bymaths/probabilistic_triangulation
Probabilistic triangulation module applied to uncalibrated human pose estimation
This helps researchers and developers working in computer vision and graphics accurately track human movement in 3D from multiple camera angles without the need for precise camera setup. It takes in 2D video feeds of a person from different views and outputs a 3D model of their pose. This is ideal for those developing applications that need to understand how people move, such as for animation, sports analysis, or human-computer interaction.
No commits in the last 6 months.
Use this if you need to perform 3D human pose estimation from multiple camera views in environments where calibrating cameras is difficult or impossible.
Not ideal if you only have a single camera view or if your application requires extremely high real-time performance on constrained hardware without a dedicated GPU.
Stars
45
Forks
5
Language
Jupyter Notebook
License
—
Category
Last pushed
Mar 20, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/bymaths/probabilistic_triangulation"
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.