Mask-Space Optimized Transformer for Semantic Segmentation of Lithium Battery Surface Defect Images
Mathematics · 20.11.2024 · 12 (22) · 3627
DOI: 10.3390/math12223627 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 20.11.2024. Verfasst von Daozong Sun und 6 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guangdong Province Key Area Research and Development Plan, Enterprise Commissioned Horizontal Projects, 2023 Guangdong Province Science and Technology Innovation Strategic Special Fund (College Students’ Science and Technology Innovation Cultivation) project.
Abstract (Originalsprache)
The segmentation of surface defects in lithium batteries is crucial for enhancing the overall quality of the production process. However, the severe foreground–background imbalance in surface images of lithium batteries, along with the irregular shapes and random distribution of foreground regions, poses significant challenges for defect segmentation. Based on these observations, this paper focuses on the separation of foreground and background in surface defect images of lithium batteries and proposes a novel Mask Space Optimization Transformer (MSOFormer) for semantic segmentation of these images. Specifically, the Mask Boundary Loss (MBL) module in our model provides more efficient supervision during training to enhance the accuracy of the mask computation within the mask attention mechanism, thereby improving the model’s performance in separating foreground and background. Additionally, the Dynamic Spatial Query (DSQ) module allocates spatial information of the image to each query, enhancing the model’s sensitivity to the positions of small foreground targets in various scenes. The Efficient Pixel Decoder (EPD) ensures deformable receptive fields for irregularly shaped foregrounds while further improving the model’s performance and efficiency. Experimental results demonstrate that our method outperforms other state-of-the-art methods in terms of mean Intersection over Union (mIoU). Specifically, our approach achieves an mIoU of 84.18% on the lithium battery surface defect test set and 85.53% and 87.05% mIoUs on two publicly available defect test sets with similar defect characteristics to lithium batteries.
Förderung
- Guangdong Province Key Area Research and Development Plan
- Enterprise Commissioned Horizontal Projects
- 2023 Guangdong Province Science and Technology Innovation Strategic Special Fund (College Students’ Science and Technology Innovation Cultivation) project
Zitieren
APA
Sun, D., Chen, J., Wu, P., Pan, Y., Zhong, H., Deng, Z., & Xue, X. (2024). Mask-Space Optimized Transformer for Semantic Segmentation of Lithium Battery Surface Defect Images. Mathematics, 12(22), 3627. https://doi.org/10.3390/math12223627
Vancouver
Sun D, Chen J, Wu P, Pan Y, Zhong H, Deng Z, et al. Mask-Space Optimized Transformer for Semantic Segmentation of Lithium Battery Surface Defect Images. Mathematics. 2024;12(22):3627. doi:10.3390/math12223627
BibTeX
@article{Sun2024,
author = {Sun, Daozong and Chen, Jiasi and Wu, Peiwen and Pan, Yucheng and Zhong, Hongsheng and Deng, Zihao and Xue, Xiuyun},
title = {Mask-Space Optimized Transformer for Semantic Segmentation of Lithium Battery Surface Defect Images},
journal = {Mathematics},
year = {2024},
volume = {12},
number = {22},
pages = {3627},
doi = {10.3390/math12223627}
}
EUVIMED