Try the live demo

RoadSight

Finds traffic events in fixed-camera CCTV video and scores accident risk frame by frame. Fully offline, on one GPU.

Give RoadSight one road-camera MP4. It returns every event as [start, end, label], from stopped vehicles and congestion to wrong-way driving, jaywalking and collisions. It also emits a risk score for every frame that uses only the frames seen so far.

How a video flows through it

Video DetectorYOLO11, FP16 TrackerByteTrack Kinematicsspeed, heading Rule engine14 detectors Post-processmerge, clip Events Scene: lanes, lines, zones Causal copypast frames only Risk featurestime to collision, braking Logistic + EMA Risk 0 to 1

Green boxes are learned; everything else is explicit, tunable rules. Read the approach.

What it measures on the sample videos

Loading sample results.

See it on real footage

Annotated sample videos with boxes, track IDs, active events and the risk curve. Open the results.

Run your own clip

Upload an MP4 of up to two minutes and get the event table, timeline and annotated playback. Open the live demo.

What worked and what did not

The one-page technical report, with measured runtimes and ablations. Read the report.