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