InsulatorGAN: A Transmission Line Insulator Detection Model Using Multi-Granularity Conditional Generative Adversarial Nets for UAV Inspection

Abstract

Insulator detection is one of the most significant issues in high-voltage transmission line inspection using unmanned aerial vehicles (UAVs) and has attracted attention from researchers all over the world. The state-of-the-art models in object detection perform well in insulator detection, but the precision is limited by the scale of the dataset and parameters. Recently, the Generative Adversarial Network (GAN) was found to offer excellent image generation. Therefore, we propose a novel model called InsulatorGAN based on using conditional GANs to detect insulators in transmission lines. However, due to the fixed categories in datasets such as ImageNet and Pascal VOC, the generated insulator images are of a low resolution and are not sufficiently realistic. To solve these problems, we established an insulator dataset called InsuGenSet for model training. InsulatorGAN can generate high-resolution, realistic-looking insulator-detection images that can be used for data expansion. Moreover, InsulatorGAN can be easily adapted to other power equipment inspection tasks and scenarios using one generator and multiple discriminators. To give the generated images richer details, we also introduced a penalty mechanism based on a Monte Carlo search in InsulatorGAN. In addition, we proposed a multi-scale discriminator structure based on a multi-task learning mechanism to improve the quality of the generated images. Finally, experiments on the InsuGenSet and CPLID datasets demonstrated that our model outperforms existing state-of-the-art models by advancing both the resolution and quality of the generated images as well as the position of the detection box in the images.

Real-time power line segmentation detection based on multi-attention with strong semantic feature extractor

“…Among them, the semantic segmentation detection algorithm based on generative adversarial network mainly relies on the game between discriminator and generator for semantic segmentation detection. chenwenxiang et al [27] proposed the InsulatorGAN network model for power inspection and proposed the InsuG-enSet dataset for power inspection; wang Jinyu et al [28] proposed the CPLD dataset as the research object and proposed KCIGD generative adversarial network model for power inspection; zhuke jian et al [29]proposed a detection algorithm for small-current power earthing systems based on generative adversarial networks. Although semantic segmentation models based on generative adversarial networks can be applied to power inspection tasks, such algorithms are difficult to train due to their complex structure;…”

A Review on Unmanned Aerial Vehicle Remote Sensing: Platforms, Sensors, Data Processing Methods, and Applications

“…In the authors' experiment, the recognition accuracy was 88.7%. Chen et al [177] proposed a method to generate wire insulator image data based on UAV RGB images. Aiming at the characteristics of a low spatial resolution and less training data of insulator image data of power line towers obtained from UAV RGB images, the authors proposed a method to generate high-resolution and realistic insulator detection images with a conditional GAN [178] for expanding training data.…”

Transmission Line Fault Insulator Detection Based on GAN- Faster RCNN

“…There are also other detection methods, such as the fault detection technology based on the SSD (Single Shot Detector) algorithm proposed by Wang et al [13] , but the detection accuracy is low. Chen et al [14] proposed the CGAN method, which improved the quality of the training dataset and identified insulators, but did not study fault insulator detection.…”