End-to-End Workflow

MAT Workflow

1. Load video and outputs
2. Set input video, CSV output, optional rendered video output.
3. Calibrate detection
4. Pick detection mode.
5. Use preview/test detection before full run.
6. Configure tracking
7. Set MAX_TARGETS, assignment distance, track lifecycle thresholds.
8. Run forward/backward tracking
9. Enable backward pass for better conflict resolution.
10. Post-process and export
11. Resolve identities, interpolate gaps as needed.
12. Save final CSV and optional diagnostics.

PoseKit Workflow

1. Load image set and project settings.
2. Label or refine keypoints frame-by-frame.
3. Use tools (smart select, metadata tags, split generation).
4. Export/prepare training-ready datasets.

Decision Points That Matter Most

• Detection mode affects raw input quality to tracker.
• Reference body size scales multiple heuristics.
• Post-processing can fix or amplify detection mistakes depending on thresholds.

Failure Pattern Checklist

• If targets merge often: tighten morphology and assignment distance.
• If tracks fragment: increase recovery/lost frame thresholds and validate detection confidence.
• If runtime is slow: reduce resize factor, disable non-critical overlays/histograms, verify GPU backend.