[1]武 斌,马玉静,刘宇航,等.基于 Deepcrack 网络的混凝土裂缝检测方法[J].计算机技术与发展,2024,34(04):198-204.[doi:10. 3969 / j. issn. 1673-629X. 2024. 04. 030]
　WU Bin,MA Yu-jing,LIU Yu-hang,et al.Concrete Crack Detection Method Based on Deepcrack Network[J].,2024,34(04):198-204.[doi:10. 3969 / j. issn. 1673-629X. 2024. 04. 030]
点击复制

基于 Deepcrack 网络的混凝土裂缝检测方法()
分享到：

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

卷:
34
期数:
2024年04期
页码:
198-204
栏目:
新型计算应用系统
出版日期:
2024-04-10

文章信息/Info

Title:
Concrete Crack Detection Method Based on Deepcrack Network
文章编号:
1673-629X(2024)04-0198-07
作者:
武 斌; 马玉静; 刘宇航; 赵 洁*
天津城建大学 计算机与信息工程学院,天津 300384
Author(s):
WU Bin; MA Yu-jing; LIU Yu-hang; ZHAO Jie*
School of Computer and Information Engineering,Tianjin Chengjian University,Tianjin 300384,China
关键词:
图像分割; 裂缝检测; 金字塔分割注意力; 全局上下文; 全维动态卷积
Keywords:
image segmentation; crack detection; pyramid split attention; global context; omni-dimensional dynamic convolution
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2024. 04. 030
摘要:
混凝土结构裂缝对建筑安全构成了极大的潜在威胁,裂缝检测对建筑结构的维护具有重要意义,当前基于深度学习的裂缝检测针对提取裂缝细节的能力仍有待提高。 因此,该文对 Deepcrack 网络进行优化,提出了基于金字塔分割注意力和全局上下文的混凝土裂缝检测算法 PG-Deepcrack。 首先,在编码器中提出双卷积-注意力并行模块,增加金字塔分割注
意力分支为卷积层提供更丰富的多尺度裂缝信息;其次,为了捕获长距离依赖关系,并行模块操作后引入全局上下文模块,进一步提升网络对裂缝细节的表达能力;最后,在特征融合阶
段利用全维动态卷积和 GELU 激活函数,对编解码器特征层联级融合,使网络更全面地保留不同尺寸的裂缝信息并提高模型的泛化性能。 为验证网络模型的有效性,在 Deepcrack
数据集上与 7 个网络模型进行对比试验,所提出的网络表现了最佳性能,IoU 达到了 72. 78% 。
Abstract:
Concrete structural cracks pose a great potential threat to building safety,and crack detection is of great significance to the maintenance of building structures. The current deep learning-based crack detection for extracting crack details still needs to be improved.Therefore,we optimize the Deepcrack network and propose a concrete crack detection algorithm PG-Deepcrack based on pyramid split attention and global context. Firstly,a dual-convolution-attention parallel block is proposed in the encoder to add a pyramid-split attentionbranch to provide richer multi - scale crack information for the convolutional layer. Secondly, in order to capture long - distancedependencies,a global context block is introduced after the operation of the parallel block,which further improves the ability of networkto express the crack details. Finally,the omni - dimensional dynamic convolution and the GELU activation function are utilized in thefeature fusion stage to cascade-level fusion of codec features,so that the network retains the information of different sizes of cracks in amore comprehensive way and improves the generalization performance of the model. To validate the effectiveness of the network model,a comparative test is conducted with seven network models on the DeepCrack dataset, and the proposed network exhibits the bestperformance with an IoU of 72. 78% .

相似文献/References:

[1]蒋璐璐 王适 王宝成 李慧敏 李鑫慧.一种改进的标记分水岭遥感图像分割方法[J].计算机技术与发展,2010,(01):36.
　JIANG Lu-lu,WANG Shi,WANG Bao-cheng,et al.Segmentation of Remote Sensing Image Based on an Improved Labeling Watershed Algorithm[J].,2010,(04):36.
[2]张少娴 俞琼.基于时空相关性预测的运动估计的优化[J].计算机技术与发展,2010,(01):100.
　ZHANG Shao-xian,YU Qiong.An Optimization Method for Spatiotemporal Predictive Motion Estimation[J].,2010,(04):100.
[3]王兴 冯子亮.基于自适应初始值的FCM聚类图像分割[J].计算机技术与发展,2010,(03):101.
　WANG Xing,FENG Zi-liang.An Image Segmentation Algorithm Based on Adaptive Initialization FCM Clustering[J].,2010,(04):101.
[4]何小娜 逄焕利.基于二维直方图和改进蚁群聚类的图像分割[J].计算机技术与发展,2010,(03):128.
　HE Xiao-na,PANG Huan-li.Image Segmentation Based on Improved Ant Colony Clustering and Two- Dimensional Histogram[J].,2010,(04):128.
[5]宋淑娜 李金霞 胡学坤 高尚.一种自适应模糊阈值区间的图像分割方法[J].计算机技术与发展,2010,(05):121.
　SONG Shu-na,LI Jin-xia,HU Xue-kun,et al.A Method of Adaptive Fuzzy Threshold Region for Image Segmentation[J].,2010,(04):121.
[6]来磊 卢文科 邓开连.基于二维Tsallis交叉熵直线型图像阈值分割方法[J].计算机技术与发展,2010,(06):105.
　LAI Lei,LU Wen-ke,DENG Kai-lian.New Image Thresholding Segmentation Methods Based on Two-Dimensional Tsallis Cross-Entropy Liner-Type[J].,2010,(04):105.
[7]黄长专 王彪 杨忠.图像分割方法研究[J].计算机技术与发展,2009,(06):76.
　HUANG Chang-zhuan,WANG Biao,YANG Zhong.A Study on Image Segmentation Techniques[J].,2009,(04):76.
[8]李光耀 聂诗良.基于小波分解和模糊聚类的图像分割方法[J].计算机技术与发展,2009,(06):121.
　LI Guang-yao,NIE Shi-liang.Image Segment Algorithm Based on Wavelet Decomposition and Fuzzy Clustering Theory[J].,2009,(04):121.
[9]吴亚 汪继文.水平集图像分割中重新初始化规避的探索[J].计算机技术与发展,2009,(09):69.
　WU Ya,WANG Ji-wen.Avoidance of Re- Initialization in Level Set Image Segmentation[J].,2009,(04):69.
[10]李鑫环 陈立潮 赵红艳 赵勇.基于多小波分析与SOFM的MR图像分割算法研究[J].计算机技术与发展,2009,(09):104.
　LI Xin-huan,CHEN Li-chao,ZHAO Hong-yan,et al.Research on MR Image Segmentation Based on Multi- wavelet Analysis and SOFM[J].,2009,(04):104.

更新日期/Last Update: 2024-04-10