Road infrastructure deteriorates continuously under traffic load and weather, and undetected damage such as potholes, surface cracks, and uneven asphalt increases accident risk and long-term repair cost. Traditional road surveys rely on manual visual inspection, which is slow, subjective, and difficult to scale across large networks. This study develops an image-based road damage detection system built on deep learning models that automatically locate and classify damage from road surface images. A curated dataset of 160 annotated road images covering four categories—Normal Road, Potholes, Road Cracks, and Severe Damage—was preprocessed through resizing and normalization and expanded with data augmentation including flipping, rotation, brightness shift, and noise injection. Three architectures were trained and compared: a baseline Convolutional Neural Network (CNN), a lightweight MobileNet classifier, and a YOLOv8 object detector. Models were evaluated using accuracy, precision, recall, F1-score, and mean Average Precision (mAP). YOLOv8 achieved the strongest results with 94.60% accuracy, 94.00% F1-score, and 92.80% mAP, outperforming MobileNet and the baseline CNN while still supporting near real-time inference. A browser-based application was implemented to upload road images, preview them, run a detection simulation, and display class labels, confidence scores, and bounding boxes over pothole regions. A moving-vehicle simulation further demonstrates real-time risk reporting, raising the warnings “Risk Detected,” “Vehicle Passing Damaged Road,” and “Maintenance Required” when the vehicle crosses a damaged zone. The contributions are a comparative deep learning study for road damage detection, an interactive detection-and-simulation prototype, and a practical workflow for automated road condition monitoring
M. S. Sungkar, A. Wenda· JINAV: Journal of Informatio...· 0 citations
Traffic safety remains a critical concern in modern urban mobility, and the violation of red traffic signals is among the most dangerous and frequent forms of non-compliance, contributing substantially to intersection collisions, injuries, and fatalities. Conventional monitoring, which relies on human officers and fixed cameras reviewed manually, is labour-intensive, error-prone, and unable to provide continuous, scalable coverage across the many intersections of a growing city. This study proposes and demonstrates a computer-vision framework for the automatic detection of red-light running, formalised through the logical rule Violation = RedLight ? VehicleCrossesStopLine. The system integrates traffic-light state recognition, vehicle detection through bounding boxes, and stop-line region-of-interest analysis within a sequential processing pipeline comprising frame extraction, preprocessing, detection, and decision modules. A browser-based prototype built with HTML5 Canvas and JavaScript was developed to embody the complete detection logic, enabling red, yellow, and green signal states, a defined stop-line region, and moving vehicles to be evaluated in real time. The system was assessed on 200 simulated events spanning four representative scenarios using accuracy, precision, recall, and F1-score. Experimental results yielded an accuracy of 94.5%, precision of 95.2%, recall of 93.1%, and an F1-score of 94.1%, confirming reliable discrimination between violating and compliant vehicles. The principal contribution is a lightweight, transparent, and extensible detection scheme that provides a foundation for intelligent transportation systems, supporting future integration with CCTV networks, YOLOv8 detectors, web dashboards, and electronic ticketing.
Alex Wenda, M. S. Sungkar· JINAV: Journal of Informatio...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
