Road Damage Detection

Author(s)	Ms. Alekhya N, Dr. Madhumitha K
Country	India
Abstract	Damages to road pavements have massive impacts on driving comfort, endanger safety, and can result in accidents. Traditional approaches to detecting damage, including hand inspection and mounted sensors, are not suitable for monitoring large areas. An alternative solution is to use street-view as a comparatively cheap option that offers current road data in the city. The proposed paper suggests a better system of pavement damage detection using YOLOv5 and street-view images. The model incorporates a Generalized Feature Pyramid Network (Generalized-FPN) to allow cross-layer and cross-scale feature fusion to improve the accuracy in detecting large distress targets. More accurate bounding box regression is done by a diagonal Intersection over Union (IoU) loss function, and the predictions and regressions are decoupled by a Head structure. The experimental findings prove that the given methodology is effective in strengthening the weak feature fusion on the spatial levels and shows higher results in detecting pavement distress in multi-scale and multi-level street-view images.
Keywords	Generalized Feature Pyramid Network (Generalized-FPN), Deep learning, Diagonal IoU Loss, Object Detection, Pavement Damage Detection, Street-View images, YOLOv5.
Field	Engineering
Published In	Volume 16, Issue 4, October-December 2025
Published On	2025-11-15
DOI	https://doi.org/10.71097/IJSAT.v16.i4.8698
Short DOI	https://doi.org/hbbm2n

About IJSAT Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us	Message on WhatsApp	+91-9687-182-185	editor@ijsat.org

International Journal on Science and Technology