Efficient and accurate methods for identifying and seat belt defects are crucial for the efficient production of seat belts. However, traditional seat belt image recognition and detection algorithms often suffer from issues such as poor adaptability, sensitivity to changes in the working environment.To address this issue, this paper proposes a deep learning based detection model Defeat YOLO, which enhances the spatial semantic information extraction capability of YOLOv10 backbone through CBAM attention mechanism. The improved Defeat YOLO model has significantly improved the accuracy and efficiency of seat belt defect detection.

Yang Xu, Xingkun Li, Yuan Liu, Yongzhao Liu, Guodong Chen. Research on Seat Belt Defect Detection Method Based on Deep Learning. International Journal of New Developments in Engineering and Society (2025), Vol. 9, Issue 1: 73-79. https://doi.org/10.25236/IJNDES.2025.090110.

[1] Yang Z, Cai Z, et al. A new method of vision-based seat belt detection[J]. International Journal of Embedded Systems, 2019, 11(6): 755-763.

[2] Ma Liping, Cui Ming, Zhu Peiyi. A surface defect detection system for automotive seat belts based on machine vision [J]. Machine Tool and Hydraulic, 2018, 46 (02): 134-8. 

[3] Ruan Huixiong. Research on Key Technologies of GIGE Industrial CIS Camera [D]. University of Electronic Science and Technology of China, 2022. 

[4] Jin Lili, Wei Lisheng. A defect detection method for solar panels based on improved YOLOv10n [J/OL]. Journal of Chongqing Technology and Business University (Natural Science Edition), 2022.

[5] CHEN Y, DING Y, ZHAO F, et al. Surface defect detection methods for industrial products: A review [J]. Applied Sciences, 2021, 11(16): 7657.

[6] Wei Lisheng, Li Ming. A review of surface defect detection of industrial products based on deep learning [J]. Journal of Suihua University, 2024, 44 (06): 151-156.

[7] CHEN J, LIU Z, WANG H, et al. Automatic defect detection of fasteners on the catenary support device using deep convolutional neural network [J]. IEEE Transactions on Instrumentation and Measurement, 2017, 67(2): 257-69.

[8] FAHIM F, HASAN M S. Enhancing the reliability of power grids: A YOLO based approach for insulator defect detection [J]. e-Prime-Advances in Electrical Engineering, Electronics and Energy, 2024, 9(100663).

[9] Li Qiangqiang, Gao Jun, Shao Xing, et al. Research on Steel Surface Defect Detection Based on YOLOv5 and ConvNext [J]. Combination Machine Tool and Automation Processing Technology, 2024, 10): 160-5+70. 

[10] MEI S, YANG H, YIN Z. An unsupervised-learning-based approach for automated defect inspection on textured surfaces [J]. IEEE transactions on instrumentation and measurement, 2018, 67(6): 1266-77.

[11] Shen Jing, Zeng Qing, Gao Yanan, et al. Vehicle and pedestrian detection method based on YOLOv10s [J]. Computer Knowledge and Technology, 2024, 20 (24): 25-7+39.

[12] Wu Sijia. Research on Lightweight Classification Network for Remote Sensing Images Based on Deep Learning [D]. Henan University of Technology, 2024.

[13] Zhou Luqing, Jia Ke, Feng Ao, et al. Improved ResNet image classification method by integrating self attention mechanism [J]. Software Guide, 2024, 23 (10): 173-8.

[14] Liu Lianhai, Li Huiye, Mao Donghui CBAM-CNN network intrusion detection method based on image convex hull features [J]. Information Network Security, 2024, 24 (09): 1422-31.

[15] Xu Jigao, Chen Jiangyi, Qin Dongchen, et al. Research on surface defect detection of steel based on CNN and CBAM [J]. Mechanical Design and Manufacturing, 2025, (02):149-152. 

[16] Zhang Nannan, Zhang Xiao, Bai Tiecheng, et al. A method for identifying cotton leaf pests and diseases in natural environments based on CBAM-YOLO v7 [J]. Journal of Agricultural Machinery, 2023, 54 (S1): 239-44.