Bolts play an important role in transmission lines, and bolt defects can easily cause abnormality or even failure of transmission lines. However, a large number of bolt defect data are difficult to obtain. Aiming at the problem of bolt defect data with few samples, this paper proposes a method for image generation of bolt defects in transmission lines based on different bolt attributes (DBA-GAN). First, the bolt images are classified according to different attributes, and these categories are used as auxiliary information for Generative Adversarial Network (GAN). Then, DBA-GAN is used to generate bolt images with specified attributes and defects. Finally, the generated bolt images are used to augment the few-shot bolt defect dataset, and the validity is verified on the bolt attribute classification network. The results show that the method in this paper improves the quality of the generated bolt images, and at the same time achieves the purpose of amplifying defective samples.
The fittings detection of transmission lines plays a vital role in ensuring the safe and stable operation of transmission lines. The fitting detection method based on deep learning only scales the original image to a smaller size. However, it ignores the high-definition resolution of the aerial image in the transmission line, resulting in the loss of rich features in the high-resolution aerial image. In order to solve this problem, we observe that aerial images of fittings are concentrated in a particular area of the aerial image. Therefore, we propose a cascading YOLOx model, including Dense Target Regions YOLOx (DTR-YOLOx), which can detect dense target areas, and Multi-Fitting YOLOx (MF-YOLOx), which can detect multiple categories of fittings. In addition, an algorithm based on the connected regions is proposed to automatically generate the dense target region for DTR-YOLOx training, reducing manual labeling costs. Furthermore, the EIOU loss function is introduced to improve the precision of the model's coordinate regression. Experiments show that the AP0.50:0.95 value of our proposed model is 18.4% higher than that of the YOLOx model.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.