collabdoor/road-anomaly-detection
Detect road anomalies such as cracks, potholes, and bumps using our trained YOLOv8 models with visual demo. Real-time detection via Streamlit and Flask app
This project helps road maintenance and urban planning professionals automatically detect and classify various road anomalies like cracks, potholes, and speed bumps. By analyzing video or image feeds, it identifies these issues and outputs their locations and types. This allows for faster identification of maintenance needs, saving time and resources compared to manual inspections.
Use this if you need a system to automatically inspect road surfaces for common defects from visual data, aiding in infrastructure maintenance planning.
Not ideal if you require highly granular material analysis of road damage or need to detect anomalies beyond the predefined categories (cracks, potholes, bumps).
Stars
18
Forks
1
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Jan 19, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/collabdoor/road-anomaly-detection"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
mounishvatti/pothole_detection_yolov8
Pothole Detection using Ultralytics YOLOv8.
nirbhayph/spothole
Spothole (Citizen App) - Artificial Intelligence Powered Pothole Detection, Reporting and...
srajan-kiyotaka/Pothole-Detection
The Model will detect whether the image consists of potholes or not. If the image consists of...
samyesuraj/Dashcam-Pothole-Detection
Real-time pothole detection using dashcam video, GPS data, and machine learning with ESP32-CAM...
mariam-william/Road-Defects-Detection
Computer vision-based system for real-time detection and localization of road surface defects...