A triple-thresholds pavement crack detection method leveraging random structured forest. (10th December 2020)

• Record Type: Journal Article
• Authors: Peng, Cheng; Yang, Mingqiang; Zheng, Qinghe; Zhang, Jiong; Wang, Deqiang; Yan, Ruyu; Wang, Jiaxing; Li, Bangjun
• Is Part Of: Construction & building materials. Volume 263(2021)
• Publication Date: 2020-12-10
• Subjects: Pavement crack detection -- Random structured forest -- Majority voting -- Threshold -- Morphological operation; Building materials -- Periodicals; 624.18
• DOI: 10.1016/j.conbuildmat.2020.120080
• Languages: English
• ISSNs: 0950-0618

Abstract

Graphical abstract: Highlights: A random structured forest is used to generate crack score map. A triple-thresholds method is developed to detect crack from crack score map. More efficiency in maintaining crack width of the given tolerance margin. Abstract: Automatic pavement crack detection has attracted increasing attention in the field of national infrastructure maintenance and rehabilitation. However, due to inhomogeneous crack pixel value, miscellaneous crack topology, noisy texture surrounding and multifarious illumination condition, automatic pavement crack detection is still a challenging problem. In this paper, a triple-thresholds pavement crack detection method is proposed leveraging random structured forest. Specifically, channel features and pairwise difference features are exploited to enrich the information of patches that comprise the crack image. We tackle the task of predicting local crack patches in a structured learning framework leveraging random structured forest. After that, a crack score map is generated where each position shows the score of crack in the corresponding position of the original image. Then, a triple-thresholds method is introduced to obtain the preliminary crack detection result from the crack score map as well as suppress the noise. Finally, a new morphological operation is proposed to enhance the continuity of the crack on premise of maintaining crack width of the given tolerance margin. Our approach is evaluated by comparing with six state-of-the-art crack detection algorithms using public data-set CFD. Experimental results show that our method outperforms the counterparts since it achieves 95.95 %, 90.59 % and 92.59 % of precision, recall and F1-score, respectively.