Computer Engineering and Applications ›› 2024, Vol. 60 ›› Issue (17): 179-190.DOI: 10.3778/j.issn.1002-8331.2404-0288

• Graphics and Image Processing • Previous Articles     Next Articles

Improved Road Defect Detection Algorithm Based on YOLOv8

WANG Xueqiu, GAO Huanbing, JIA Zemeng   

  1. School of Information and Electrical Engineering, Shandong Jianzhu University, Jinan 250101, China
  • Online:2024-09-01 Published:2024-08-30

改进YOLOv8的道路缺陷检测算法

王雪秋,高焕兵,郏泽萌   

  1. 山东建筑大学 信息与电气工程学院,济南 250101

Abstract: Various defects can emerge on the road surface after prolonged use. Failing to promptly detect and repair these defects can significantly reduce the road’s lifespan and jeopardize driving safety. Consequently, real-time detection of road defects assumes paramount importance. However, traditional detection methods suffer from sluggish speed and hefty cost requirements. Hence, to tackle these challenges, a novel road detection algorithm called DML-YOLO is proposed, which builds upon the YOLOv8 framework. This algorithm integrates the MultiPath coordinate attention (MPCA) mechanism into the backbone network to enhance feature extraction. Additionally, the C2f-MPDC module is introduced to dynamically adjust the receptive field and improve detection capabilities. Furthermore, the network’s neck structure is redesigned, introducing a novel diversity feature pyramid network (DFPN) that reduces model size and fuses low-level feature maps to extract rich, detailed information and elevate the success rate of detecting small targets. Moreover, a lightweight shared convolutional detection head (LSCD head) is meticulously designed to enhance detection efficiency while reducing model size. Ultimately, extensive experimental results demonstrate that DML-YOLO achieves remarkable average detection precision, with mAP@0.5 scores of 89.6% on the RDD2022 dataset and 73.6% on the VOC2007 dataset, surpassing other models tested. Additionally, compared to the YOLOv8 model, DML-YOLO boasts a reduction of 32.37% in parameter count and 14.49% in computational workload, making it highly suitable for deployment in resource-constrained computing environments like embedded systems and mobile devices.

Key words: MultiPath coordinate attention, road detection, YOLOv8, shared convolutional

摘要: 道路在长期使用后路面会出现各种缺陷,未能及时侦测和修补这些缺陷可能严重缩短道路寿命并危害行车安全。因此,道路缺陷的即时检测是一项重要的任务。传统的检测方法存在检测速度慢,成本要求高的问题。为了解决这些问题,在YOLOv8的基础上提出了一种名为DML-YOLO新型道路检测算法,该算法在主干网络中加入MPCA(MultiPath coordinate attention)注意力机制,提高主干网络的特征提取能力,在此基础上提出了C2f-MPDC模块,动态调整感受野,提高检测能力;重新设计了网络的颈部结构,提出新的特征融合金字塔结构DFPN(diversity feature pyramid network),减小模型的体积并融合低层的特征图获得丰富的细节信息,提高检测小目标的成功率;设计一种轻量级共享卷积检测头(LSCD head),减少模型尺寸,提高检测效率。大量实验结果表明,DML-YOLO在RDD2022数据集和VOC2007数据集上平均检测精度mAP@0.5分别为89.6%和73.6%,优于其他测试模型,并且参数量和计算量相较于YOLOv8模型分别减少了32.37%和14.49%,更加适合部署在嵌入式系统、移动设备等计算资源受限和边缘计算的场景。

关键词: 多路聚合注意力机制, 道路检测, YOLOv8, 共享卷积