of the second quantity of the second target image and the first quantity of first object image is judged
Whether it is more than the first fractional threshold, determines whether target pedestrian has worn safety cap, can also be the sieve in first object image
The picture quality for selecting target pedestrian meets the third target image of preset requirement, in third target image, detects target line
Whether people has worn safety cap.
Since electronic equipment can be by first detecting pedestrian head region in the embodiment of the present invention, then safety cap is detected, or
Person can be by first detecting safety cap, then detects pedestrian head region, to realize to target pedestrian's safety cap wear condition
Detection, also make the mode of detection more flexible.
Embodiment 5：
It is described according to pedestrian region in every image in the embodiment of the present invention on the basis of the various embodiments described above,
Determine that the first object image comprising the target pedestrian includes：
According to pedestrian region in every image, determine each region in its preset corresponding image capture device
Plane coordinates in plane of delineation coordinate system；
It is reflected according to the plane of delineation coordinate system of the image capture device pre-saved and the world coordinate system of construction scene
Relationship, and the plane coordinates in each region are penetrated, determines that the world of the corresponding pedestrian in each region in the world coordinate system is sat
Mark；
Image comprising the target pedestrian is determined as first object image.
Image capture device obtains the two dimensional image of several different directions, and pedestrian is carried out to the two dimensional image of different direction
Detection, judges whether the people in the image of different direction is same according to space coordinate of the pedestrian detected in three-dimensional scenic
Individual, so that it is determined that including the image of same target pedestrian.
The plane of delineation coordinate system of each image capture device is preserved in electronic equipment, and the world of construction scene is sat
Mark system, and each mapping relations of plane of delineation coordinate system and world coordinate system.
The plane of delineation coordinate system of each image capture device, and the world coordinate system of construction scene can be according to reality
The preset coordinate system of demand.
The image that electronic equipment is acquired according to each image capture device got, it may be determined that each image is right at its
Plane coordinates in the plane of delineation coordinate system for the image capture device answered, therefore electronic equipment is detected according in each image
Pedestrian, determine plane coordinates of the pedestrian region in the plane of delineation coordinate system of its corresponding image capture device.
After electronic equipment determines the plane coordinates in each region, according to the image of the corresponding image capture device in each region
The mapping relations of plane coordinate system and world coordinate system determine that the world of the corresponding pedestrian in each region in world coordinate system is sat
Mark, to according to the world coordinates of pedestrian, it is determined whether be same target pedestrian.
According to the world coordinates of pedestrian, it is determined whether can be by the corresponding row in each region when being same target pedestrian
The world coordinates of people is identical, is determined as same target pedestrian, and the image where the corresponding region of same target pedestrian is wrapped
Image containing the same target pedestrian is determined as first object image.
Electronic equipment preserves the mapping relations of each plane of delineation coordinate system and world coordinate system, is to Image Acquisition in fact
Equipment is demarcated, and to the three-dimensional reconstruction for scene of constructing.
By taking image capture device is video camera as an example, the mapping for preserving each plane of delineation coordinate system and world coordinate system is closed
System specifically includes：After different direction installs video camera, to camera calibration, effective imaging model is established, that is, determines figure
Relationship between photo coordinate system and camera coordinate system, world coordinate system, to seek intrinsic parameters of the camera and outer
Portion's parameter, establish two-dimensional plane of delineation coordinate system to three-dimensional world coordinate system mapping relations, wherein to camera calibration
Traditional camera marking method or camera self-calibration method etc. can be used；
Two dimensional image, that is, video frame images usually are obtained from the video flowing of video camera in the calibration process of video camera, generally
Each video camera of different direction obtains the image of two width or two width or more, carries out feature extraction to two dimensional image, extraction is crucial
The features such as point, point of interest.After obtaining characteristic point progress Feature Points Matching is utilized with finding similar part in two images
The feature of extraction establishes the correspondence between image pair, that is, find in space a little in the corresponding projection of different images
Point finally obtains three dimensions in conjunction with the inner parameter and external parameter of camera calibration using matching result by match point
The coordinate at midpoint, i.e., from some pixel of plane of delineation coordinate system, inverse mapping just restores at the spatial point in world coordinate system
Go out three-dimensional scene information, determines the mapping relations of plane of delineation coordinate system and world coordinate system.
