Skip to content

Real time human activity recognition using tensorflow openpose and LSTM

License

Notifications You must be signed in to change notification settings

chinmayembedded/Human-Activity-Recognition

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Human Activity Recognition

This module detects Real time human activities such as throwing, jumping, jumping_jacks, boxing, sitting.

FPS 20-25 on Nvidia AGX Xavier

Install

Dependencies

You need dependencies below.

  • python3
  • tensorflow 1.4.1+
$ pip3 install --pre --extra-index-url https://developer.download.nvidia.com/compute/redist/jp/v411 tensorflow-gpu
$cd Human-Activity-Recognition
$pip3 install requirements.txt
$sudo apt-get install swig
$cd tf_pose/pafprocess
$swig -python -c++ pafprocess.i && python3 setup.py build_ext --inplace
$cd ../..

Realtime Webcam

$ python3 run_webcam.py webcam0 abc abc

Prerecorded Video

$ python3 run_webcam.py video-path abc abc

About

Real time human activity recognition using tensorflow openpose and LSTM

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published