OpenMMLab Pose Estimation Toolbox and Benchmark.
RTMPose series (RTMPose, DWPose, RTMO, RTMW) without mmcv, mmpose, mmdet etc.
Compute 2D human pose and angles from a video or a webcam.
juxtapose: Multi-Person Pose Tracking Inference SDK with RTMDet, YOLOv8, GDino, RTMPose (ONNX) & Trackers (ByteTrack & BotSORT) & Tapnet with custom ROIs + FastAPI GPU exe
A fully automated, markerless extrinsic camera calibration pipeline using human motion. Features RTMPose or Metrabs, 3D lifting, and real-world metric scaling.
Markerless motion capture with GoPro
High-performance browser-based AI library for real-time object detection (YOLO12) and pose estimation (RTMW) using ONNX Runtime Web
Two-stage skeleton-based action recognition: YOLOv8 + RTMPose + ST-GCN, C++ on NVIDIA DeepStream / TensorRT
A high-performance, multi-threaded C++ pipeline for real-time multi-camera keypoint detection.
Tennis broadcast analysis pipeline: F3ED shot detection + scoreboard OCR + score-delta reconciler that recovers events the model has no class for (aces, double-faults, first-serve faults). Two-phase Colab→local.
AI pull-up detection & technique scoring from video — RTMPose pose estimation, rep counting and GTO-standard violation detection. FastAPI CV engine + Flask web platform.
Real-time home training posture feedback system using pose estimation and TCN-based exercise quality classification.
High-Precision Human Velocity Analysis Framework
from a gait video to recognition emotion
Track Analyzer is the first mobile app providing high-level motion analysis for athletics balancing accuracy, speed, accessibility and portability. By using pose estimation AI models, the system provides immediate and accurate feedback on technical gestures without expensive hardware.
Experiment: real-time human pose estimation desktop app built with Tauri v2 + WebAssembly (RTMPose/ONNX). Compared with a Flutter implementation.
On-device real-time pose estimation with RTMPose + ONNX Runtime. Flutter Web & desktop. Live demo on GitHub Pages.
Official implementation of lightweight spatial representation enhancement for RTMPose, featuring P4/P5 semantic-detail fusion and Scale-Adaptive Crop Resolution (SACR).
Train RTMPose on custom keypoint datasets. Includes YOLO-to-COCO preprocessing, 18-keypoint config, and full training/inference workflow for MMPose.
Add a description, image, and links to the rtmpose topic page so that developers can more easily learn about it.
To associate your repository with the rtmpose topic, visit your repo's landing page and select "manage topics."