Summarize Tracked PPE

How it fits

Typical backends

Caveats

• Hard constraintThe three input lists are consumed positionally and must have equal length; a length mismatch aborts the call rather than truncating.
• Hard constraintEach classifier probability vector must hold exactly two entries (missing-PPE then present-PPE); any other length aborts the call.
• AccuracyA track's running probability is weighted by body-part detection confidence and the unfilled history slots are padded with the prior, so a person just entering view leans toward the prior until enough confident crops accumulate.
• I/O contractCrops below the configured minimum width or height are dropped before reaching a track's history, so a person seen only at small scale can sit in the uncertain band because no sample qualified.
• Parameter interactionThe status has three bands (present / uncertain / missing); collapsing or inverting positive_confidence_threshold against negative_confidence_threshold removes the uncertain band and lets the missing-PPE verdict take precedence.
• Parameter interactionKeep forget_num_frames at least as large as the upstream tracker's own forget window so the tracker does not reference ids this component has already discarded.
• State lifetimeConfiguration is captured once at the first tick; later changes do not take effect, and an empty input batch returns an empty list without touching per-track state.