AI/ML / 2024 / Maintained
Browser-to-inference platform for streaming camera frames to a FastAPI detection service, visualising detections in the browser, and monitoring streaming behaviour in real time.
Role
Designer and engineer (solo)
Disciplines
Perception / AI Integration / Backend Systems / Full-Stack
Status
Maintained
Computer vision portfolios usually live in notebooks — hard for hiring teams to actually run, and disconnected from real product surfaces. Streaming inference under backpressure is rarely shown end-to-end.
React/Vite client captures webcam or video frames, sends them through a WebSocket to a FastAPI frame processor, and renders bounding-box overlays plus throughput, latency, and confidence telemetry. A detector abstraction lets the system run with a deterministic mock detector by default and an optional YOLOv8 adapter when weights are supplied.
In real-time vision systems, processing a stale frame is often worse than skipping it — the world has already moved on. The pipeline acknowledges one frame at a time and drops anything that arrives during processing.
Reviewers can verify the streaming architecture, backpressure behaviour, and dashboard wiring without GPU drivers or model weights. The mock is honestly labelled and emits deterministic detections.
Maximum connection counts, target FPS limits, and maximum frame-pixel limits sit at the WebSocket boundary so a misbehaving client cannot saturate the worker pool.
Self-contained demo that runs in mock mode with zero setup, then upgrades to real YOLOv8 when weights are dropped in.