[1]谢文斌,李顺新.基于注意力和特征融合的路面缺陷检测算法[J].计算机技术与发展,2025,(04):15-21.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0371]
　XIE Wen-bin,LI Shun-xin.Pavement Defect Detection Algorithm Based on Attention and Feature Fusion[J].,2025,(04):15-21.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0371]
点击复制

基于注意力和特征融合的路面缺陷检测算法()

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2025年04期
页码:
15-21
栏目:
媒体计算
出版日期:
2025-04-10

文章信息/Info

Title:
Pavement Defect Detection Algorithm Based on Attention and Feature Fusion
文章编号:
1673-629X(2025)04-0015-07
作者:
谢文斌1; 2; 3; 李顺新1; 2; 3
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
Author(s):
XIE Wen-bin1; 2; 3; LI Shun-xin1; 2; 3
1. School of Computer Science and Technology,Wuhan University of Science and Technology,Wuhan 430065,China;
2. Big Data Science and Engineering Research Institute,Wuhan University of Science and Technology,Wuhan 430065,China;
3. Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial,Wuhan 430065,China
关键词:
YOLOv8 n; 注意力机制; 轻量化; 深度学习; 路面缺陷检测
Keywords:
YOLOv8 n; attention mechanism; lightweight; deep learning; pavement defect detection
分类号:
TP391.4
DOI:
10.20165/j.cnki.ISSN1673-629X.2024.0371
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。
Abstract:
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 light-weighting. 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.

相似文献/References:

[1]李梦洁,董峦.基于 PyTorch 的机器翻译算法的实现[J].计算机技术与发展,2018,28(10):160.[doi:10.3969/ j. issn.1673-629X.2018.10.033]
　LI Meng-jie,DONG Luan.Implementation of Machine Translation Algorithm Based on PyTorch[J].,2018,28(04):160.[doi:10.3969/ j. issn.1673-629X.2018.10.033]
[2]李东欣,禹 龙,田生伟,等.注意力机制的 LSTM-DBN 维语人称代词指代消解[J].计算机技术与发展,2019,29(07):33.[doi:10. 3969 / j. issn. 1673-629X. 2019. 07. 007]
　LI Dong-xin,YU Long,TIAN Sheng-wei,et al.Attention Mechanism of LSTM-DBN Uyghur Personal Pronoun Anaphora Resolution[J].,2019,29(04):33.[doi:10. 3969 / j. issn. 1673-629X. 2019. 07. 007]
[3]尹 鹏,周 林,郭 强,等.基于短语级注意力机制的关系抽取方法[J].计算机技术与发展,2019,29(09):24.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 005]
　YIN Peng,ZHOU Lin,GUO Qiang,et al.Relation Extraction Based on Phrase-level Attention[J].,2019,29(04):24.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 005]
[4]钟 诚,周浩杰,韦海亮.一种基于注意力机制的三维点云物体识别方法[J].计算机技术与发展,2020,30(04):41.[doi:10. 3969 / j. issn. 1673-629X. 2020. 04. 008]
　ZHONG Cheng,ZHOU Hao-jie,WEI Hai-liang.A 3D Point Cloud Object Recognition Method Based on Attention Mechanism[J].,2020,30(04):41.[doi:10. 3969 / j. issn. 1673-629X. 2020. 04. 008]
[5]王乾铭,李 吟.基于深度学习的个性化聊天机器人研究[J].计算机技术与发展,2020,30(04):79.[doi:10. 3969 / j. issn. 1673-629X. 2020. 04. 015]
　WANG Qian-ming,LI Yin.Research on Personalized Chatbot Based on Deep Learning[J].,2020,30(04):79.[doi:10. 3969 / j. issn. 1673-629X. 2020. 04. 015]
[6]朱立倩.基于深度学习的数显仪表字符识别[J].计算机技术与发展,2020,30(06):141.[doi:10. 3969 / j. issn. 1673-629X. 2020. 06. 027]
　ZHU Li-qian.Character Recognition of Digital Display Instrument Based on Deep Learning[J].,2020,30(04):141.[doi:10. 3969 / j. issn. 1673-629X. 2020. 06. 027]
[7]申静波,李井辉,孙丽娜.注意力机制在评论文本情感分析中的应用研究[J].计算机技术与发展,2020,30(07):169.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 036]
　SHEN Jing-bo,LI Jing-hui,SUN Li-na.Research on Application of Attention Mechanism in Comment Text Emotional Analysis[J].,2020,30(04):169.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 036]
[8]张亚飞.基于注意力的权重分配机制[J].计算机技术与发展,2020,30(09):49.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 009]
　ZHANG Ya-fei.Attention-based Weight Allocation Mechanism[J].,2020,30(04):49.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 009]
[9]王振业,叶成绪*,王文韬,等.基于 LSTM-Att 方法的音乐流行趋势预测[J].计算机技术与发展,2020,30(09):188.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 034]
　WANG Zhen-ye,YE Cheng-xu*,WANG Wen-tao,et al.Music Trend Forecast Based on LSTM-Att Method[J].,2020,30(04):188.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 034]
[10]陈 琛,刘小云,方玉华.融合注意力机制的电子病历命名实体识别[J].计算机技术与发展,2020,30(10):216.[doi:10. 3969 / j. issn. 1673-629X. 2020. 10. 038]
　CHEN Chen,LIU Xiao-yun,FANG Yu-hua.Named Entity Recognition in Electronic Medical Record Introducing Attention Mechanisms[J].,2020,30(04):216.[doi:10. 3969 / j. issn. 1673-629X. 2020. 10. 038]

更新日期/Last Update: 2025-04-10