The feature of extraction can be characteristic point, characteristic curve or region, using characteristic point as Matching unit, feature point extraction algorithm
Using the method based on template, the method based on edge and the method etc. based on image intensity contrast's relationship.Based on template
Feature point detection algorithm need to design complicated template, it is not applicable to complicated image, therefore better simply image can be answered
With the algorithm；It is very big to the dependence of edge detection based on the feature point detection algorithm at edge, therefore can be to sharp-edged
Image application this method；Feature point detecting method based on brightness change is more common, common are Harris, SUSAN, SIFT
Algorithm, in selected characteristic extracting method can according to actual acquisition to image and the applicable scene of each method selected
It takes.Matching process can utilize the methods of matching process based on gray scale, feature-based matching method.
It, can be according to the construction personnel's that three-dimensionalreconstruction determines when electronic equipment determines the non-safe wearing cap of target pedestrian
Work construction personnel's safe wearing cap is reminded in position in the way of regional broadcast etc..
Since image capture device obtains the two dimensional image of several different directions in the embodiment of the present invention, to different direction
Two dimensional image carry out pedestrian detection, the figure of different direction is judged according to space coordinate of the pedestrian detected in three-dimensional scenic
Whether the people as in is same person, so that it is determined that including the image of same target pedestrian.
Embodiment 6：
On the basis of the various embodiments described above, the embodiment of the present invention additionally provides a kind of electronic equipment, as shown in figure 8, packet
It includes：Processor 801, communication interface 802, memory 803 and communication bus 804, wherein processor 801, communication interface 802 are deposited
Reservoir 803 completes mutual communication by communication bus 804；
It is stored with computer program in the memory 803, when described program is executed by the processor 801 so that
The processor 801 executes following steps：
Obtain the correspondence at least two acquired in synchronization mounted at least two image capture devices of different direction
Image；
According at least two images, judge whether target pedestrian has worn safety cap；
If so, determining that the target pedestrian has worn safety cap；Otherwise, it determines the non-safe wearing of target pedestrian
Cap.
Electronic equipment provided in an embodiment of the present invention be specifically as follows desktop computer, portable computer, smart mobile phone,
The electronic equipments such as tablet computer, personal digital assistant, server.
The communication bus that above-mentioned electronic equipment is mentioned can be Peripheral Component Interconnect standard (Peripheral Component
Interconnect, PCI) bus or expanding the industrial standard structure (Extended Industry Standard
Architecture, EISA) bus etc..The communication bus can be divided into address bus, data/address bus, controlling bus etc..For just
It is only indicated with a thick line in expression, figure, it is not intended that an only bus or a type of bus.
Communication interface 802 is for the communication between above-mentioned electronic equipment and other equipment.
Memory may include random access memory (Random Access Memory, RAM), can also include non-easy
The property lost memory (Non-Volatile Memory, NVM), for example, at least a magnetic disk storage.Optionally, memory may be used also
To be at least one storage device for being located remotely from aforementioned processor.
Above-mentioned processor can be general processor, including central processing unit, network processing unit (Network
Processor, NP) etc.；It can also be digital command processor (Digital Signal Processing, DSP), special collection
At circuit, field programmable gate array either other programmable logic device, discrete gate or transistor logic, discrete hard
Part component etc..
In embodiments of the present invention, image is acquired by least two image capture devices mounted on different direction, passed through
The image of multiple angles solves target pedestrian's quilt to be detected in image to detect whether target pedestrian has worn safety cap
The problem of blocking improves the accuracy of testing result.
Embodiment 7：
On the basis of the various embodiments described above, the embodiment of the present invention additionally provides a kind of computer storage readable storage medium
Matter is stored with the computer program that can be executed by electronic equipment in the computer readable storage medium, when described program is in institute
It states when being run on electronic equipment so that the electronic equipment realizes following steps when executing：
Obtain the correspondence at least two acquired in synchronization mounted at least two image capture devices of different direction
Image；
According at least two images, judge whether target pedestrian has worn safety cap；
If so, determining that the target pedestrian has worn safety cap；Otherwise, it determines the non-safe wearing of target pedestrian
Cap.
Above computer readable storage medium storing program for executing can be any usable medium that the processor in electronic equipment can access
Or data storage device, including but not limited to magnetic storage such as floppy disk, hard disk, tape, magneto-optic disk (MO) etc., optical memory
Such as CD, DVD, BD, HVD and semiconductor memory such as ROM, EPROM, EEPROM, nonvolatile memory (NAND
FLASH), solid state disk (SSD) etc..
