Concrete roadway crack segmentation using encoder-decoder networks with range images

作     者：Zhou, Shanglian Song, Wei 

作者机构：Univ Alabama Dept Civil Construct & Environm Engn Tuscaloosa AL 35487 USA 

出 版 物：《AUTOMATION IN CONSTRUCTION》 (建造自动化)

年 卷 期：2020年第120卷

页      面：103403-103403页

核心收录：

学科分类：08[工学] 0813[工学-建筑学] 0814[工学-土木工程] 

基　　金：Alabama Department of Transportation [930-930, 25663] Alabama Transportation Institute 

主　　题：Deep convolutional neural network Encoder-decoder networks Residual connection Range image Crack segmentation Pavement groove 

摘      要：Recently, researchers have utilized DCNN for pixel-wise crack classification through semantic segmentation. Nevertheless, some issues in current DCNN-based roadway crack segmentation are yet to be fully addressed. For example, image pre-processing techniques are often required to eliminate the surface variations in range images, which may bring uncertainties due to subjective parameter selection;besides, disturbances from many non-crack patterns such as pavement grooves can deteriorate the crack segmentation performance, which remains a challenge for current DCNN-based methodologies. This paper proposes a methodology based on encoder-decoder networks to achieve pixel-wise crack classification performance on laser-scanned range images, under the disturbance of surface variations and grooved patterns in concrete pavements. The raw range data is directly applied in this methodology without any pre-processing. A comparative study is performed to determine the optimal architecture layout among twelve proposed candidates. Meanwhile, the influence of residual connections on DCNN performance is investigated and demonstrated.