Block Sparse Low-rank Matrix Decomposition based Visual Defect Inspection of Rail Track Surfaces

• Published in: KSII transactions on Internet and information systems 2019, 13(12), , pp.6043-6062
• Main Authors: Zhang, Linna, Chen, Shiming, Cen, Yigang, Cen, Yi, Wang, Hengyou, Zeng, Ming
• Format: Article
• Language: English
• Subjects: Design and construction; Railroads; 컴퓨터학
• ISSN: 1976-7277; 1976-7277
• DOI: 10.3837/tiis.2019.12.014

Low-rank matrix decomposition has shown its capability in many applications such as image in-painting, de-noising, background reconstruction and defect detection etc. In this paper, we consider the texture background of rail track images and the sparse foreground of the defects to construct a low-rank matrix decomposition model with block sparsity for defect inspection of rail tracks, which jointly minimizes the nuclear norm and the 2-1 norm. Similar to ADM, an alternative method is proposed in this study to solve the optimization problem. After image decomposition, the defect areas in the resulting low-rank image will form dark stripes that horizontally cross the entire image, indicating the preciselocations of the defects. Finally, a two-stage defect extraction method is proposed to locate the defect areas. The experimental results of the two datasets show that our algorithm achieved better performance compared with other methods. Keywords: Rail surface inspection, Low-rank matrix recovery, 2-1 norm, block sparsity