Abstract
Cracks are one of the most common types of surface defects that occur on various engineering infrastructures. Visual-based crack detection is a challenging step due to the variation of size, shape, and appearance of cracks. Existing convolutional neural network (CNN)-based crack detection networks, typically using encoder-decoder architectures, may suffer from loss of spatial resolution in the high-to-low and low-to-high resolution processes, affecting the accuracy of prediction. Therefore, we propose ${{\rm HRNet}^{\rm e}}$, an enhanced version of a high-resolution network (HRNet), by removing the downsampling operation in the initial stage, reducing the number of high-resolution representation layers, using dilated convolution, and introducing hierarchical feature integration. Experiments show that the proposed ${{\rm HRNet}^{\rm e}}$ with relatively few parameters can achieve more accuracy and robust performance than other recent approaches.
© 2021 Optical Society of America
Full Article | PDF ArticleMore Like This
Linwei Qiu, Haichao Li, Zhi Li, and Cheng Wang
Appl. Opt. 60(21) 6002-6014 (2021)
Aniwat Juhong, Bo Li, Cheng-You Yao, Chia-Wei Yang, Dalen W. Agnew, Yu Leo Lei, Xuefei Huang, Wibool Piyawattanametha, and Zhen Qiu
Biomed. Opt. Express 14(1) 18-36 (2023)
Minghui Chen, Wenfei Ma, Linfang Shi, Manqi Li, Cheng Wang, and Gang Zheng
Appl. Opt. 60(23) 6761-6768 (2021)