2020/09/22 by B. G. Vijay Kumar, Kumar, Babloo, Sayantari Ghosh +1
Engineering · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Industrial Vision Systems and Defect Detection #Infrastructure Maintenance and Monitoring #Structural Health Monitoring Techniques #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2009.10612
openalex publication_date 2020/09/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Due to cyclic loading and fatigue stress cracks are generated, which affect\nthe safety of any civil infrastructure. Nowadays machine vision is being used\nto assist us for appropriate maintenance, monitoring and inspection of concrete\nstructures by partial replacement of human-conducted onsite inspections. The\ncurrent study proposes a crack detection method based on deep convolutional\nneural network (CNN) for detection of concrete cracks without explicitly\ncalculating the defect features. In the course of the study, a database of 3200\nlabelled images with concrete cracks has been created, where the contrast,\nlighting conditions, orientations and severity of the cracks were extremely\nvariable. In this paper, starting from a deep CNN trained with these images of\n256 x 256 pixel-resolution, we have gradually optimized the model by\nidentifying the difficulties. Using an augmented dataset, which takes into\naccount the variations and degradations compatible to drone videos, like,\nrandom zooming, rotation and intensity scaling and exhaustive ablation studies,\nwe have designed a dual-channel deep CNN which shows high accuracy (~ 92.25%)\nas well as robustness in finding concrete cracks in realis-tic situations. The\nmodel has been tested on the basis of performance and analyzed with the help of\nfeature maps, which establishes the importance of the dual-channel structure.\n