Image is acquired by least two image capture devices mounted on different direction in embodiments of the present invention, by more
The image of a angle solves target pedestrian to be detected in image and is hidden to detect whether target pedestrian has worn safety cap
The problem of gear, improves the accuracy of testing result.
Fig. 9 is the detection device schematic diagram that a kind of safety cap provided in an embodiment of the present invention is worn, which includes：
Acquisition module 91, for obtaining at least two image capture devices mounted on different direction in synchronization acquisition
Correspondence at least two images；
Judgment module 92 judges whether target pedestrian has worn safety cap at least two images according to；
Determining module 93 determines that the target pedestrian wears for being yes when the judging result of the judgment module 92
Safety cap；When the judging result of the judgment module 92 is no, the non-safe wearing cap of the target pedestrian is determined.
The judgment module 92 is specifically used for, according to pedestrian region in every image, determining to include the target line
The first object image of people；In the first object image, it will detect that the target pedestrian has worn the image of safety cap
It is determined as the second target image；Judge the first quantity of the second quantity and the first object image of second target image
Ratio whether be more than preset first fractional threshold, determine whether the target pedestrian has worn safety cap.
The judgment module 92 is specifically used for, according to pedestrian region in every image, determining to include the target line
The first object image of people；In the first object image, the picture quality for filtering out the target pedestrian meets default want
The third target image asked；In the third target image, detect whether the target pedestrian has worn safety cap.
The judgment module 92 is specifically used for, according to target pedestrian region, determining the head of the target pedestrian
The subgraph in portion region；The subgraph is input in the grader pre-saved, according to the classification results of the grader,
Determine whether the classification of the head zone belongs to safe wearing cap classification；If so, determining that the target pedestrian wears
Safety cap；If not, determining the non-safe wearing cap of target pedestrian；Or if detection in target pedestrian region
To safety cap, it is determined that the head zone of the target pedestrian judges whether the safety cap is located at the head zone and corresponds to
Predeterminable area within the scope of；If so, determining that the target pedestrian has worn safety cap；If not, determining the target line
The non-safe wearing cap of people.
The judgment module 92 is specifically used for, according to pedestrian region in every image, determining each region default
Its corresponding image capture device plane of delineation coordinate system in plane coordinates；According to the image capture device pre-saved
Plane of delineation coordinate system and the world coordinate system of construction scene mapping relations, and each region plane coordinates, determine every
World coordinates of the corresponding pedestrian in a region in the world coordinate system；Image comprising the target pedestrian is determined as
One target image.
Image is acquired by least two image capture devices mounted on different direction in the embodiment of the present invention, by multiple
The image of angle solves target pedestrian to be detected in image and is blocked to detect whether target pedestrian has worn safety cap
The problem of, improve the accuracy of testing result.
For systems/devices embodiment, since it is substantially similar to the method embodiment, so the comparison of description is simple
Single, the relevent part can refer to the partial explaination of embodiments of method.
It should be understood by those skilled in the art that, embodiments herein can be provided as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, the application can be used in one or more wherein include computer usable program code computer
The computer program production implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of product.
The application is with reference to method, the flow of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that can be realized by computer program instructions every first-class in flowchart and/or the block diagram
The combination of flow and/or box in journey and/or box and flowchart and/or the block diagram.These computer programs can be provided
Instruct the processor of all-purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine so that the instruction executed by computer or the processor of other programmable data processing devices is generated for real
The device for the function of being specified in present one flow of flow chart or one box of multiple flows and/or block diagram or multiple boxes.
These computer program instructions, which may also be stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that instruction generation stored in the computer readable memory includes referring to
Enable the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one box of block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device so that count
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, in computer or
The instruction executed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Although the preferred embodiment of the application has been described, created once a person skilled in the art knows basic
Property concept, then additional changes and modifications can be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as
It selects embodiment and falls into all change and modification of the application range.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
God and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (12)
1. the detection method that a kind of safety cap is worn, which is characterized in that this method includes：
Obtain correspondence at least two images acquired in synchronization mounted at least two image capture devices of different direction；
According at least two images, judge whether target pedestrian has worn safety cap；
If so, determining that the target pedestrian has worn safety cap；Otherwise, it determines the non-safe wearing cap of target pedestrian.
