← all projects
Computer VisionCVAI

StreetSpecter — Real-Time Pothole Detection

Custom-trained YOLOv8s on 5,493 images — 90% detection accuracy. OpenStreetMap API integration to map 1,000+ km of road data for geolocated pothole reporting. Dockerized deployment.

PythonYOLOv8FlaskDockerOpenStreetMap

Problem

Road damage reporting becomes more useful when detection is geolocated. StreetSpecter combines object detection with map context so potholes can be identified and tied to road segments.

Approach

System Diagram

1

Image/video input

Frames are submitted to the detection service for pothole inference.

2

YOLOv8s model

Runs object detection over road imagery and returns pothole bounding boxes.

3

Flask API

Exposes inference results and keeps model serving deployable.

4

OpenStreetMap layer

Maps detections to road context and geolocation data.

5

Reporting output

Produces geolocated pothole reports for downstream review.

Key Decisions

Why YOLOv8s

The small model balances speed and accuracy, which matters for a real-time road-inspection workflow.

Why OpenStreetMap

Raw detections are only half the product; map data turns them into actionable road-segment reports.

Concepts Used

Object detectionTransfer learningGeospatial enrichmentModel servingDockerized deployment

Outcomes

← back to featured projects