[1]ZHAO Zhenbing,TANG Chenkang,ZHANG Jingliang,et al.Rust knowledge-guided dual-stage detection method for distribution line fitting and defect detection[J].CAAI Transactions on Intelligent Systems,2026,21(1):167-178.[doi:10.11992/tis.202507033]
Copy

Rust knowledge-guided dual-stage detection method for distribution line fitting and defect detection

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 21 Number of periods: 2026 1 Page number: 167-178 Column: 学术论文—智能系统 Public date: 2026-03-05
Title:
Rust knowledge-guided dual-stage detection method for distribution line fitting and defect detection
Author(s):
ZHAO Zhenbing1; 2; 3;  TANG Chenkang1;  ZHANG Jingliang1;  BI Yuxuan1;  LI Haopeng1
1. Department of Electronic and Communication Engineering, North China Electric Power University, Baoding 071003, China;
2. Hebei Key Laboratory of Power Internet of Things Technology, North China Electric Power University, Baoding 071003, China;
3. Engineering Research Center of Intelligent Computing for Complex Energy Systems, Ministry of Education, North China Electric Power University, Baoding 071003, China
Keywords:
distribution lines; object detection; defect detection; fittings; tension clamps; rust knowledge; frequency feature fusion; adaptive texture extraction
CLC:
TP183
DOI:
10.11992/tis.202507033
Abstract:
Aiming at the challenges of small target feature extraction in aerial images, high false detection rates under complex lighting conditions, and low inter-class differences between normal and rusted fittings in corrosion detection of distribution line hardware, this paper proposes a rust knowledge-guided dual-stage detection method. First, a coarse-to-fine dual-stage framework is constructed: the coarse detection phase employs a foreground aggregation module to achieve density clustering of target regions and suppress background interference. Second, a rust knowledge extraction module is proposed, integrating illumination-invariant features with an adaptive texture extraction strategy to establish chromatic-frequency joint representations. Finally, a frequency-aware feature fusion network is introduced, utilizing adaptive low-pass filtering and high-frequency enhancement mechanisms to optimize multi-scale feature consistency, while a deformable detection head is proposed to improve the modeling capability for irregular rust morphologies. Experimental results demonstrate that the proposed method achieves mAP50 and mAP of 85.8% and 62.5%, respectively, on a self-built dataset, and exhibits strong generalization capability on public power inspection datasets, providing an efficient solution for defect detection of distribution equipment in complex scenarios.
References:
[1] 陶岩, 张辉, 黄志鸿, 等. 面向配电网典型部件的热故障精准判别方法[J]. 智能系统学报, 2025, 20(2): 506-515 TAO Yan, ZHANG Hui, HUANG Zhihong, et al. Accurate identification of thermal faults for typical components of distribution networks[J]. CAAI transactions on intelligent systems, 2025, 20(2): 506-515
[2] NGUYEN V N, JENSSEN R, ROVERSO D. Automatic autonomous vision-based power line inspection: a review of current status and the potential role of deep learning[J]. International journal of electrical power & energy systems, 2018, 99: 107-120
[3] 纪钢, 吴萍萍. 在HSV下的材料腐蚀特征区域颜色与边界量化处理[J]. 重庆理工大学学报(自然科学), 2016(1): 63-69 JI Gang, WU Pingping. Processing of regional color and boundary quantization about material erosion in HSV[J]. Journal of Chongqing University of Technology (natural science), 2016(1): 63-69
[4] HUANG Xinbo, ZHANG Xiaoling, ZHANG Ye, et al. A method of identifying rust status of dampers based on image processing[J]. IEEE transactions on instrumentation and measurement, 2020, 69(8): 5407-5417
[5] GUO Zhimin, TIAN Yangyang, MAO Wandeng. A robust faster R-CNN model with feature enhancement for rust detection of transmission line fitting[J]. Sensors, 2022, 22(20): 7961
[6] 王凌云, 李婷宜, 李阳, 等. 基于FEF-DeepLabV3+的电力金具锈蚀分割方法[J]. 电子测量与仪器学报, 2023, 37(7): 166-176 WANG Lingyun, LI Tingyi, LI Yang, et al. Rust segmentation method for power fittings based on FEF-DeepLabV3+[J]. Journal of electronic measurement and instrumentation, 2023, 37(7): 166-176
[7] ZHAO Zhenbing, QI Hongyu, QI Yincheng, et al. Detection method based on automatic visual shape clustering for pin-missing defect in transmission lines[J]. IEEE transactions on instrumentation and measurement, 2020, 69(9): 6080-6091
[8] CHEN Xiaojiao, AN Zhenyu, HUANG Liansheng, et al. Surface defect detection of electric power equipment in substation based on improved YOLOV4 algorithm[C]//2020 10th International Conference on Power and Energy Systems. Chengdu: IEEE, 2021: 256-261.
[9] 叶飞, 骆星智, 宋永春, 等. 基于双特征融合的改进R-CNN电力小金具缺陷检测方法研究[J]. 电子测量与仪器学报, 2023, 37(7): 213-220 YE Fei, LUO Xingzhi, SONG Yongchun, et al. Research on an improved R-CNN power small fitting defect detection method based on dual-feature fusion[J]. Journal of electronic measurement and instrumentation, 2023, 37(7): 213-220
