Customizing frame-drawing using the Hailo 8L chip on a Raspberry Pi 5

General
,
1

I’m working on a Raspberry Pi 5 project using the Hailo 8L chip, where I currently have a YOLO model tracking people. I’d like to implement some additional features related to “drawing on frames,” such as:

  1. Deciding my own bounding box colors for each object.
  2. Drawing static lines on the frame.
  3. Applying my own clustering algorithm to group people into clusters and drawing the cluster boundaries.
  4. Enhancing the current tracking logic (I’m using hailo_tracker, but it’s not customizable enough for my needs).

Are there tools compatible with the Hailo 8L that allow these enhancements without retraining the model? Any suggestions or examples would be greatly appreciated!

This is my pipeline:

    pipeline = (
        f"{SOURCE_PIPELINE('rpi')} "
        f"{INFERENCE_PIPELINE(self.config['paths']['model']['hef_path'], self.config['paths']['model']['post_process_path'], batch_size=1, additional_params=inference_params)} ! "
        f"{TRACKER_PIPELINE()} ! "
        f"{USER_CALLBACK_PIPELINE()} ! "
        f"{DISPLAY_PIPELINE(video_sink='xvimagesink', sync='false', show_fps='true')}"
    )

and this is the tracker_pipeline:

tracker_pipeline = (
    f'{QUEUE(name=f"{name}_q")} ! '
    f'hailotracker name={name} '
    'keep-tracked-frames=30 '     # Keep track for ~1 sec at 30fps
    'keep-new-frames=15 '         # Half second to confirm new track
    'keep-lost-frames=5 '        # Half second before considering track lost
)