| Issue |
ITM Web Conf.
Volume 74, 2025
International Conference on Contemporary Pervasive Computational Intelligence (ICCPCI-2024)
|
|
|---|---|---|
| Article Number | 03001 | |
| Number of page(s) | 10 | |
| Section | Engineering, Smart Systems, and Optimization | |
| DOI | https://doi.org/10.1051/itmconf/20257403001 | |
| Published online | 20 February 2025 | |
Real-Time Road Surface Analysis for Pothole Detection
1 Department of Electronics and Communication Engineering, Sreenidhi Institute of Science and Technology, Hyderabad, India
2 Department of EEE, Shiv Nadar University, Greater Noida UP, India
* Corresponding author: ganesh.g@sreenidhi.edu.in
This paper presents a potentially low cost approach to detecting potholes using segmentation, by pairing a low cost computing platform (the Raspberry Pi) with a camera module and OpenCV image processing software. By getting real-time images processed with computational resources of Raspberry Pi and OpenCV image analysis functions, our system makes the search in real-time for potholes. The small form factor and flexibility of the Raspberry Pi makes it among the perfect platforms to interface with camera modules to capture high-resolution images of road surfaces. OpenCV provides an elaborate tool kit to enable image preprocessing, feature extraction, classification and precise crack detection. According to testing, this system has shown the ability to accurately detect potholes in a variety of environmental conditions and on different road types, making this solution cost-effective and scalable for transportation departments and cities looking to improve road safety and speed up pothole repairs.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.