A hierarchical learning approach for railway fastener detection using imbalanced samples. (December 2021)

• Record Type: Journal Article
• Authors: Liu, Jianwei; Teng, Yun; Shi, Bo; Ni, Xuefeng; Xiao, Weichu; Wang, Chao; Liu, Hongli
• Is Part Of: Measurement. Volume 186(2021)
• Publication Date: 2021-12
• Subjects: Fastener detection -- Hierarchical learning -- Deep detection network -- Region classification -- Decision tree; Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2021.110240
• Languages: English
• ISSNs: 0263-2241

Abstract

Highlights: A detection network called MSF-DDN is proposed to locate fastener regions. A new method called RCN&DT is proposed to detect the imbalanced fasteners. A region classification network is proposed to recognize type of key sub-regions. Abstract: Fastener needs to be detected periodically to maintain the railway safety. However, the detection performance of the existing methods is insufficient in the case of imbalanced fastener samples. To tackle this problem, a hierarchical learning approach which consists of fastener localization and fastener detection is proposed in this paper. Firstly, a multi-scale features-based deep detection network (MSF-DDN) is proposed to locate the fastener regions from railway images. Then, a region classification network is constructed to recognize the type of key sub-regions obtained from the located fastener region images. Finally, fastener detection is achieved by analyzing the recognition results of key sub-regions through the constructed decision tree. A large number of experiments are conducted on the collected real railway images. The experimental results indicate that the hierarchical learning approach achieves an average precision of 96.4% and recall of 96.3% on the detection of imbalanced fasteners, which outperforms state-of-the-art methods.