Human Activity Recognition (HAR) include recognition of human falls, fights, lying and sitting in video streams and video files.
The following configuration is required to enable HAR on a single Full HD @ 25fps video stream:
- GPU: performance ~FP32 10 TFLOPS; 3GB VRAM; CUDA11 Runtime;
- RAM: +4Gb;
- CPU: 2 AVX cores @3GHz.
When an activity type is detected, OMNI Agent generates an activity process and sends it to OMNI Platform or to a third-party service.
How to Enable HAR
Open the run_params.json configuration file and set "true" in the
When enabling HAR, we recommend using:
- CUDA: set "true" in the
use_cuda_onnxfield of the run_params.json file or enable "CUDA usage" option in Settings of OMNI Agent web-interface.
For stable work of OMNI Agent, disable the generation of face biometric templates. To do this, open the run_params.json configuration file and set "false" in the