AUTHOR=Yu Hongliang , Zhu Lei , Li Dongbiao , Wang Qi , Liu Xiangyang , Shen Caihua 

TITLE=Comparative Study on Concrete Crack Detection of Tunnel Based on Different Deep Learning Algorithms

JOURNAL=Frontiers in Earth Science

VOLUME=Volume 9 - 2021

YEAR=2022

URL=https://www.frontiersin.org/journals/earth-science/articles/10.3389/feart.2021.817785

DOI=10.3389/feart.2021.817785

ISSN=2296-6463

ABSTRACT=The computer visual inspection for surface cracks of concrete structure is characterized by convenient and efficient on-site inspection around the clock. Segmentation method of an instance and semantic segmentation method are adopted in this paper to realize the surface crack identification of concrete structure, and designs concrete crack detection based on two different deep learning methods. The crack area, output the crack mask and maintain the crack shape information can be shown in the experimental results. Finally, the advantages and disadvantages of the two methods are compared and analyzed from a multi-directional perspective.