Multi-Model Edge-AI System for Real-Time Road Health Diagnostics using Vision-Acoustic Sensor Fusion
Road damage, particularly potholes, poses significant challenges to transportation safety and road maintenance.Conventional road inspection methods rely heavily on manual surveys, which are time-consuming and may not provide continuous monitoring.This paper presents a multi-modal Edge AI system for real-time pothole detection and road health monitoring using computer vision, accelerometer sensing, and GPS-based location tracking.The proposed system uses a Raspberry Pi 4 Model B as the central processing unit, integrated with a USB camera, MPU6050 accelerometer, and NEO-6M GPS module.OpenCV is employed for image acquisition and frame processing, while a trained YOLOv8 model identifies potholes from captured road images.Accelerometer readings provide supporting information about vehicle motion, and GPS coordinates are associated with detected pothole events.The collected images and detection records are stored locally and displayed through a web-based dashboard containing a map, photo log, and data table .The system performs processing at the edge, reducing reliance on continuous cloud communication.The proposed implementation provides a compact and practical approach to automated road damage identification, locationbased reporting, and road condition monitoring.
Authors
- Rishika S
- Supriya V
- Niharika K
- Rishi H
- Thanuja K B
Publication Details
- Journal
- IJARCCE
- Published
- 2026-11-21
- DOI
- https://doi.org/10.17148/ijarcce.2026.1511175
- Primary Topic
- Infrastructure Maintenance and Monitoring
- Type
- article
- Field-Weighted Citation Impact
- 0.00