Litcius/Paper detail

YOLO-ROC: a high-precision and ultra-lightweight model for real-time road damage detection

Zicheng Lin, Weichao Pan

2025Measurement Science and Technology7 citationsDOI

Abstract

Abstract Road damage detection is a critical task for ensuring traffic safety and maintaining infrastructure integrity. While deep learning-based detection methods are now widely adopted, they still face two core challenges: first, the inadequate multi-scale feature extraction capabilities of existing networks for diverse targets like cracks and potholes, leading to high miss rates for small-scale damage; and second, the substantial parameter counts and computational demands of mainstream models, which hinder their deployment for efficient, real-time detection in practical applications. To address these issues, this paper proposes a high-precision and lightweight model, Y ou O nly L ook O nce- R oad O rthogonal C ompact ( YOLO-ROC ). We designed a B idirectional M ulti- s cale S patial P yramid P ooling F ast (BMS-SPPF) module to enhance multi-scale feature extraction and implemented a hierarchical channel compression strategy to reduce computational complexity. The BMS-SPPF module leverages a bidirectional spatial-channel attention mechanism to improve the detection of small targets. Concurrently, the channel compression strategy reduces the parameter count from 3.01 M to 0.89 M and giga floating-point operations per second (GFLOPs) from 8.1 to 2.6. Experiments on the RDD2022-China Drone dataset demonstrate that YOLO-ROC achieves a mAP50 of 67.6%, surpassing the baseline YOLOv8n by 1.4%. Notably, the recall rate for the small-target D40 category improved by 19%, and the final model size is only 2.0 MB. Furthermore, the model exhibits excellent generalization performance on the RDD2022-China Motorbike dataset.

Topics & Concepts

Computer scienceSoftware deploymentGeneralizationReal-time computingFeature extractionChannel (broadcasting)Feature (linguistics)Task (project management)Artificial intelligenceFace (sociological concept)Data miningEmbedded systemPattern recognition (psychology)Baseline (sea)Precision and recallSimulationDroneKey (lock)Situation awarenessCompression (physics)RecallData compressionIsolation (microbiology)Deep learningFirefightingStack (abstract data type)Infrastructure Maintenance and MonitoringAdvanced Neural Network ApplicationsDomain Adaptation and Few-Shot Learning
YOLO-ROC: a high-precision and ultra-lightweight model for real-time road damage detection | Litcius