Post-processing for object detection models
Model version:
A postprocessing layer that allows you to track bounding boxes across inference runs,
turning raw bounding boxes into stable “tracked” detections with unique identifiers.
This can also significantly reduce jitter and provide continuity of object labels across frames.
Learn block thresholds
Score threshold
0.2
Preview
Sample:
No object tracking results yet, click "Render preview" first.
This video is using a different aspect ratio
(1280×720)
than your impulse
(640×640).
Frames are squashed before running inference.
For the most representative results, use the same aspect ratio as your impulse.
