ABSTRACT
Aerial photography patrol has become the main method of electric power patrol on transmission lines instead of manual patrol, and the integrity of insulators on transmission lines directly affects the power supply reliability. Under the interference of complex background, traditional insulator detection method tends to have a low ability to perform the detection tasks. To solve this problem, we proposed a new method based on enhanced YOLOv4. Based on watershed algorithm and data augmentation combinations, the problem of accurate image detection of aerial photo insulator is studied. Combined with the watershed algorithm and data augmentation combinations, the enhanced YOLO model has robust ability against different distances, various lighting conditions in complex environments. It is shown that our proposed method achieved competitive performance in the experiments.
- Wang Y, Wang J, Gao F, et al. Detection and Recognition for Fault Insulator Based on Deep Learning[C]// 2018 11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI).Google Scholar
- Miao X, Liu X, Chen J, et al. Insulator Detection in Aerial Images for Transmission Line Inspection Using Single Shot Multibox Detector [J]. IEEE Access, 2019:1--1.Google Scholar
- Ren S, He K, Girshick R, et al. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39(6):1137--1149.Google ScholarDigital Library
- Redmon J, Farhadi A. YOLO9000: Better, Faster, Stronger[C]// IEEE Conference on Computer Vision & Pattern Recognition. IEEE, 2017:6517--6525.Google Scholar
- Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation[C]// International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer International Publishing, 2015.Google Scholar
- Liu W, Anguelov D, Erhan D, et al. SSD: Single Shot MultiBox Detector[J]. European Conference on Computer Vision, 2016.Google ScholarCross Ref
- Redmon J, Farhadi A. YOLOv3: An Incremental Improvement[J]. arXiv e-prints, 2018.Google Scholar
- Bochkovskiy A, Wang C Y, Liao H. YOLOv4: Optimal Speed and Accuracy of Object Detection[J]. 2020.Google Scholar
- Liu S, Qi L, Qin H, et al. Path Aggregation Network for Instance Segmentation[J]. IEEE, 2018.Google ScholarCross Ref
- He K, Zhang X, Ren S, et al. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2014, 37(9):1904--16.Google ScholarDigital Library
- Lin T Y, Dollar P, Girshick R, et al. Feature Pyramid Networks for Object Detection[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society, 2017.Google Scholar
- Bieniek A, Moga A. An efficient watershed algorithm based on connected components [J]. Pattern Recognition, 2000, 33(6):907--916.Google ScholarCross Ref
- Liu Y, Huang X. Research on Insulator Burst Fault Identification Based on YOLOv4 and Improved Watershed Algorithm [J]. Power System and Clean Energy, 2021, 5 (7): 51--57.Google Scholar
- Wang S, "An Augmentation Small Object Detection Method Based on NASFPN," 2020 7th International Conference on Information Science and Control Engineering (ICISCE), 2020, pp. 213--218, doi: 10.1109/ICISCE50968.2020.00054.Google ScholarCross Ref
Index Terms
- A Novel Transmission Line Insulator Detection Method Based on Enhanced YOLO Model
Recommendations
Semi-supervised Cloud Edge Collaborative Power Transmission Line Insulator Anomaly Detection Framework
Image and GraphicsAbstractThe widely deployed power transmission line expedites developing the age of electricity. Thus, it is necessary to maintain a power system with a great quantity of manpower and material resources, especially for crucial equipment, such as insulator ...
Insulator Detection Based on SSD with the Default Box Adaptively Selection
CSAE '18: Proceedings of the 2nd International Conference on Computer Science and Application EngineeringDetecting1 power line insulator automatically has important practical significance for the stable and reliable operation of the entire power system. In this paper, Single Shot Multibox Detector is applied to target detection of power line insulator ...
SMD-YOLO: An efficient and lightweight detection method for mask wearing status during the COVID-19 pandemic
Highlights- A face mask detection and monitoring system is developed by using an improved variant of YOLOv4-tiny.
Abstract Background and ObjectiveAt present, the COVID-19 epidemic is still spreading worldwide and wearing a mask in public areas is an effective way to prevent the spread of the respiratory virus. Although there are many deep ...
Comments