摘要
为解决轨道板裂缝检测问题,提出了一种基于分支级联卷积神经网络的轨道板裂缝检测模型DDTSCD。首先该模型通过注意力机制和搜索分支结构突出轨道板裂缝的位置信息,同时抑制干扰信息;然后采用检测分支结构完成裂缝的像素级检测;最后对检测结果中出现的图像细节退化问题,利用参数映射关系实现特征图的上采样。实验结果表明:所提出的方法能够准确地检测出轨道板表面图像中的裂缝,其像素准确率可达97.56%,F1-score可达86.28%,并且在跨数据集测试中表现出较强的泛化性。
In order to solve the problem of track slab crack detection,a track slab crack detection model based on branch cascaded convolutional neural network,TSCD,is proposed.First,the model highlights the position information of track slab cracks through attention mechanism and structure of search branches to suppress interference information.Second,it realizes the pixel-level detection of cracks by structure of detecting branches.Finally,in order to solve the problem of image detail degradation in detection results,parameter mapping is used to achieve up-sampling of the feature maps.Experimental results show that the proposed model in this paper can not only detect the cracks in track plate surface images accurately with pixel accuracy rate of 97.56%and F1-score of 86.28%,but also performs strong generalization in cross-dataset tests.
作者
李文举
张耀星
陈慧玲
李培刚
沙利业
LI Wenju;ZHANG Yaoxing;CHEN Huiling;LI Peigang;SHA Liye(School of Railway Transportation,Shanghai Institute of Technology,Shanghai 201418,China;School of Computer Science and Information Engineering,Shanghai Institute of Technology,Shanghai 201418,China;Shanghai Prinsen Dosing&Weighting System Co.,Ltd,Shanghai 201108,China)
出处
《应用科学学报》
CAS
CSCD
北大核心
2022年第1期155-166,共12页
Journal of Applied Sciences
基金
上海市科技创新行动计划基金(No.21210750300)资助
关键词
裂缝检测
分支级联
参数映射
轨道板
卷积神经网络
crack detection
branch cascade
parameter mapping
track plate
convolutional neural network
作者简介
通信作者:李培刚,博士,讲师,研究方向为高速、重载及交通轨道结构。E-mail:lipeigang@sit.edu.cn
