nimanthakasun/cnn_robotarm
This project implements a markerless motion capture system using Convolutional Neural Networks (CNNs) to estimate 3D human poses from video input without any markers or sensor systems
This system helps you analyze human movement in 3D space directly from standard video footage, without needing special suits, markers, or sensors. You provide video recordings of a person, and it outputs a detailed 3D representation of their body pose. It's ideal for professionals in fields like biomechanics or robotics who need to understand human motion.
No commits in the last 6 months.
Use this if you need to accurately track and analyze 3D human body movements from video for applications like physical therapy analysis, athletic performance review, or robot interaction design.
Not ideal if you require a simple 2D motion tracking solution or if your primary goal is real-time interaction with a robot that already has integrated sensor systems.
Stars
8
Forks
—
Language
Python
License
—
Category
Last pushed
Aug 10, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nimanthakasun/cnn_robotarm"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
talmolab/sleap
A deep learning framework for multi-animal pose tracking.
kennymckormick/pyskl
A toolbox for skeleton-based action recognition.
open-mmlab/mmaction2
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
jgraving/DeepPoseKit
a toolkit for pose estimation using deep learning
kenshohara/3D-ResNets-PyTorch
3D ResNets for Action Recognition (CVPR 2018)