A hybrid deep learning based framework for component defect detection of moving trains

• Main Authors: CHEN, Cen, LI, Kenli, CHENG, Zhongyao, PICCIALLI, Francesco, HOI, Steven C. H., ZENG, Zeng
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2022
• Subjects: Automatic defect detection; deep convolutional neural networks; Deep learning; Feature extraction; Image segmentation; Inspection; Object detection; Rail transportation; railway system; Semantics; train component defects; visual inspection; China; Databases and Information Systems; Transportation
• Online Access: https://ink.library.smu.edu.sg/sis_research/6181
• Institution: Singapore Management University

Defect detection of trains is of great significance for operation safety and maintenance efficiency for railway maintenance. Nowadays, China railway system utilizes high-speed line scan cameras to capture images of critical parts of moving trains. The visual inspection on the images still heavily relies on manual interpretation. To reduce the labor requirements, we propose a novel two-stage deep learning based framework for component defect detection of moving trains. The proposed framework is composed of two major successive stages: detecting train components by using our proposed hierarchical object detection scheme (HOD), and detecting component defects based on multiple neural networks and image processing methods. Our proposed HOD can effectively detect and localize train components from large to small in a hierarchical way. Furthermore, a gated feature fusion method that can extract and combine the hierarchical contextual features and spatial contexts is also proposed to improve the performance. To the best of our knowledge, it is the first time in the literature that component defect detection of moving trains is systematically analyzed. Extensive experiments on real images from China railway system have demonstrated that our framework outperforms the state-of-the-art baselines significantly.