Small Target Paste Randomly Data Augmentation Method Based on a Pin-losing Bolt Data Set

Zhao, Wenqing; Jia, Mengying; Zhang, Haiming; Xu, Minfu

doi:10.1109/icpds54746.2021.9689931

Cited by 3 publications

(1 citation statement)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [ 14 ], the authors used wide residuals as the backbone network and selected the optimal structure to achieve effective recognition of bolt defects by adjusting the network-widening dimension. In [ 15 ], a bolt defect data augmentation method was proposed based on random pasting, and it effectively expanded the number of bolt defect samples and improved the accuracy of defect recognition. However, due to the small size of the bolt itself, the bolt image features of the aerial transmission line are difficult to extract, and the bolt defect recognition effect is not satisfactory.…”

Section: Introductionmentioning

confidence: 99%

A New Bolt Defect Identification Method Incorporating Attention Mechanism and Wide Residual Networks

Liu

Zhao

Chen

et al. 2022

Sensors

View full text Add to dashboard Cite

Bolts are important components on transmission lines, and the timely detection and exclusion of their abnormal conditions are imperative to ensure the stable operation of transmission lines. To accurately identify bolt defects, we propose a bolt defect identification method incorporating an attention mechanism and wide residual networks. Firstly, the spatial dimension of the feature map is compressed by the spatial compression network to obtain the global features of the channel dimension and enhance the attention of the network to the vital information in a weighted way. After that, the enhanced feature map is decomposed into two one-dimensional feature vectors by embedding a cooperative attention mechanism to establish long-term dependencies in one spatial direction and preserve precise location information in the other direction. During this process, the prior knowledge of the bolts is utilized to help the network extract critical feature information more accurately, thus improving the accuracy of recognition. The test results show that the bolt recognition accuracy of this method is improved to 94.57% compared with that before embedding the attention mechanism, which verifies the validity of the proposed method.

show abstract

Section: Introductionmentioning

confidence: 99%

A New Bolt Defect Identification Method Incorporating Attention Mechanism and Wide Residual Networks

Liu

Zhao

Chen

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

A supervised data augmentation strategy based on random combinations of key features

Ding

Liu

Zhu

et al. 2023

Information Sciences

View full text Add to dashboard Cite

Research Progress on Power Visual Detection of Overhead Line Bolt Defects Based on UAV Images

Deng,

He,

Zheng

et al. 2024

Drones

View full text Add to dashboard Cite

In natural environments, the connecting bolts of overhead lines and power towers are prone to loosening and missing, posing potential risks to the safe and stable operation of the power system. This paper reviews the challenges in bolt defect detection using power vision technology, with a particular focus on unmanned aerial vehicle (UAV) images. These UAV images offer a cost-effective and flexible solution for detecting bolt defects. However, challenges remain, including missed detection due to the small size of bolts, false detection caused by dense and occluded bolts, and underfitting resulting from imbalanced bolt defect datasets. To address these issues, this paper summarizes solutions that leverage deep learning algorithms. An experimental analysis is conducted on a dataset derived from UAV inspections, comparing the detection characteristics and visualizing the results of various algorithms. The paper also discusses future trends in the application of UAV-based power vision technology for bolt defect detection, providing insights for the advancement of intelligent power inspection.

show abstract

Small Target Paste Randomly Data Augmentation Method Based on a Pin-losing Bolt Data Set

Cited by 3 publications

References 3 publications

A New Bolt Defect Identification Method Incorporating Attention Mechanism and Wide Residual Networks

A New Bolt Defect Identification Method Incorporating Attention Mechanism and Wide Residual Networks

A supervised data augmentation strategy based on random combinations of key features

Research Progress on Power Visual Detection of Overhead Line Bolt Defects Based on UAV Images

Contact Info

Product

Resources

About