← ProjectsComputer Vision2026Deployed

Plate Tracker

A YOLOv8 license-plate detector's raw per-frame output, replayed as a clickable overlay in sync with the source video — no live inference, no backend.

YOLOv8UltralyticsByteTrackReactSVG
1,800
Frames processed
83.7%
Frames with a detection
2,052
Boxes replayed
01

Introduction

SummaryTwo minutes

Plate Tracker shows what a YOLOv8 license-plate detector actually found in a real test clip — every box, every confidence score, every frame — without running the model live for each visitor. Hover or focus any box in the demo below to see the exact coordinates and confidence behind it.

The detector runs once, offline. What ships to the browser is its recorded output.

02

Context

ProblemBefore

Demoing a detector live in a browser means paying inference cost on every visit and keeping a model server up just to show a portfolio piece.

ApproachAfter

Run YOLOv8 with tracking once, offline, over a real test clip; export every frame's boxes, confidence and track id to JSON; replay that JSON client-side, synced to the looping video by timestamp.

03

Methodology

Pipeline
Test videoYOLOv8 + ByteTrack (offline)Per-frame JSON exportLooping videoTimestamp-synced overlay

YOLOv8 with ByteTrack processes the clip frame by frame at 30fps, and every frame's boxes, confidence scores and track ids are exported to a single JSON file. The browser's only job is to look up the frame closest to the video's current playback time and draw whatever was recorded there — the same technique subtitle files use to stay in sync with a video, applied to bounding boxes instead of text.

Export formatPer frame
frame_index / timestamp_seconds
Position in the clip
bbox_xyxy
Corner coordinates in source pixels
confidence
Detector's score for that box
id
ByteTrack's identity for the object, or null
04

Interactive

YOLOv8 detections — replayed1 box this frame
Hover or focus a box for its exact coordinates and confidence
00:00.00 / 20:24.89
Plates detected
0s20:25
05

Results

ResultsOne offline pass, 1,800 frames
1,800
Frames processed
83.7%
Frames with a detection
2,052
Boxes replayed
  • 1,800 frames at 30fps processed once offline; 83.7% contain at least one detection.
  • 2,052 individual detections replayed in the browser, confidence 0.25–0.84 (avg 0.54).
  • The entire interactive demo is a video file plus a 760KB JSON — no backend, no per-visit inference cost.
Detections replayed from a 1,800-frame exportavg confidence 0.54
0.760.54
06

Technical explanation

Why this worksMechanism

Coordinates are stored in the source video's native pixel space (848×478), not normalized — the overlay is an SVG sized to that exact viewBox and stretched over the video element, so a box drawn at pixel (292, 248) lands on the video's pixel (292, 248) regardless of how large the player is rendered on screen.

Because the lookup runs on every animation frame against the video's own currentTime, the overlay stays correct whether the video is autoplaying, paused, or scrubbed by hand — there is no dependency on playback events firing at any particular rate.

07

Conclusion

What I would keepRetrospective
  • Replaying a recorded inference pass is a legitimate way to demo a model — it removes GPU cost and cold-start latency from the demo entirely, at the cost of it being one fixed clip rather than anything the visitor can upload.
  • The tracker occasionally assigns two ids to the same physical plate for a few frames — a real limitation of the tracking step, left in rather than cleaned up, because it is honest about what the model does.
  • Storing coordinates in native pixels instead of normalizing them upfront moved the scaling math to one place (the overlay) instead of scattering it through the export script.
© 2026 Héctor LiceaDesign concept · placeholder contentBuild 2026.08Rendered client-side · no tracking