2. the method as described in claim 1, which is characterized in that at least two images described in the basis judge target pedestrian
Whether having worn safety cap includes：
According to pedestrian region in every image, the first object image for including the target pedestrian is determined；
In the first object image, it will detect that the image that the target pedestrian has worn safety cap is determined as the second target
Image；
Judge whether the ratio of the second quantity and the first quantity of the first object image of second target image is more than
Preset first fractional threshold, determines whether the target pedestrian has worn safety cap.
3. the method as described in claim 1, which is characterized in that at least two images described in the basis judge target pedestrian
Whether having worn safety cap includes：
According to pedestrian region in every image, the first object image for including the target pedestrian is determined；
In the first object image, the picture quality for filtering out the target pedestrian meets the third target figure of preset requirement
Picture；
In the third target image, detect whether the target pedestrian has worn safety cap.
4. method as claimed in claim 2 or claim 3, which is characterized in that in the target image, detect whether the target pedestrian wears
Having worn safety cap includes：
According to target pedestrian region, the subgraph of the head zone of the target pedestrian is determined；
The subgraph is input in the grader pre-saved, according to the classification results of the grader, determines the head
Whether the classification in portion region belongs to safe wearing cap classification；
If so, determining that the target pedestrian has worn safety cap；If not, determining the non-safe wearing cap of target pedestrian；
Or
If detecting safety cap in target pedestrian region, it is determined that the head zone of the target pedestrian is sentenced
Whether the safety cap that breaks is located within the scope of the corresponding predeterminable area of the head zone；
If so, determining that the target pedestrian has worn safety cap；If not, determining the non-safe wearing of target pedestrian
Cap.
5. method as claimed in claim 2 or claim 3, which is characterized in that it is described according to pedestrian region in every image, it determines
Including the first object image of the target pedestrian includes：
According to pedestrian region in every image, determine each region its preset corresponding image capture device image
Plane coordinates in plane coordinate system；
It is closed according to the plane of delineation coordinate system of the image capture device pre-saved and the mapping of the world coordinate system of construction scene
System, and each plane coordinates in region, determine world coordinates of the corresponding pedestrian in each region in the world coordinate system；
Image comprising the target pedestrian is determined as first object image.
6. the detection device that a kind of safety cap is worn, which is characterized in that the device includes：
Acquisition module, the correspondence that at least two image capture devices for obtaining mounted on different direction are acquired in synchronization
At least two images；
Judgment module judges whether target pedestrian has worn safety cap at least two images according to；
Determining module determines that the target pedestrian has worn safety cap for being yes when the judging result of the judgment module；When
The judging result of the judgment module is no, determines the non-safe wearing cap of the target pedestrian.
7. device as claimed in claim 6, which is characterized in that the judgment module is specifically used for according to row in every image
People region determines the first object image for including the target pedestrian；In the first object image, by detecting
It states target pedestrian and has worn the image of safety cap and be determined as the second target image；Judge the second quantity of second target image
Whether it is more than preset first fractional threshold with the ratio of the first quantity of the first object image, determines the target pedestrian
Whether safety cap has been worn.
8. device as claimed in claim 6, which is characterized in that the judgment module is specifically used for according to row in every image
People region determines the first object image for including the target pedestrian；In the first object image, filter out described
The picture quality of target pedestrian meets the third target image of preset requirement；In the third target image, the mesh is detected
Whether mark pedestrian has worn safety cap.
9. device as claimed in claim 7 or 8, which is characterized in that the judgment module is specifically used for according to the target line
People region determines the subgraph of the head zone of the target pedestrian；The subgraph is input to point pre-saved
In class device, according to the classification results of the grader, determine whether the classification of the head zone belongs to safe wearing cap class
Not；If so, determining that the target pedestrian has worn safety cap；If not, determining the non-safe wearing cap of target pedestrian；Or
If detecting safety cap in target pedestrian region, it is determined that the head zone of the target pedestrian judges institute
State whether safety cap is located within the scope of the corresponding predeterminable area of the head zone；If so, determining that the target pedestrian has worn
Safety cap is worn；If not, determining the non-safe wearing cap of target pedestrian.
10. device as claimed in claim 7 or 8, which is characterized in that the judgment module is specifically used for according to every image
Middle pedestrian region determines that each region is flat in the plane of delineation coordinate system of its preset corresponding image capture device
Areal coordinate；According to the mapping of the plane of delineation coordinate system of the image capture device pre-saved and the world coordinate system of construction scene
Relationship, and each plane coordinates in region, determine world coordinates of the corresponding pedestrian in each region in the world coordinate system；
Image comprising the target pedestrian is determined as first object image.
