jimmyyhwu/pose-interpreter-networks
Real-time robotic object pose estimation with deep learning
This project helps industrial automation engineers and roboticists accurately identify and locate objects in a robot's workspace using standard camera feeds. It takes live color images from a camera as input and outputs the precise 3D position and orientation of target objects. This system is designed for professionals building or deploying robotic systems that need to manipulate or interact with specific physical items.
127 stars. No commits in the last 6 months.
Use this if you need a robotic system to quickly and accurately determine the 3D pose of objects using only a standard RGB camera, especially when you want to avoid expensive manual pose data annotation for training.
Not ideal if your application requires the system to identify objects without any prior training, or if you cannot provide 3D mesh models of the objects you want to detect.
Stars
127
Forks
28
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Apr 11, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jimmyyhwu/pose-interpreter-networks"
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
DenisTome/Lifting-from-the-Deep-release
Implementation of "Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image"