Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM69240
Volume:
10 |
11 |
Nov 2026
Pages:
1-4
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Computer engineering
Shivnagar vidya prasarak mandal college of engineering malegaon baramati
Computer engineering
Shivnagar vidya prasarak mandal college of engineering malegaon baramati
Computer engineering
Shivnagar vidya prasarak mandal college of engineering malegaon baramati
Computer engineering
Shivnagar vidya prasarak mandal college of engineering malegaon baramati
Computer engineering
Shivnagar vidya prasarak mandal college of engineering
Urban roadway infrastructure is subject to progressive surface deterioration, including potholes, fatigue cracks, unmarked speed bumps, and sunken manholes. Traditional municipal road assessments rely on manual inspections or capital-intensive dedicated survey vehicles, which suffer from intermittent scheduling, prohibitive operational costs, and delayed repair cycles. To overcome these critical bottlenecks, this paper presents the Smart Road Damage Detection Network, an edge-assisted, crowdsourced urban pavement monitoring and mapping architecture deployed across public transit and municipal fleets. The onboard edge unit integrates an ESP32 microcontroller, an InvenSense MPU6050 six-axis inertial measurement unit (IMU), a u-blox NEO-6M global positioning system (GPS) receiver, and an ESP32-CAM module. To mitigate cellular transmission costs and battery depletion, we formulate a dynamic, speed-compensated vertical acceleration threshold that triggers optical image acquisition strictly upon physical impact events. This event-gated mechanism suppresses continuous video transmission, curtailing wireless data bandwidth by 84.6% relative to streaming baselines. Captured geotagged frames are transmitted via 4G LTE to a centralized cloud analytics server, where a custom 23-layer deep convolutional neural network (DD-CNN-23) categorizes anomalies across four primary classes with 98.19% classification accuracy, 91.86% precision, and 97.54% [email protected]. Furthermore, Density-Based Spatial Clustering of Applications with Noise (DBSCAN) aggregates multi-vehicle detections, eliminating 93.4% of false alarms caused by driver braking and railroad crossings. Verified anomalies populate an interactive Web GIS dashboard with prioritized maintenance work orders, offering smart cities a scalable, cost-effective infrastructure asset management platform.
KEYWORDS
This paper presented the Smart Road Damage Detection Network, a crowdsourced urban road anomaly mapping platform uniting low-cost edge IoT sensing, speed-compensated vibration gating, deep convolutional neural networks, and DBSCAN geospatial clustering. By capturing optical snapshots strictly upon verified kinematic impacts, the system reduces cellular bandwidth consumption by 84.6% while eliminating continuous video streaming. The cloud DD-CNN-23 model delivers 98.19% classification accuracy across potholes, cracks, speed bumps, and manholes, while DBSCAN eliminates 93.4% of false alarms. The platform provides smart cities with a scalable, production-ready blueprint for autonomous roadway infrastructure maintenance.
1. Alrajhi, A., Roy, K., Qingge, L., Kribs, J.: Detection of Road Condition Defects Using Multiple Sensors and IoT Technology: A Review. IEEE Open Journal of Intelligent Transportation Systems 4, 110–130 (2023) 2. Bouhsissin, S., Assemlali, H., Sael, N.: Enhancing road safety: A convolutional neural network based approach for road damage detection. Sustainable Futures 7, 100185 (2024) 3. Arfain, A., Shariff, I., Karthik, B.A., Anam, H., Divyashree, G., Amulya, M.P.: Next-Gen Smart Road Damage Detection & Predictive Maintenance System. International Journal of Engineering Research & Technology (IJERT) 15(8), 1–6 (2026) 4. Geethamahalakshmi, G.: CNN-Based Road Damage Detection. Qeios, 1–16 (2023). doi:10.32388/KIY05S 5. World Health Organization: Global Status Report on Road Safety. WHO Press, Geneva, Switzerland, 1–24 (2023)
Publication Date
11/19/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
2
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...