TL-YOLO: Foreign-Object Detection on Power Transmission Line Based on Improved Yolov8

被引:6
作者
Shao, Yeqin [1 ]
Zhang, Ruowei [2 ]
Lv, Chang [1 ]
Luo, Zexing [1 ]
Che, Meiqin [1 ]
机构
[1] Nantong Univ, Sch Transportat & Civil Engn, Nantong 226019, Peoples R China
[2] Nantong Univ, Sch Elect Engn, Nantong 226004, Peoples R China
基金
中国国家自然科学基金;
关键词
power transmission line; foreign-object detection; Yolov8; attention mechanism; feature fusion;
D O I
10.3390/electronics13081543
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Foreign objects on power transmission lines carry a significant risk of triggering large-scale power interruptions which may have serious consequences for daily life if they are not detected and handled in time. To accurately detect foreign objects on power transmission lines, this paper proposes a TL-Yolo method based on the Yolov8 framework. Firstly, we design a full-dimensional dynamic convolution (ODConv) module as a backbone network to enhance the feature extraction capability, thus retaining richer semantic content and important visual features. Secondly, we present a feature fusion framework combining a weighted bidirectional feature pyramid network (BiFPN) and multiscale attention (MSA) module to mitigate the degradation effect of multiscale feature representation in the fusion process, and efficiently capture the high-level feature information and the core visual elements. Thirdly, we utilize a lightweight GSConv cross-stage partial network (GSCSP) to facilitate efficient cross-level feature fusion, significantly reducing the complexity and computation of the model. Finally, we employ the adaptive training sample selection (ATSS) strategy to balance the positive and negative samples, and dynamically adjust the selection process of the training samples according to the current state and performance of the model, thus effectively reducing the object misdetection and omission. The experimental results show that the average detection accuracy of the TL-Yolo method reaches 91.30%, which is 4.20% higher than that of the Yolov8 method. Meanwhile, the precision and recall metrics of our method are 4.64% and 3.53% higher than those of Yolov8. The visualization results also show the superior detection performance of the TL-Yolo algorithm in real scenes. Compared with the state-of-the-art methods, our method achieves higher accuracy and speed in the detection of foreign objects on power transmission lines.
引用
收藏
页数:18
相关论文
共 43 条
[1]   Feature GANs: A Model for Data Enhancement and Sample Balance of Foreign Object Detection in High Voltage Transmission Lines [J].
Dou, Yimin ;
Yu, Xiangru ;
Li, Jinping .
COMPUTER ANALYSIS OF IMAGES AND PATTERNS, CAIP 2019, PT II, 2019, 11679 :568-580
[2]  
Guan Qianjun, 2023, 2023 International Conference on the Cognitive Computing and Complex Data (ICCD), P73, DOI 10.1109/ICCD59681.2023.10420656
[3]   Modeling and investigation on the performance enhancement of hovering UAV-based FSO relay optical wireless communication systems under pointing errors and atmospheric turbulence effects [J].
Hayal, Mohammed R. R. ;
Elsayed, Ebrahim E. E. ;
Kakati, Dhiman ;
Singh, Mehtab ;
Elfikky, Abdelrahman ;
Boghdady, Ayman I. I. ;
Grover, Amit ;
Mehta, Shilpa ;
Mohsan, Syed Agha Hassnain ;
Nurhidayat, Irfan .
OPTICAL AND QUANTUM ELECTRONICS, 2023, 55 (07)
[4]   Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2015, 37 (09) :1904-1916
[5]   A New Target Detection Method of Ferrography Wear Particle Images Based on ECAM-YOLOv5-BiFPN Network [J].
He, Lei ;
Wei, Haijun ;
Wang, Qixuan .
SENSORS, 2023, 23 (14)
[6]   Real-time defect detection method based on YOLO-GSS at the edge end of a transmission line [J].
Hou, Chao ;
Li, Zhilei ;
Shen, Xueliang ;
Li, Guochao .
IET IMAGE PROCESSING, 2024, 18 (05) :1315-1327
[7]   UAV-Based Oblique Photogrammetry for Outdoor Data Acquisition and Offsite Visual Inspection of Transmission Line [J].
Jiang, San ;
Jiang, Wanshou ;
Huang, Wei ;
Yang, Liang .
REMOTE SENSING, 2017, 9 (03)
[8]  
Jin Lijun, 2013, Journal of Tongji University (Natural Science), V41, P277, DOI 10.3969/j.issn.0253-374x.2013.02.021
[9]   An Improved YOLOv3 for Foreign Objects Detection of Transmission Lines [J].
Li, Hui ;
Liu, Lizong ;
Du, Jun ;
Jiang, Fan ;
Guo, Fei ;
Hu, Qilong ;
Fan, Lin .
IEEE ACCESS, 2022, 10 :45620-45628
[10]  
Li J., 2017, Power Syst. Clean Energy, V33, P62