11. a kind of electronic equipment, which is characterized in that including：Processor, communication interface, memory and communication bus, wherein place
Device, communication interface are managed, memory completes mutual communication by communication bus；
It is stored with computer program in the memory, when described program is executed by the processor so that the processor
Perform claim requires the step of any one of 1~5 the method.
12. a kind of computer readable storage medium, which is characterized in that it is stored with the computer journey that can be executed by electronic equipment
Sequence, when described program is run on the electronic equipment so that the electronic equipment perform claim requires any one of 1~5 institute
The step of stating method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810267214.3A CN108564010A (en) | 2018-03-28 | 2018-03-28 | A kind of detection method, device, electronic equipment and storage medium that safety cap is worn |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810267214.3A CN108564010A (en) | 2018-03-28 | 2018-03-28 | A kind of detection method, device, electronic equipment and storage medium that safety cap is worn |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108564010A true CN108564010A (en) | 2018-09-21 |
Family
ID=63533208
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810267214.3A Pending CN108564010A (en) | 2018-03-28 | 2018-03-28 | A kind of detection method, device, electronic equipment and storage medium that safety cap is worn |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108564010A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109697430A (en) * | 2018-12-28 | 2019-04-30 | 成都思晗科技股份有限公司 | The detection method that working region safety cap based on image recognition is worn |
| CN110009006A (en) * | 2019-03-15 | 2019-07-12 | 华中科技大学 | A kind of point target detecting method and system based on machine learning |
| CN110070033A (en) * | 2019-04-19 | 2019-07-30 | 山东大学 | Safety cap wearing state detection method in a kind of power domain dangerous work region |
| CN110443976A (en) * | 2019-08-14 | 2019-11-12 | 深圳市沃特沃德股份有限公司 | Safety prompt function method, apparatus and storage medium based on safety cap |
| CN111091069A (en) * | 2019-11-27 | 2020-05-01 | 云南电网有限责任公司电力科学研究院 | Power grid target detection method and system guided by blind image quality evaluation |
| CN111126192A (en) * | 2019-12-10 | 2020-05-08 | 枣庄矿业（集团）有限责任公司蒋庄煤矿 | Underground coal mine object state recognition system based on deep learning |
| CN111553199A (en) * | 2020-04-07 | 2020-08-18 | 厦门大学 | Motor vehicle traffic violation automatic detection technology based on computer vision |
| CN111604888A (en) * | 2020-05-29 | 2020-09-01 | 珠海格力电器股份有限公司 | Inspection robot control method, inspection system, storage medium and electronic device |
| CN112784642A (en) * | 2019-11-08 | 2021-05-11 | 杭州海康威视数字技术股份有限公司 | Vehicle detection method and device |
| CN112906533A (en) * | 2021-02-07 | 2021-06-04 | 成都睿码科技有限责任公司 | Safety helmet wearing detection method based on self-adaptive detection area |
| CN113222882A (en) * | 2020-01-21 | 2021-08-06 | 上海铼钠克数控科技股份有限公司 | Cloth seam detection method and device, electronic equipment and storage medium |
| CN113221783A (en) * | 2021-05-20 | 2021-08-06 | 上海可深信息科技有限公司 | Low-resolution image helmet identification method |
| CN113283296A (en) * | 2021-04-20 | 2021-08-20 | 晋城鸿智纳米光机电研究院有限公司 | Helmet wearing detection method, electronic device and storage medium |
| CN113361347A (en) * | 2021-05-25 | 2021-09-07 | 东南大学成贤学院 | Job site safety detection method based on YOLO algorithm |
| CN113469043A (en) * | 2021-06-30 | 2021-10-01 | 南方科技大学 | Method and device for detecting wearing state of safety helmet, computer equipment and storage medium |
| CN114783144A (en) * | 2022-06-17 | 2022-07-22 | 深圳市易智博网络科技有限公司 | Intelligent building site safety monitoring method and device and computer equipment |
| CN118038491A (en) * | 2024-02-18 | 2024-05-14 | 四川明星新能源科技有限公司 | Dangerous area constructor electronic positioning management system |