[10] 赵振兵, 郭广学, 王艺衡, 等. 融合边缘感知与统计纹理知识的输电线路金具锈蚀检测[J]. 智能系统学报, 2024, 19(5): 1228-1237 ZHAO Zhenbing, GUO Guangxue, WANG Yiheng, et al. Rust detection in transmission line fittings via fusion of edge perception and statistical texture knowledge[J]. CAAI transactions on intelligent systems, 2024, 19(5): 1228-1237
[11] 倪有豪, 陆欢, 季超, 等. 基于语义分割的桥梁锈蚀病害识别对比分析[J]. 东南大学学报(自然科学版), 2023, 53(2): 201-209 NI Youhao, LU Huan, JI Chao, et al. Comparative analysis of bridge corrosion identification based on semantic segmentation[J]. Journal of Southeast University (natural science edition), 2023, 53(2): 201-209
[12] 赵振兵, 席悦, 冯烁, 等. 面向复杂场景的变电设备锈蚀检测方法[J]. 智能系统学报, 2025, 20(3): 679-688 ZHAO Zhenbing, XI Yue, FENG Shuo, et al. A corrosion detection method of substation equipment for complex scenarios[J]. CAAI transactions on intelligent systems, 2025, 20(3): 679-688
[13] ZHOU Xingyi, KOLTUN V, KR?HENB?HL P. Probabilistic two-stage detection[EB/OL]. (2021-03-12) [2025-07-30]. https://arxiv.org/abs/2103.07461.
[14] CHENG Shen, FAN Haoqiang, HONG Mingbo, et al. You only look around: learning illumination-invariant feature for low-light object detection[EB/OL]. (2024-10-24)[2025-07-30]. https://arxiv.org/abs/2410.18398.
[15] CHEN Linwei, FU Ying, GU Lin, et al. Frequency-aware feature fusion for dense image prediction[J]. IEEE transactions on pattern analysis and machine intelligence, 2024, 46(12): 10763-10780
[16] XIONG Yuwen, LI Zhiqi, CHEN Yuntao, et al. Efficient deformable ConvNets: rethinking dynamic and sparse operator for vision applications[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2024: 5652-5661.
[17] LIU Chenguang, GAO Guangshuai, HUANG Ziyue, et al. YOLC: you only look clusters for tiny object detection in aerial images[J]. IEEE transactions on intelligent transportation systems, 2024, 25(10): 13863-13875
[18] LUAN Shangzhen, CHEN Chen, ZHANG Baochang, et al. Gabor convolutional networks[J]. IEEE transactions on image processing, 2018, 27(9): 4357-4366
[19] SHANNON C E. Communication in the presence of noise[J]. Proceedings of the IRE, 1949, 37(1): 10-21
[20] CHOLLET F. Xception: deep learning with depthwise separable convolutions[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 1800-1807.
[21] GIRSHICK R. Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision. Santiago: IEEE, 2016: 1440-1448.
[22] CAI Zhaowei, VASCONCELOS N. Cascade R-CNN: delving into high quality object detection[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 6154-6162.
[23] JOCHER G, STOKEN A, BOROVEC J, et al. Ultralytics YOLOv5: a state-of-the-art real-time object detection system[EB/OL]. (2022-11-22) [2025-07-30]. https://github.com/ultralytics/yolov5.
[24] LI Chuyi, LI Lulu, JIANG Hongliang, et al. YOLOv6: a single-stage object detection framework for industrial applications[EB/OL]. (2022-09-07) [2025-07-30]. https://arxiv.org/abs/2209.02976.
[25] WANG C Y, BOCHKOVSKIY A, LIAO H M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver: IEEE, 2023: 7464-7475.
[26] WANG Gang, CHEN Yanfei, AN Pei, et al. UAV-YOLOv8: a small-object-detection model based on improved YOLOv8 for UAV aerial photography scenarios[J]. Sensors, 2023, 23(16): 7190
[27] WANG C Y, YEH I H, MARK LIAO H Y. YOLOv9: learning what you want toLearn using programmable gradient information[C]//Computer Vision–ECCV 2024. Cham: Springer, 2025: 1-21.
[28] CHEN Hui, CHEN Kai, DING Guiguang, et al. YOLOv10: real-time end-to-end object detection[EB/OL]. (2024-05-23) [2025-07-30]. https://arxiv.org/abs/2405.14458.
[29] CARION N, MASSA F, SYNNAEVE G, et al. End-to-end object detection with transformers[C]//Computer Vision–ECCV 2020. Cham: Springer, 2020: 213-229.
[30] LIU Shilong, LI Feng, ZHANG Hao, et al. DAB-DETR: dynamic anchor boxes are better queries for DETR[EB/OL]. (2022-01-28)[2025-07-30]. https://arxiv.org/abs/2201.12329.
[31] ZHU Xizhou, SU Weijie, LU Lewei, et al. Deformable DETR: deformable transformers for end-to-end object detection[EB/OL]. (2020-10-08)[2025-07-30]. https://arxiv.org/abs/2010.04159.
[32] LIU Shilong, ZENG Zhaoyang, REN Tianhe, et al. Grounding DINO: marrying DINO withGrounded pre-training forOpen-set object detection[C]//Computer Vision–ECCV 2024. Cham: Springer, 2025: 38-55.
[33] VIEIRA E SILVA A L B, DE CASTRO FELIX H, SIM?ES F P M, et al. InsPLAD: a dataset and benchmark for power line asset inspection in UAV images[J]. International journal of remote sensing, 2023, 44(23): 7294-7320
[34] TAO Xian, ZHANG Dapeng, WANG Zihao, et al. Detection of power line insulator defects using aerial images analyzed with convolutional neural networks[J]. IEEE transactions on systems, man, and cybernetics: systems, 2020, 50(4): 1486-1498
Similar References:

Memo

-

Last Update: 2026-01-05

Copyright © CAAI Transactions on Intelligent Systems