检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:谢文斌 李顺新[1,2,3] XIE Wen-bin;LI Shun-xin(School of Computer Science and Technology,Wuhan University of Science and Technology,Wuhan 430065,China;Big Data Science and Engineering Research Institute,Wuhan University of Science and Technology,Wuhan 430065,China;Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial,Wuhan 430065,China)
机构地区:[1]武汉科技大学计算机科学与技术学院,湖北武汉430065 [2]武汉科技大学大数据科学与工程研究室,湖北武汉430065 [3]湖北智能信息处理与实时工业系统重点实验室,湖北武汉430065
出 处:《计算机技术与发展》2025年第4期15-21,共7页Computer Technology and Development
基 金:国家自然科学基金联合基金重点支持项目(U1803262)。
摘 要:针对现有道路损伤检测方法检测精度不足,难以兼顾模型规模和精度的问题,提出了一种路面损伤实时检测算法YOLOv8-Pavement defect(YOLOv8-PD)。由于YOLOv8网络在快速目标检测拥有显著成效,将其作为改进的基准网络。首先,在骨干网络上,在YOLOv8特征提取模块C2f上融合ECA注意力机制,能够更好地提取图片特征和关注重点对象;其次,在颈部结构引入LightConv结构进行轻量化;最后,针对坑洞(D40)检测不理想的情况,加入小目标层和加权特征融合,加强对于小目标坑洞的检测效果。实验结果表明,在RDD2022路面损伤数据集上,YOLOv8-PD比原算法YOLOv8n在mAP50-95上提升了5.67%,在mAP50上提升了3.06%,在T4上FPS上达到了71 FPS,满足实时检测的需求。与YOLO等主流算法相比,该算法在精度上超越了所有的YOLO系列的轻量级模型,证明了改进算法的有效性。A real-time pavement defect detection algorithm called YOLOv8-Pavement defect(YOLOv8-PD)is proposed to address the problem of insufficient accuracy in detecting small targets in current road damage detection methods,making it difficult to balance model size and accuracy.Since the YOLOv8 network has significant results in fast target detection,it is used as an improved baseline network.Firstly,an ECA attention mechanism is fused onto the YOLOv8 feature extraction module C2f on the backbone network,enabling better feature extraction from images and focusing on key objects.Secondly,a LightConv structure is integrated into the neck structure for lightweighting.Finally,to address the suboptimal detection of potholes(D40),a small target layer and weighted feature fusion are added to enhance the detection performance of small target potholes.Experimental results on the RDD2022 road damage dataset show that YOLOv8-PD improves the original YOLOv8 algorithm by 5.67%in mAP50-95,3.06%in mAP50,achieving 71 FPS on T4,meeting the requirements for real-time detection.Compared with mainstream algorithms like YOLO,the proposed algorithm almost surpasses all YOLO series lightweight models in accuracy,demonstrating its effectiveness.
关 键 词:YOLOv8 n 注意力机制 轻量化 深度学习 路面缺陷检测
分 类 号:TP391.4[自动化与计算机技术—计算机应用技术]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.33