Weather-Domain Transfer-Based Attention YOLO for Multi-Domain Insulator Defect Detection and Classification in UAV Images

被引:7
|
作者
Liu, Yue [1 ]
Huang, Xinbo [1 ,2 ]
Liu, Decheng [3 ]
机构
[1] Xian Univ Technol, Sch Elect Engn, Xian 710054, Peoples R China
[2] Xian Polytech Univ, Sch Elect & Informat, Xian 710048, Peoples R China
[3] Xidian Univ, Sch Cyber Engn, Xian 710126, Peoples R China
关键词
cross-modality information; insulator defect detection; classification; image processing;
D O I
10.3390/e26020136
中图分类号
O4 [物理学];
学科分类号
0702 ;
摘要
Insulator defect detection of transmission line insulators is an important task for unmanned aerial vehicle (UAV) inspection, which is of immense importance in ensuring the stable operation of transmission lines. Transmission line insulators exist in complex weather scenarios, with small and inconsistent shapes. These insulators under various weather conditions could result in low-quality images captured, limited data numbers, and imbalanced sample problems. Traditional detection methods often struggle to accurately identify defect information, resulting in missed or false detections in real-world scenarios. In this paper, we propose a weather domain synthesis network for extracting cross-modality discriminative information on multi-domain insulator defect detection and classification tasks. Firstly, we design a novel weather domain synthesis (WDSt) module to convert various weather-conditioned insulator images to the uniform weather domain to decrease the existing domain gap. To further improve the detection performance, we leverage the attention mechanism to construct the Cross-modality Information Attention YOLO (CIA-YOLO) model to improve the detection capability for insulator defects. Here, we fuse both shallow and deep feature maps by adding the extra object detection layer, increasing the accuracy for detecting small targets. The experimental results prove the proposed Cross-modality Information Attention YOLO with the weather domain synthesis algorithm can achieve superior performance in multi-domain insulator datasets (MD-Insulator). Moreover, the proposed algorithm also gives a new perspective for decreasing the multi-domain insulator modality gap with weather-domain transfer, which can inspire more researchers to focus on the field.
引用
收藏
页数:18
相关论文
共 50 条
  • [1] Efficient Cross-Modality Insulator Augmentation for Multi-Domain Insulator Defect Detection in UAV Images
    Liu, Yue
    Huang, Xinbo
    SENSORS, 2024, 24 (02)
  • [2] An Improved YOLO Network for Insulator and Insulator Defect Detection in UAV Images
    Zhou, Fangrong
    Liu, Lifeng
    Hu, Hao
    Jin, Weishi
    Zheng, Zezhong
    Li, Zhongnian
    Ma, Yi
    Wang, Qun
    PHOTOGRAMMETRIC ENGINEERING AND REMOTE SENSING, 2024, 90 (06): : 355 - 361
  • [3] Domain attention model for multi-domain sentiment classification
    Yuan, Zhigang
    Wu, Sixing
    Wu, Fangzhao
    Liu, Junxin
    Huang, Yongfeng
    KNOWLEDGE-BASED SYSTEMS, 2018, 155 : 1 - 10
  • [4] Multi-Domain Sentiment Classification Based on Domain-Aware Embedding and Attention
    Cai, Yitao
    Wan, Xiaojun
    PROCEEDINGS OF THE TWENTY-EIGHTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2019, : 4904 - 4910
  • [5] Multi-Domain Fake News Detection Based on Serial Attention Networks
    Qiu, Chongfeng
    PROCEEDINGS OF 2024 3RD INTERNATIONAL CONFERENCE ON CYBER SECURITY, ARTIFICIAL INTELLIGENCE AND DIGITAL ECONOMY, CSAIDE 2024, 2024, : 91 - 96
  • [6] A2MADA-YOLO: Attention Alignment Multiscale Adversarial Domain Adaptation YOLO for Insulator Defect Detection in Generalized Foggy Scenario
    Li, Jun
    Zhou, Haoxing
    Lv, Ganyun
    Chen, Jianhua
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2025, 74
  • [7] Collaborative attention neural network for multi-domain sentiment classification
    Yue, Chunyi
    Cao, Hanqiang
    Xu, Guoping
    Dong, Youli
    APPLIED INTELLIGENCE, 2021, 51 (06) : 3174 - 3188
  • [8] Collaborative attention neural network for multi-domain sentiment classification
    Chunyi Yue
    Hanqiang Cao
    Guoping Xu
    Youli Dong
    Applied Intelligence, 2021, 51 : 3174 - 3188
  • [9] Manipulation Classification for JPEG Images Using Multi-Domain Features
    Yu, In-Jae
    Nam, Seung-Hun
    Ahn, Wonhyuk
    Kwon, Myung-Joon
    Lee, Heung-Kyu
    IEEE ACCESS, 2020, 8 : 210837 - 210854
  • [10] Manipulation Classification for JPEG Images Using Multi-Domain Features
    Yu, In-Jae
    Nam, Seung-Hun
    Ahn, Wonhyuk
    Kwon, Myung-Joon
    Lee, Heung-Kyu
    Lee, Heung-Kyu (heunglee@kaist.ac.kr), 1600, Institute of Electrical and Electronics Engineers Inc. (08): : 210837 - 210854