Education, Science, Technology, Innovation and Life
Open Access
Sign In

GMI-DETR: Insulator defect detection network based on GSConv and multi-scale isometric convolution

Download as PDF

DOI: 10.23977/acss.2026.100111 | Downloads: 5 | Views: 258

Author(s)

Xuanyu Liao 1, Chengjiang Zhou 1

Affiliation(s)

1 School of Information Science and Technology, Yunnan Normal University, Kunming, Yunnan, China

Corresponding Author

Chengjiang Zhou

ABSTRACT

As a core component of high-voltage transmission lines, the accuracy and efficiency of insulator defect detection are directly related to the safe and stable operation of power systems. Aiming at the problems of insufficient accuracy, weak small-target defect recognition ability and poor adaptability to complex backgrounds in existing insulator detection algorithms, this study introduces a novel insulator defect detection network that integrates GSConv and multi-scale isometric convolution. Firstly, we design the Group Sparse Convolution Cross-stage Fusion Module (GSC), which reduces the number of model parameters and computational overhead while enhancing the feature discrimination ability. Secondly, the Multi-scale Isometric Convolution Module (CRMIC) is constructed to strengthen the recognition capability for small-target defects. Finally, a parallel architecture combining the CRMIC branch and the GSC branch is built to achieve efficient integration of semantic information and spatial details, thereby improving the adaptability to defects with variable scales and complex backgrounds. Experimental results show that, compared with the Baseline, the proposed GMI-DETR achieves 88.0% mAP@50-95 and 99.3% mAP@50 on public datasets, with respective improvements of 0.5% and 0.3%. The model proposed in this paper demonstrates excellent performance in surface defect detection.

KEYWORDS

Insulator; GSConv; MIC; DETR; Defect detection

CITE THIS PAPER

Xuanyu Liao, Chengjiang Zhou. GMI-DETR: Insulator defect detection network based on GSConv and multi-scale isometric convolution. Advances in Computer, Signals and Systems (2026). Vol. 10, No. 1, 84-92. DOI: http://dx.doi.org/10.23977/acss.2026.100111.

REFERENCES

[1] W. Yi, S. Ma, R. Li, Insulator and defect detection model based on improved yolo-s, IEEE Access 11 (2023) 93215–93226, 10.1109/ACCESS.2023.3309693. 
[2] M. Zhou, B. Li, J. Wang, S. He, Fault detection method of glass insulator aerial image based on the improved yolov5, IEEE Transactions on Instrumentation and Measurement 72 (2023) 1–10, 10.1109/TIM.2023.3269099.
[3] Z.-D. Zhang, B. Zhang, Z.-C. Lan, H.-C. Liu, D.-Y. Li, L. Pei, W.-X. Yu, Finet: An insulator dataset and detection benchmark based on synthetic fog and improved yolov5, IEEE Transactions on Instrumentation and Measurement  71 (2022) 1–8, 10.1109/TIM.2022.3194909.
[4] K. Hao, G. Chen, L. Zhao, Z. Li, Y. Liu, C. Wang, An insulator defect detection model in aerial images based on multiscale feature pyramid network, IEEE Transactions on Instrumentation and Measurement 71 (2022) 1–12, 10.1109/TIM.2022.3200861.
[5] J. Liu, M. Hu, J. Dong, X. Lu, The application of a lightweight model fa-yolov5 with fused attention mechanism in insulator defect detection, Frontiers in Energy Research 11 (2023), 10.3389/fenrg.2023. 1283394. 
[6] X. Tian, M. Zhang, G. Lu, Power line insulator defect detection using cnn with dense connectivity and efficient attention mechanism, MULTIMEDIA TOOLS AND APPLICATIONS 83 (10) (2024) 28305–28322, 10.1007/s11042-023-15522-7. 
[7] Z. Tao, Y. He, S. Lin, T. Yi, M. Li, Snakenet: An adaptive network for small object and complex background for insulator surface defect detection, Computers and Electrical Engineering 117 (2024) 109259, https://doi.org/10.1016/j.compeleceng.2024.109259.
[8] L. Jin, W. Ding, S. Han, J. Wang, A real-time edge inference method for insulator contamination detection with yolov11-ssl,  IEEE Transactions on Instrumentation and Measurement 74 (2025) 1–15, 10.1109/TIM.2025.3565254.
[9]  D. Li, P. Yang, Y. Zou, Optimizing insulator defect detection with improved detr models, Mathematics .2024; 12 (10).
[10]  H. Li, J. Li, H. Wei, Z. Liu, Z. Zhan, Q. Ren, Slim-neck by gsconv: a lightweight-design for real-time detector architectures,  Journal of Real-Time Image Processing ,2024, 21 (3), 10.1007/s11554-024-01436-6.
[11] H. Wang, J. Peng, F. Huang, J. Wang, J. Chen, Y. Xiao, MICN: Multi-scale local and global context modeling for long-term series forecasting, in: The Eleventh International Conference on Learning Representations, 2023, https://openreview.net/forum?id=zt53IDUR1U. 

Downloads: 44983
Visits: 1012078

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.