Paper Reading AI Learner

YOLO-ROC: A High-Precision and Ultra-Lightweight Model for Real-Time Road Damage Detection

2025-07-31 03:35:19
Zicheng Lin, Weichao Pan

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, YOLO - Road Orthogonal Compact (YOLO-ROC). We designed a Bidirectional Multi-scale Spatial Pyramid Pooling Fast (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 3.01M to 0.89M and 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 2.11%. Notably, the mAP50 for the small-target D40 category improved by 16.8%, and the final model size is only 2.0 MB. Furthermore, the model exhibits excellent generalization performance on the RDD2022_China_Motorbike dataset.

Abstract (translated)

道路损坏检测是确保交通安全和维护基础设施完整性的关键任务。虽然基于深度学习的检测方法现在已被广泛采用,但仍面临两大核心挑战:首先,现有的网络在提取裂缝、坑洞等多样化目标的多尺度特征方面能力不足,导致小规模损害的漏检率高;其次,主流模型参数量大且计算需求高,这限制了它们在实际应用中进行高效实时检测的能力。为了解决这些问题,本文提出了一种高精度和轻量级模型——YOLO-Road Orthogonal Compact (YOLO-ROC)。 我们设计了一个双向多尺度空间金字塔池化快速(BMS-SPPF)模块来增强多尺度特征提取,并实施了层次化的通道压缩策略以减少计算复杂度。BMS-SPPF模块利用双向空间-通道注意机制,提升了对小目标的检测能力。同时,通过通道压缩策略将参数量从3.01M降低到0.89M,浮点运算次数(GFLOPs)也从8.1降至2.6。 在RDD2022_China_Drone数据集上的实验表明,YOLO-ROC达到了mAP50为67.6%,比基准模型YOLOv8n高出2.11%。值得注意的是,针对小目标D40类别的mAP50提高了16.8%,最终模型大小仅为2.0 MB。此外,在RDD2022_China_Motorbike数据集上,该模型表现出色的泛化性能。 这些改进和优化使YOLO-ROC成为在实际应用中高效进行道路损坏检测的理想选择。

URL

https://arxiv.org/abs/2507.23225

PDF

https://arxiv.org/pdf/2507.23225.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model LLM Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Robot Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Time_Series Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot