Abstract:
Catenary is one of the most crucial parts of an electrified railway system. How to detect the part defects of catenary in time and keep it in a stable and safe operation ...Show MoreMetadata
Abstract:
Catenary is one of the most crucial parts of an electrified railway system. How to detect the part defects of catenary in time and keep it in a stable and safe operation condition are the main tasks for maintenance. The existing data-driven vision-based defect detection methods will face a big challenge that, there are many catenary parts, and each part has several types of defects, but there are few defect sample images for each type of defect, which limits them in real applications. To alleviate this problem, a semantic label-enhanced (LE) variational autoencoder (VAE) method for catenary part defect detection, termed defect VAE (DefVAE), is presented. The proposed method is based on an LE VAE network that determines the distribution boundary in latent feature space of defect sample for additional defect generation. The addition of semantic label information to the VAE improves the interclass distance in latent space, clarifying the boundary and further boosting the capabilities of the defect detection method, which is demonstrated in our experiments. In addition, the defect type is classified by combining the outputs of the classifier confidence and the pixel-level reconstruction error, which is based on a sliding label mode of the VAE. Extensive experiments with the open benchmark dataset MVTec and the catenary dataset collected by ourselves demonstrate that the presented DefVAE outperforms the baseline methods across the majority of indicators.
Published in: IEEE Transactions on Instrumentation and Measurement ( Volume: 72)