基于改进PSPNet的桥梁裂缝图像分割算法  

Segmentation Algorithm of Bridge Crack Image Based on Modified PSPNet

作　　者：李良福[1] 王楠[1] 武彪 张晰 Li Liangfu;Wang Nan;Wu Biao;Zhang Xi(School of Computer Science,Shaanai Normal University,Xi'an,Shaanai 710119,China)

机构地区：[1]陕西师范大学计算机科学学院,陕西西安710119

出　　处：《激光与光电子学进展》2021年第22期93-101,共9页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(61573232,61401263)。

摘　　要：针对传统桥梁裂缝检测算法检测精度低和现有的主流语义分割算法容易丢失裂缝图像细节信息、结果不连续等问题,提出了一种基于改进PSPNet的桥梁裂缝图像分割算法。首先使用无人机采集桥梁图像,通过图像增强处理得到桥梁裂缝数据集;其次通过带有扩张卷积的残差网络初步提取裂缝特征;接着将提取到的特征送入到空间位置自注意力模块(SPAM)和金字塔池化模块的串联结构中,使其能够在空间维度上获得丰富的上下文信息。实验结果表明,与现有的主流语义分割算法相比,所提算法得到的裂缝细节更加丰富,各项分割指标都有较为显著的提升,平均交并比达到84.31%,并能对细小桥梁裂缝进行准确、完整提取。This study proposes a bridge crack image segmentation algorithm based on modified PSPNet to resolve the problems such as the low detection accuracy of the traditional bridge crack detection algorithms,loss of details in crack images and discontinuous findings of the existing mainstream semantic segmentation algorithms.First,the bridge images are acquired using an unmanned aerial vehicle,and the bridge crack datasets are procured via image enhancement processing.Second,the crack features are initially extracted using the residual network with dilated convolution.Then,the extracted features are sent to the serial structure of the spatial position self-attention module(SPAM)and pyramid pooling module,enabling the features to achieve rich contextual information in spatial dimensions.The experimental results reveal that the proposed algorithm obtains more precise crack details compared with the existing mainstream semantic segmentation algorithms,with each segmentation index being greatly improved,reaching 84.31%on mean intersection over the union.The proposed algorithm can extract small bridge cracks accurately and completely.

关 键 词：图像处理 桥梁裂缝检测 自注意力机制 金字塔池化 残差网络 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]