Greedy nearest-neighbour
Two-pass greedy association on predicted position, constant-velocity prediction, fixed 2 s coasting. Deliberately simple — the published floor every improvement must beat.
Tracker model benchmark
Two tracker models, one identical fixed-seed synthetic scene with perfect ground truth. The sensor model, detection generation, difficulty settings, and metric definitions are byte-identical between models — only the tracker differs. Reproduce every row yourself: open the live demonstration and press "Run benchmark". No signup, no NDA, no clearance.
01The models
Confirmed-track auction
Track confirmation, three-tier auction association, velocity-consistency gating tuned to the scene's physics, a noise-scaled reservation price against cross-grabs, and confidence-decayed coasting.
02Results — identity switches per minute
| Config | Movers | Sensor | Occl. | Contrast | Detection | v1 sw/min | v2 sw/min | Δ |
|---|---|---|---|---|---|---|---|---|
| baseline | 150 | 2 fps | 0 % | 100 % | 88 % | 2 042 | 1 183 | −42.1 % |
| dense | 400 | 2 fps | 0 % | 100 % | 73 % | 14 032 | 8 040 | −42.7 % |
| frame-starved | 150 | 0.5 fps | 0 % | 100 % | 88 % | 3 467 | 2 890 | −16.6 % |
| occluded | 150 | 2 fps | 20 % | 100 % | 72 % | 2 698 | 2 196 | −18.6 % |
| degraded | 300 | 1 fps + 2 px | 15 % | 70 % | 65 % | 8 974 | 7 352 | −18.1 % |
SEED 1337 · 20 s WARM-UP + 120 s MEASURED PER ROW · DETECTION IS A SENSOR PROPERTY — IDENTICAL FOR BOTH MODELS BY CONSTRUCTION · V2 RUNTIME ~1.2 ms AVG PER SENSOR TICK AT DENSITY 400 (BUDGET 10 ms)
03Method
ID switches/min counts every change of the track identity assigned to a ground-truth object — deliberately stricter than the MOT-challenge IDSW definition, because fragmentations and re-acquisitions count as switches too. Detection is detections ÷ true objects per sensor frame. The fixed seed makes every row reproducible: same numbers on every run in the same browser, and the matrix above was additionally reproduced headless (two identical runs) before publication.
Why we publish failure numbers: both models still commit thousands of identity errors per minute under stress, and those rows stay on this page on purpose. Synthetic scenes provide perfect ground truth, so these are measurements, not marketing. Every future tracker model must land here as a new column against the same seed — in public. Every demonstration slice stays runnable as shipped: slice 1, slice 2 (tracker v1), slice 3 (tracker v2, current).
FULLY SYNTHETIC — EVERY PIXEL GENERATED. NO REAL PERSONS, VEHICLES, OR PLACES.