computer vision and sports

Cybervision can generate a 3D model from two photos of an object

Vision-based GNSS-Free Localization for UAVs in the Wild

SoccerNet@CVPR | 1st place solution for Camera Calibration Challenge 2023

Official implementation of DeepLabCut: Markerless pose estimation of user-defined features with deep learning for all animals incl. humans

2D keypoint detection with Pytorch Lightning and wandb

Predictions of the four corners of documents.

PyTorch-based toolkit for landmark detection

This project utilizes various computer vision techniques to track two tennis players, a court's key-points, and a tennis ball. It also measures the players' ball shot speed, movement speed and number of shots that they have taken.

50356-Images-Human-Body-Segmentation-and-18-Landmarks-Data

25581-Images-88-Facial-Landmarks-Annotation-Data

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

Computer vision library for wildfire detection 🌲 Deep learning models in PyTorch & ONNX for inference on edge devices (e.g. Raspberry Pi)

This computer vision project analyzes tennis match videos using cutting-edge techniques. It employs YOLOv8 for player detection, finetuned YOLO for ball tracking, and ResNet50 for extracting court keypoints. Additionally, it calculates player and ball speeds and generates a mini court reflecting player positions.

ml experiments

Unofficial simplified implementation of Painter (2023 CVPR)

Microsoft COCO: Common Objects in Context for huggingface datasets

ORB (Oriented FAST and Rotated BRIEF)

Foot Classification Project and Other Experiments with YOLOv8

一份关于yolov8的入门级(训练+预测)的代码demo（目标检测/实例分割/关键点检测........）； A code demo about yolov8's entry-level (training + prediction) (object detection/instance segmentation/key point detection...)