Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{200237,
        author = {Aditya Mandhare and Kaustubh Mhatre and Atharv Bhagat and Tejaswee Jha and Sandeep Kate and Dr. Jyoti Gangane},
        title = {Real-Time Pothole Detection and Severity Mapping System},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {2046-2055},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=200237},
        abstract = {Road infrastructure degradation, particularly the formation of potholes, poses a significant threat to vehicular safety, economic productivity, and public welfare in urban and semi-urban environments. Conventional pothole detection methods based on manual road inspection are inadequate in terms of timeliness, consistency, and scalability, while existing automated solutions are constrained by high implementation costs and dependency on external network infrastructure. 
This paper presents the design and implementation of a Real-Time Pothole Detection and Severity Mapping System utilizing a Raspberry Pi 3 Model B+ as the central processing unit, integrated with an HC-SR04 ultrasonic sensor for depth measurement, an ADXL345 tri-axis accelerometer for vibration-based detection, a Raspberry Pi camera module for visual road surface analysis, and a NEO-6M GPS module for real-time geographic localization. A multi-sensor data fusion algorithm consolidates the outputs of all sensing modalities to confirm pothole detection events, minimizing false positives and enhancing overall detection reliability. Detected potholes are classified into three severity levels — Low, 
Moderate, and High — based on measured depth and vibration magnitude parameters. All hardware components are interconnected through a custom-designed Printed Circuit Board (PCB) ensuring reliable and compact vehicular deployment. 
Experimental evaluation demonstrated an overall detection accuracy of 96.7%, a mean absolute depth measurement error of 0.31 cm, and a GPS positional accuracy of 2.8 metres. The geographic data collected is utilized to generate an interactive pothole severity map using the Folium library, providing actionable road condition information for road maintenance authorities. The proposed system demonstrates that a cost-effective, self-contained, and multi-sensor embedded platform represents a practically viable solution for real-time road condition monitoring in resource-constrained environments},
        keywords = {Pothole Detection, Raspberry Pi, HC-SR04, ADXL345, NEO-6M GPS, Sensor Data Fusion, Severity Classification, Road Condition Monitoring, Embedded Systems, PCB Design.},
        month = {May},
        }