| US20240212035A1 (en) * | 2018-04-16 | 2024-06-27 | Bird Rides, Inc. | On-demand rental of electric vehicles |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110141485A1 (en) * | 2009-12-16 | 2011-06-16 | Industrial Technology Research Institute | System and Method for Localizing a Carrier, Estimating a Posture of the Carrier and Establishing a Map |
| CN104063722A (en) * | 2014-07-15 | 2014-09-24 | 国家电网公司 | Safety helmet identification method integrating HOG human body target detection and SVM classifier |
| CN104517292A (en) * | 2014-12-25 | 2015-04-15 | 杭州电子科技大学 | Multi-camera high-density crowd partitioning method based on planar homography matrix restraint |
| CN105469038A (en) * | 2015-11-19 | 2016-04-06 | 国网福建省电力有限公司泉州供电公司 | Safety cap video detection method for electric power switching station |
| CN106203497A (en) * | 2016-07-01 | 2016-12-07 | 浙江工业大学 | A kind of finger vena area-of-interest method for screening images based on image quality evaluation |
| CN106408000A (en) * | 2016-08-25 | 2017-02-15 | 国网浙江省电力公司杭州供电公司 | Method and device for intelligent detection on personnel safety helmet |
| CN106548131A (en) * | 2016-10-14 | 2017-03-29 | 南京邮电大学 | A kind of workmen's safety helmet real-time detection method based on pedestrian detection |
| CN106878670A (en) * | 2016-12-24 | 2017-06-20 | 深圳云天励飞技术有限公司 | A kind of method for processing video frequency and device |
| CN107292252A (en) * | 2017-06-09 | 2017-10-24 | 南京华捷艾米软件科技有限公司 | A kind of personal identification method of autonomous learning |
-
2018
- 2018-03-28 CN CN201810267214.3A patent/CN108564010A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110141485A1 (en) * | 2009-12-16 | 2011-06-16 | Industrial Technology Research Institute | System and Method for Localizing a Carrier, Estimating a Posture of the Carrier and Establishing a Map |
| CN104063722A (en) * | 2014-07-15 | 2014-09-24 | 国家电网公司 | Safety helmet identification method integrating HOG human body target detection and SVM classifier |
| CN104517292A (en) * | 2014-12-25 | 2015-04-15 | 杭州电子科技大学 | Multi-camera high-density crowd partitioning method based on planar homography matrix restraint |
| CN105469038A (en) * | 2015-11-19 | 2016-04-06 | 国网福建省电力有限公司泉州供电公司 | Safety cap video detection method for electric power switching station |
| CN106203497A (en) * | 2016-07-01 | 2016-12-07 | 浙江工业大学 | A kind of finger vena area-of-interest method for screening images based on image quality evaluation |
| CN106408000A (en) * | 2016-08-25 | 2017-02-15 | 国网浙江省电力公司杭州供电公司 | Method and device for intelligent detection on personnel safety helmet |
| CN106548131A (en) * | 2016-10-14 | 2017-03-29 | 南京邮电大学 | A kind of workmen's safety helmet real-time detection method based on pedestrian detection |
| CN106878670A (en) * | 2016-12-24 | 2017-06-20 | 深圳云天励飞技术有限公司 | A kind of method for processing video frequency and device |
| CN107292252A (en) * | 2017-06-09 | 2017-10-24 | 南京华捷艾米软件科技有限公司 | A kind of personal identification method of autonomous learning |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20240212035A1 (en) * | 2018-04-16 | 2024-06-27 | Bird Rides, Inc. | On-demand rental of electric vehicles |
| CN109697430A (en) * | 2018-12-28 | 2019-04-30 | 成都思晗科技股份有限公司 | The detection method that working region safety cap based on image recognition is worn |
| CN110009006A (en) * | 2019-03-15 | 2019-07-12 | 华中科技大学 | A kind of point target detecting method and system based on machine learning |
| CN110070033A (en) * | 2019-04-19 | 2019-07-30 | 山东大学 | Safety cap wearing state detection method in a kind of power domain dangerous work region |
| CN110443976A (en) * | 2019-08-14 | 2019-11-12 | 深圳市沃特沃德股份有限公司 | Safety prompt function method, apparatus and storage medium based on safety cap |
| CN110443976B (en) * | 2019-08-14 | 2021-05-28 | 深圳市沃特沃德股份有限公司 | Safety reminding method and device based on safety helmet and storage medium |
| CN112784642A (en) * | 2019-11-08 | 2021-05-11 | 杭州海康威视数字技术股份有限公司 | Vehicle detection method and device |
| CN111091069A (en) * | 2019-11-27 | 2020-05-01 | 云南电网有限责任公司电力科学研究院 | Power grid target detection method and system guided by blind image quality evaluation |
