Post-processing for object detection models BETA
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. Best suited for tracking objects that move in smooth, predictable paths, such as along a conveyor belt.
More info.
Preview options
Leave empty to show all objects. Separate classes by ','.
