Litter Watch — Street Garbage Detection

Overview

Litter Watch detects garbage and trash piles in street footage filmed from a phone mounted on a moving scooter — the cheapest possible survey rig for an Indian city. A YOLO detector runs over sampled frames, and every confirmed pile is pinned to its own coordinate so the output is a map of where the problem actually is, not just a count.

The hard part is not detection but suppression. Street scenes are full of things that look like a trash pile to a naive detector: people crouching, parked vehicles, stones, tree litter, benches, posters and fences. A geometry gate filters these forbidden classes explicitly and reports how many boxes it rejected, so the confirmed count means something.

The same detector drives two faces — a FastAPI backend streaming an MJPEG feed to a Next.js dashboard with a live map and per-locality stats, and a CLI that batch-processes a video into an annotated file plus a JSON report.

The problem

Municipal garbage surveys are done on foot with clipboards — slow, expensive and stale by the time they are compiled. There was no cheap way to answer "where exactly is the garbage" across a city, and a naive detector run over street video reports every crouching person and parked vehicle as a pile.

The solution

A detection pipeline driven by phone video from a moving scooter: sampled frames run through a YOLO model trained on trash piles, a geometry gate rejects forbidden classes, and every surviving detection is pinned to a coordinate and streamed to a live dashboard.

Technical stack

System architecture

1. 1

   YOLOv8 detector with custom trash-pile weights, run through Ultralytics and OpenCV

2. 2

   FastAPI backend exposing detection control, run statistics and an MJPEG frame stream

3. 3

   Next.js dashboard with live feed, Leaflet coverage map, detection gallery and per-zone stats

4. 4

   Geometry gate that filters forbidden classes and reports the rejection count for transparency

5. 5

   Sandboxed video library — the detector resolves every job inside one folder and rejects escaping paths

6. 6

   CLI batch path sharing the same detector, emitting an annotated video plus a JSON report

Engineering challenges

Core features

• YOLO detector trained for street-level garbage piles
• Geometry gate that filters people, vehicles and street furniture
• Live MJPEG feed of annotated frames in the browser
• Every pile pinned to its own map coordinate
• Per-locality breakdown of where garbage was found
• Confidence and frame-interval controls at runtime
• Video upload from the dashboard with progress
• Webcam and IP-camera sources alongside video files
• CLI batch mode producing an annotated video plus a JSON report
• Downloadable annotated video after a run

Results & impact

A survey that previously needed people walking with clipboards became a scooter ride: in a single run the system processed street footage live, confirmed piles at 78%+ average confidence, filtered the forbidden-class boxes, and dropped every confirmed pile onto a Ranchi coverage map with a per-locality breakdown.

Screenshots

What I learned

• On a real-world detector, the filtering rules carry more product value than the model — and showing what was rejected is what makes the remaining count trustworthy.
• Constraining file jobs to a single sandboxed folder is worth doing on day one when the input is user-uploaded video.