OpenDR human activity recognition demo

Live demo of online human activity recognition using the OpenDR toolkit.

Installation

git clone https://github.com/LukasHedegaard/opendr-activity-recognition-demo.git
cd opendr-activity-recognition-demo
pip install -e .

In addition, you need to install the OpenDR toolkit (which is not publicly available yet)

Running the example

Human Activity Recognition using X3D

python demo.py --ip 0.0.0.0 --port 8000 --algorithm x3d --model xs

Human Activity Recognition using CoX3D

python demo.py --ip 0.0.0.0 --port 8000 --algorithm cox3d --model s

If you navigate your piano and http://0.0.0.0:8000 and pick up a ukulele, you might see something like this:

For other options, see python demo.py --help

Troubleshooting

If no video is displayed for any of the methods, you may try to select another video source using the --video_source flag:

python demo.py --ip 0.0.0.0 --port 8000 --algorithm cox3d --model s --video_source 1

Acknowledgement

This work has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 871449 (OpenDR). This publication reflects the authors’ views only. The European Commission is not responsible for any use that may be made of the information it contains.