Detection of Pin Defects in Aerial Images Based on Cascaded Convolutional Neural Network
Pins are standard fasteners in power transmission lines, and the hidden dangers of pins falling off dramatically affects their safe operation. If a pin is missed, it is called pin defects in this paper. As the pin is a small target and has a complex background, traditional detection algorithms were...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9427490/ |
| _version_ | 1818658115199959040 |
|---|---|
| author | Yewei Xiao Zhiqiang Li Dongbo Zhang Lianwei Teng |
| author_facet | Yewei Xiao Zhiqiang Li Dongbo Zhang Lianwei Teng |
| author_sort | Yewei Xiao |
| collection | DOAJ |
| description | Pins are standard fasteners in power transmission lines, and the hidden dangers of pins falling off dramatically affects their safe operation. If a pin is missed, it is called pin defects in this paper. As the pin is a small target and has a complex background, traditional detection algorithms were used to identify pin defects from aerial images which suffer from poor accuracy and low efficiency. This paper proposed a target detection method based on cascaded convolutional neural networks. First, a small-scale shallow full convolutional neural network was used to obtain the region of interest; then, a deeper convolutional neural network conducted target classification and positioning on the obtained region of interest. Next, a nonlinear multilayer perceptron was introduced, the convolution kernel was decomposed, and the multi-scale feature maps were fused. At this point, an angle variable was added to the classification cross-entropy loss function. Multi-task learning and offline hard sample mining strategies were used in the training phase. The proposed method was tested on a self-built pin dataset and the remote sensing image RSOD dataset, and the experimental results proved its effectiveness. Our method can accurately identify pin defects in aerial images, thereby solving the engineering application problem of pin defect detection in transmission lines. |
| first_indexed | 2024-12-17T03:52:14Z |
| format | Article |
| id | doaj.art-7a961a3858d34bb6a5fa0e03bcb271a7 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-17T03:52:14Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-7a961a3858d34bb6a5fa0e03bcb271a72022-12-21T22:04:42ZengIEEEIEEE Access2169-35362021-01-019730717308210.1109/ACCESS.2021.30791729427490Detection of Pin Defects in Aerial Images Based on Cascaded Convolutional Neural NetworkYewei Xiao0https://orcid.org/0000-0001-9689-3760Zhiqiang Li1https://orcid.org/0000-0002-0259-8910Dongbo Zhang2Lianwei Teng3https://orcid.org/0000-0001-6523-9731School of Information Engineering, Xiangtan University, Xiangtan, ChinaSchool of Information Engineering, Xiangtan University, Xiangtan, ChinaSchool of Information Engineering, Xiangtan University, Xiangtan, ChinaSchool of Information Engineering, Xiangtan University, Xiangtan, ChinaPins are standard fasteners in power transmission lines, and the hidden dangers of pins falling off dramatically affects their safe operation. If a pin is missed, it is called pin defects in this paper. As the pin is a small target and has a complex background, traditional detection algorithms were used to identify pin defects from aerial images which suffer from poor accuracy and low efficiency. This paper proposed a target detection method based on cascaded convolutional neural networks. First, a small-scale shallow full convolutional neural network was used to obtain the region of interest; then, a deeper convolutional neural network conducted target classification and positioning on the obtained region of interest. Next, a nonlinear multilayer perceptron was introduced, the convolution kernel was decomposed, and the multi-scale feature maps were fused. At this point, an angle variable was added to the classification cross-entropy loss function. Multi-task learning and offline hard sample mining strategies were used in the training phase. The proposed method was tested on a self-built pin dataset and the remote sensing image RSOD dataset, and the experimental results proved its effectiveness. Our method can accurately identify pin defects in aerial images, thereby solving the engineering application problem of pin defect detection in transmission lines.https://ieeexplore.ieee.org/document/9427490/Pin defectaerial imagecascaded convolutional neural networknonlinear multilayer perceptronhard sample mining |
| spellingShingle | Yewei Xiao Zhiqiang Li Dongbo Zhang Lianwei Teng Detection of Pin Defects in Aerial Images Based on Cascaded Convolutional Neural Network IEEE Access Pin defect aerial image cascaded convolutional neural network nonlinear multilayer perceptron hard sample mining |
| title | Detection of Pin Defects in Aerial Images Based on Cascaded Convolutional Neural Network |
| title_full | Detection of Pin Defects in Aerial Images Based on Cascaded Convolutional Neural Network |
| title_fullStr | Detection of Pin Defects in Aerial Images Based on Cascaded Convolutional Neural Network |
| title_full_unstemmed | Detection of Pin Defects in Aerial Images Based on Cascaded Convolutional Neural Network |
| title_short | Detection of Pin Defects in Aerial Images Based on Cascaded Convolutional Neural Network |
| title_sort | detection of pin defects in aerial images based on cascaded convolutional neural network |
| topic | Pin defect aerial image cascaded convolutional neural network nonlinear multilayer perceptron hard sample mining |
| url | https://ieeexplore.ieee.org/document/9427490/ |
| work_keys_str_mv | AT yeweixiao detectionofpindefectsinaerialimagesbasedoncascadedconvolutionalneuralnetwork AT zhiqiangli detectionofpindefectsinaerialimagesbasedoncascadedconvolutionalneuralnetwork AT dongbozhang detectionofpindefectsinaerialimagesbasedoncascadedconvolutionalneuralnetwork AT lianweiteng detectionofpindefectsinaerialimagesbasedoncascadedconvolutionalneuralnetwork |