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

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
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Multi-Model Edge-AI System for Real-Time Road Health Diagnostics using Vision-Acoustic Sensor Fusion

Rishika S, Supriya V, Niharika K, Rishi H et al.
IJARCCE
Infrastructure Maintenance and Monitoring
article

Multi-Model Edge-AI System for Real-Time Road Health Diagnostics using Vision-Acoustic Sensor Fusion

Rishika S, Supriya V, Niharika K, Rishi H, Thanuja K B
article en

Abstract

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.

IJARCCEVol. 15(11)
Infrastructure Maintenance and Monitoring
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon
Multi-Model Edge-AI System for Real-Time Road Health Diagnostics using Vision-Acoustic Sensor Fusion — Rishika S, Supriya V, et al. · IJARCCE (2026) | TGRS Research Map | TGRS