Human action recognition (HAR)

HAR (Human Action Recognition) includes recognition of human falls, fights, lying and sitting in video streams and video files. When an action type is detected, OMNI Agent generates a process and an event which can be sent to OMNI Platform or to a third-party service.

How to enable HAR

Open the configuration file run_params.json and set true in the action_recognition.enabled field.

To enable HAR event sending, set true in the corresponding field depending on the type of event:

• events.har_events.fall.enable — fall
• events.har_events.fight.enable — fight
• events.har_events.sit.enable — sitting
• events.har_events.lie.enable — lying

info

When enabling HAR, we recommend using:

• CUDA: set "true" in the use_cuda_onnx field of the run_params.json file or enable "CUDA usage" option in Settings of OMNI Agent web-interface.

caution

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 pipelines.face.enable_templates_generation field.