🚀 Added

• Detections.mask to enable segmentation support. (#58)
• MaskAnnotator to allow easy Detections.mask annotation. (#58)
• Detections.from_sam to enable native Segment Anything Model (SAM) support. (#58)

🌱 Changed

• Detections.area behaviour to work not only with boxes but also with masks. (#58)

🏆 Contributors

• @SkalskiP

🚀 Added

• Detections.empty to allow easy creation of empty Detections objects. (#48)
• Detections.from_roboflow to allow easy creation of Detections objects from Roboflow API inference results. (#56)
• plot_images_grid to allow easy plotting of multiple images on single plot. (#56)
• Initial support for Pascal VOC XML format with detections_to_voc_xml method. (#56)

🌱 Changed

• show_frame_in_notebook refactored and renamed to plot_image. (#56)

🏆 Contributors

• @SkalskiP

🌱 Changed

• Drop requirement for class_id in sv.Detections (#50) to make it more flexible

🏆 Contributors

• @SkalskiP

🌱 Changed

• Detections.wth_nms support class agnostic and non-class agnostic case (#36)

🛠️ Fixed

• PolygonZone throws an exception when the object touches the bottom edge of the image (#41)
• Detections.wth_nms method throws an exception when Detections is empty (#42)

🏆 Contributors

• @SkalskiP

🚀 Added

New methods in sv.Detections API:

• from_transformers - convert Object Detection 🤗 Transformer result into sv.Detections
• from_detectron2 - convert Detectron2 result into sv.Detections
• from_coco_annotations - convert COCO annotation into sv.Detections
• area - dynamically calculated property storing bbox area
• with_nms - initial implementation (only class agnostic) of sv.Detections NMS

🌱 Changed

• Make sv.Detections.confidence field Optional.

🏆 Contributors

• @SkalskiP

🔪 Killer features

• Support for PolygonZone and PolygonZoneAnnotator 🔥

import numpy as np
import supervision as sv
from ultralytics import YOLO

# initiate polygon zone
polygon = np.array([
    [1900, 1250],
    [2350, 1250],
    [3500, 2160],
    [1250, 2160]
])
video_info = sv.VideoInfo.from_video_path(MALL_VIDEO_PATH)
zone = sv.PolygonZone(polygon=polygon, frame_resolution_wh=video_info.resolution_wh)

# initiate annotators
box_annotator = sv.BoxAnnotator(thickness=4, text_thickness=4, text_scale=2)
zone_annotator = sv.PolygonZoneAnnotator(zone=zone, color=sv.Color.white(), thickness=6, text_thickness=6, text_scale=4)

# extract video frame
generator = sv.get_video_frames_generator(MALL_VIDEO_PATH)
iterator = iter(generator)
frame = next(iterator)

# detect
model = YOLO('yolov8s.pt')
results = model(frame, imgsz=1280)[0]
detections = sv.Detections.from_yolov8(results)
detections = detections[detections.class_id == 0]
zone.trigger(detections=detections)

# annotate
box_annotator = sv.BoxAnnotator(thickness=4, text_thickness=4, text_scale=2)
labels = [f"{model.names[class_id]} {confidence:0.2f}" for _, confidence, class_id, _ in detections]
frame = box_annotator.annotate(scene=frame, detections=detections, labels=labels)
frame = zone_annotator.annotate(scene=frame)

• Advanced vs.Detections filtering with pandas-like API.

detections = detections[(detections.class_id == 0) & (detections.confidence > 0.5)]

• Improved integration with YOLOv5 and YOLOv8 models.

import torch
import supervision as sv

model = torch.hub.load('ultralytics/yolov5', 'yolov5x6')
results = model(frame, size=1280)
detections = sv.Detections.from_yolov5(results)

from ultralytics import YOLO
import supervision as sv

model = YOLO('yolov8s.pt')
results = model(frame, imgsz=1280)[0]
detections = sv.Detections.from_yolov8(results)

🚀 Added

• supervision.get_polygon_center function - takes in a polygon as a 2-dimensional numpy.ndarray and returns the center of the polygon as a Point object
• supervision.draw_polygon function - draw a polygon on a scene
• supervision.draw_text function - draw a text on a scene
• supervision.ColorPalette.default() - class method - to generate default ColorPalette
• supervision.generate_2d_mask function - generate a 2D mask from a polygon
• supervision.PolygonZone class - to define polygon zones and validate if supervision.Detections are in the zone
• supervision.PolygonZoneAnnotator class - to draw supervision.PolygonZone on scene

🌱 Changed

• VideoInfo API - change the property name resolution -> resolution_wh to make it more descriptive; convert VideoInfo to dataclass
• process_frame API - change argument name frame -> scene to make it consistent with other classes and methods
• LineCounter API - rename class LineCounter -> LineZone to make it consistent with PolygonZone
• LineCounterAnnotator API - rename class LineCounterAnnotator -> LineZoneAnnotator

🏆 Contributors

• @SkalskiP
• @capjamesg

🚀 Added

• ⓒ Add project license
• 🎨 DEFAULT_COLOR_PALETTE, Color, and ColorPalette classes
• 📐 initial implementation of Point, Vector, and Rect classes
• 🎬 VideoInfo and VideoSink classes as well as get_video_frames_generator
  -📓 show_frame_in_notebook util
• 🖌️ draw_line, draw_rectangle, draw_filled_rectangle utils added
• 📦 Initial version Detections and BoxAnnotator added
• 🧮 initial implementation of LineCounter and LineCounterAnnotator classes

🏆 Contributors

@SkalskiP