In modern urban and rural road infrastructure, the detection and monitoring of road anomalies such as speed humps and potholes play a crucial role in ensuring road safety and infrastructure maintenance. Speed humps are raised pavement structures designed to slow down vehicles at specific locations, while potholes are depressions or holes in the road surface that can pose hazards to vehicles and pedestrians alike. Detecting these anomalies accurately and efficiently is essential to mitigate associated risks and ensure timely maintenance. Computer vision-based methods use high-resolution cameras and machine learning algorithms to automatically detect and classify road anomalies with greater accuracy and efficiency. This approach enables early detection, real-time monitoring and timely maintenance thus improving road safety. In this paper, a real time implementation of pothole and hump detection system is proposed. The Deep Learning algorithm, YOLOv8 model is used to detect potholes and humps.
Computer Vision-Based Speed Hump and Pothole Detection System for Vehicles
21.03.2025
1308422 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Pothole Detection Using Computer Vision and Learning
IEEE | 2020
|POTHOLE AND SPEED BUMP DETECTION BASED ON VEHICLE'S BEHAVIORS USING COMPUTER VISION
Europäisches Patentamt | 2024
|Road Pothole Detection System Based on Stereo Vision
IEEE | 2018
|A Vision-Based Pothole Detection Using CNN Model
Springer Verlag | 2023
|