重庆科技大学学报（自然科学版）2024，Vol.26Issue(5)：99-106,8.DOI:10.19406/j.issn.2097-4531.2024.05.015
基于改进YOLO网络的混凝土裂缝检测方法研究
Concrete Crack Detection Method Based on Improved YOLO Network
摘要
Abstract
The target detection network with large models and high computing power requirements is difficult to im-plement mobile deployment,which restricts its application in the field of concrete crack detection.A concrete crack detection network model(YOLO-GAMM)is proposed,in which the backbone network of YOLOv5s is replaced by a lightweight network MobileNetV3 and a global attention mechanism is introduced to achieve YOLO-GAMM,so that its complexity and accuracy can satisfy the requirements of portable concrete crack detection systems.The sim-ulation results show that compared with the YOLOv5s model,the improved network model has a 60.0%reduction in computation and a 65.5%reduction in memory consumption and has a good performance.关键词
YOLO网络/目标检测/混凝土裂缝/轻量型网络/全局注意力机制Key words
YOLO network/target detection/concrete cracks/lightweight network/global attention mechanism分类
建筑与水利引用本文复制引用
黎乐,谭银华,文玉双,赵晨溪,胡文金..基于改进YOLO网络的混凝土裂缝检测方法研究[J].重庆科技大学学报（自然科学版）,2024,26(5):99-106,8.基金项目
重庆市研究生科研创新项目"频率失配对超声波换能器的影响及应对策略研究"(CYS23746) （CYS23746）
重庆市研究生教育教学改革研究项目"控制类专业学位研究生工程实践教学内容的重构与资源建设"(YJG213132) （YJG213132）
重庆科技大学硕士研究生创新计划项目"基于图像识别和四旋翼无人机的外墙砖裂缝检测方法研究"(YKJCX2220407) （YKJCX2220407）