| CN111126192A (en) * | 2019-12-10 | 2020-05-08 | 枣庄矿业（集团）有限责任公司蒋庄煤矿 | Underground coal mine object state recognition system based on deep learning |
| CN113222882A (en) * | 2020-01-21 | 2021-08-06 | 上海铼钠克数控科技股份有限公司 | Cloth seam detection method and device, electronic equipment and storage medium |
| CN111553199A (en) * | 2020-04-07 | 2020-08-18 | 厦门大学 | Motor vehicle traffic violation automatic detection technology based on computer vision |
| CN111604888B (en) * | 2020-05-29 | 2021-09-14 | 珠海格力电器股份有限公司 | Inspection robot control method, inspection system, storage medium and electronic device |
| CN111604888A (en) * | 2020-05-29 | 2020-09-01 | 珠海格力电器股份有限公司 | Inspection robot control method, inspection system, storage medium and electronic device |
| CN112906533A (en) * | 2021-02-07 | 2021-06-04 | 成都睿码科技有限责任公司 | Safety helmet wearing detection method based on self-adaptive detection area |
| CN113283296A (en) * | 2021-04-20 | 2021-08-20 | 晋城鸿智纳米光机电研究院有限公司 | Helmet wearing detection method, electronic device and storage medium |
| CN113221783A (en) * | 2021-05-20 | 2021-08-06 | 上海可深信息科技有限公司 | Low-resolution image helmet identification method |
| CN113361347A (en) * | 2021-05-25 | 2021-09-07 | 东南大学成贤学院 | Job site safety detection method based on YOLO algorithm |
| CN113469043A (en) * | 2021-06-30 | 2021-10-01 | 南方科技大学 | Method and device for detecting wearing state of safety helmet, computer equipment and storage medium |
| CN114783144A (en) * | 2022-06-17 | 2022-07-22 | 深圳市易智博网络科技有限公司 | Intelligent building site safety monitoring method and device and computer equipment |
| CN118038491A (en) * | 2024-02-18 | 2024-05-14 | 四川明星新能源科技有限公司 | Dangerous area constructor electronic positioning management system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108564010A (en) | A kind of detection method, device, electronic equipment and storage medium that safety cap is worn | |
| Shen et al. | Detecting safety helmet wearing on construction sites with bounding‐box regression and deep transfer learning | |
| Gaur et al. | Video flame and smoke based fire detection algorithms: A literature review | |
| CN108062349B (en) | Video monitoring method and system based on video structured data and deep learning | |
| CN108416250B (en) | People counting method and device | |
| JP5980148B2 (en) | How to measure parking occupancy from digital camera images | |
| US20240062518A1 (en) | Method, apparatus, computer device and storage medium for detecting objects thrown from height | |
| CN106296721B (en) | Object aggregation detection method and device based on stereoscopic vision | |
| CN110264495B (en) | Target tracking method and device | |
| US8243987B2 (en) | Object tracking using color histogram and object size | |
| WO2019083738A9 (en) | Methods and systems for applying complex object detection in a video analytics system | |
| US9008365B2 (en) | Systems and methods for pedestrian detection in images | |
| CN110807385A (en) | Target detection method and device, electronic equipment and storage medium | |
| CN111160125A (en) | Railway foreign matter intrusion detection method based on railway monitoring | |
| CN109670383B (en) | Video shielding area selection method and device, electronic equipment and system | |
| JP2004534315A (en) | Method and system for monitoring moving objects | |
| CN102673979B (en) | Method and device for judging deviation of conveying belt | |
| JP2004537790A (en) | Moving object evaluation system and method | |
| Ko et al. | Survey of computer vision–based natural disaster warning systems | |
| CN101167086A (en) | Human detection and tracking for security applications | |
| JP2004531842A (en) | Method for surveillance and monitoring systems | |
| US9317765B2 (en) | Human image tracking system, and human image detection and human image tracking methods thereof | |
| US20220309635A1 (en) | Computer vision-based anomaly detection method, device and electronic apparatus | |
| CN109766779A (en) | It hovers personal identification method and Related product | |
| CN112270253A (en) | High-altitude parabolic detection method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180921 |