Tower Masking MIM: A Self-Supervised Pretraining Method for Power Line Inspection
- 19 April 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (1) , 513-523
Abstract
For intelligent inspection of power lines, a core task is to detect components in aerial images. Currently, deep supervised learning, a data-hungry paradigm, has attracted great attention. However, considering real-world scenarios, labeled data are usually limited, and the utilization of abundant unlabeled data is rarely investigated in this field. This study deploys a pretrained model for power line component detection based on a self-supervised pretraining approach, which exploits useful information from unannotated data. Concretely, we design a new masking strategy based on the structural characteristic of power lines to guide the pretraining process with meaningful semantic content. Meanwhile, a Siamese architecture is proposed to extract complete global features by using dual reconstruction with semantic targets provided by the proposed masking strategy. Then, the knowledge distillation is utilized to enable the pretrained model to learn both domain-specific and general representations. Moreover, a feature pyramid mechanism is adopted to capture multiscale features, which can benefit the detection task. Experimental results show that the proposed approach can successfully improve the performance of a variety of detection frameworks for power line components, and outperforms other self-supervised pretraining methods.Keywords
Funding Information
- Industry-University Cooperation Project in Fujian Province University (2022H6020)
- Science and technology Project of State Grid Corporation of China (00102126)
- China Scholarship Council (202106650019)
This publication has 37 references indexed in Scilit:
- Detection of Power Line Insulator Defects Using Aerial Images Analyzed With Convolutional Neural NetworksIEEE Transactions on Systems, Man, and Cybernetics: Systems, 2018
- Focal Loss for Dense Object DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- Real‐time segmentation of various insulators using generative adversarial networksIET Computer Vision, 2018
- Energy-Efficient Industrial Internet of UAVs for Power Line Inspection in Smart GridIEEE Transactions on Industrial Informatics, 2018
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Deep Residual Learning for Image Recognition2016
- Localization of multiple insulators by orientation angle detection and binary shape prior knowledgeIEEE Transactions on Dielectrics and Electrical Insulation, 2015
- An Active Contour Model Based on Texture Distribution for Extracting Inhomogeneous Insulators From Aerial ImagesIEEE Transactions on Geoscience and Remote Sensing, 2013
- Condition monitoring of 11 kV distribution system insulators incorporating complex imagery using combined DOST-SVM approachIEEE Transactions on Dielectrics and Electrical Insulation, 2013
- ImageNet: A large-scale hierarchical image database2009