Open Source Computer Vision Library

Caffe: a fast open framework for deep learning.

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

Useful CMake Examples

🤘 awesome-semantic-segmentation

Real-Time SLAM for Monocular, Stereo and RGB-D Cameras, with Loop Detection and Relocalization Capabilities

机器人视觉 移动机器人 VS-SLAM ORB-SLAM2 深度学习目标检测 yolov3 行为检测 opencv PCL 机器学习 无人驾驶

Intel® RealSense™ SDK

Cartographer is a system that provides real-time simultaneous localization and mapping (SLAM) in 2D and 3D across multiple platforms and sensor configurations.

ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM

edition 2 of the slambook

The official documentation for Raspberry Pi computers and microcontrollers

A Robust and Versatile Monocular Visual-Inertial State Estimator

The Kalibr visual-inertial calibration toolbox

An optimization-based multi-sensor state estimator

Python package for the evaluation of odometry and SLAM

SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)

The OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919

g2o: A General Framework for Graph Optimization

Semantic Segmentation on PyTorch (include FCN, PSPNet, Deeplabv3, Deeplabv3+, DANet, DenseASPP, BiSeNet, EncNet, DUNet, ICNet, ENet, OCNet, CCNet, PSANet, CGNet, ESPNet, LEDNet, DFANet)

学习C & C++ & python&汇编语言 LLVM编译器 数据结构 算法 操作系统 单片机 linux 面试

Pytorch implementation of U-Net, R2U-Net, Attention U-Net, and Attention R2U-Net.

LSD-SLAM

Semantic Segmentation Suite in TensorFlow. Implement, train, and test new Semantic Segmentation models easily!

ROS Wrapper for Intel(R) RealSense(TM) Cameras

LeGO-LOAM: Lightweight and Ground-Optimized Lidar Odometry and Mapping on Variable Terrain

Pangolin is a lightweight portable rapid development library for managing OpenGL display / interaction and abstracting video input.

中国大学MOOC《机器人操作系统入门》课程代码示例

Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021, T-PAMI 2022