YuliangXiu/PoseFlow
PoseFlow: Efficient Online Pose Tracking (BMVC'18)
This helps analysts and researchers accurately follow the movement of multiple individuals in video recordings. It takes a video and initial estimations of people's poses frame-by-frame, then outputs a refined sequence showing each person's consistent pose over time. Anyone working with human movement analysis in video, such as in sports science, behavioral research, or safety monitoring, would find this useful.
440 stars. No commits in the last 6 months.
Use this if you need to reliably track the specific body poses of several people across an entire video sequence.
Not ideal if you only need to detect individual poses in single frames without tracking their movement over time.
Stars
440
Forks
90
Language
C++
License
—
Category
Last pushed
May 03, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/YuliangXiu/PoseFlow"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
DeepLabCut/DeepLabCut
Official implementation of DeepLabCut: Markerless pose estimation of user-defined features with...
openpifpaf/openpifpaf
Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and...
lambdaloop/anipose
🐜🐀🐒🚶 A toolkit for robust markerless 3D pose estimation
DIYer22/bpycv
Computer vision utils for Blender (generate instance annoatation, depth and 6D pose by one line code)
NeLy-EPFL/DeepFly3D
Motion capture (markerless 3D pose estimation) pipeline and helper GUI for tethered Drosophila.