timctho/convolutional-pose-machines-tensorflow
A TensorFlow implementation of Convolutional Pose Machines for 2D body and hand pose estimation.
Not currently ranked — collecting fresh signals.
star history
This repository provides a TensorFlow implementation of the Convolutional Pose Machines model, a deep learning approach for 2D human body and hand pose estimation. It includes multi-stage graph construction for sequential heatmap prediction, Kalman filters for smoothing pose outputs, and a simple self-tracking module. The project supports body pose estimation, hand pose estimation, and tracking through webcam input or video files.
Frequently asked
- What is timctho/convolutional-pose-machines-tensorflow?
- A TensorFlow implementation of Convolutional Pose Machines for 2D body and hand pose estimation.
- Is convolutional-pose-machines-tensorflow open source?
- Yes — timctho/convolutional-pose-machines-tensorflow is open source, released under the Apache-2.0 license.
- What language is convolutional-pose-machines-tensorflow written in?
- timctho/convolutional-pose-machines-tensorflow is primarily written in Python.
- How popular is convolutional-pose-machines-tensorflow?
- timctho/convolutional-pose-machines-tensorflow has 796 stars on GitHub.
- Where can I find convolutional-pose-machines-tensorflow?
- timctho/convolutional-pose-machines-tensorflow is on GitHub at https://github.com/timctho/convolutional-pose-machines-tensorflow.