A segmentation algorithm for train wheel tread defect area based on attention mechanism

Wan Jiang; Kai Yang; Chunrong Qiu; Jinlong Li; Rongrong Qin; Dan Jiang; Min Xu

doi:10.1117/12.2653162

15 December 2022 A segmentation algorithm for train wheel tread defect area based on attention mechanism

Wan Jiang, Kai Yang, Chunrong Qiu, Jinlong Li, Rongrong Qin, Dan Jiang, Min Xu

Proceedings Volume 12478, Thirteenth International Conference on Information Optics and Photonics (CIOP 2022); 124781C (2022) https://doi.org/10.1117/12.2653162
Event: Thirteenth International Conference on Information Optics and Photonics (CIOP 2022), 2022, Xi'an, China

Abstract

The defect of the train wheel tread is a threat to its safe driving, and the defect detection of the tread is an important work. The extraction of defect area is a crucial link. In this paper, we propose a segmentation algorithm of tread defect area based on attention mechanism, which realizes the more accurate segmentation of tread defect area.This algorithm uses U-net as the backbone network, firstly, introduces the Lovasz-Softmax loss, secondly, CBAM is introduced between the encoder and decoder. Get the attention feature map information in the channel and space dimensions, and then multiply the two feature map information with the original input feature map to make adaptive feature correction to obtain a more accurate feature map and improve the accuracy of the segmentation algorithm.Validated on the dataset of train wheel tread, and the experimental results show that the algorithm PA is 99.54% and mIoU is 98.27%, which improves by 0.83% and 0.73% compared with Unet algorithm, which verifies the effectiveness of the algorithm.

Citation Download Citation

Wan Jiang, Kai Yang, Chunrong Qiu, Jinlong Li, Rongrong Qin, Dan Jiang, and Min Xu "A segmentation algorithm for train wheel tread defect area based on attention mechanism", Proc. SPIE 12478, Thirteenth International Conference on Information Optics and Photonics (CIOP 2022), 124781C (15 December 2022); https://doi.org/10.1117/12.2653162

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available