Detection and Evaluation Method of Transmission Line Defects Based on Deep Learning

Abstract

The issues of existing research on transmission line detection include the following three: only detects a few categories, no open transmission line component dataset, and no unified, comprehensive evaluation index. In this paper, we propose a detection and evaluation method of defect for transmission line inspection based on deep learning. The transmission line contains various pivotal components, while previous research has mostly focused on a few categories. In the proposed approach, the following study is performed by establishing a transmission line dataset named Wire_10, which considers defects as a category. Wire_10 contains 8 defects in transmission line components, such as insulator defect, triple-plate defect, damper defect, grading ring defect, and et al., as well as nest and foreign body that attached to the transmission line. The object detection of aerial images taken during the actual inspection is susceptible to background and lighting. These two factors are used as variables to define the background-dataset and the lighting-dataset. Faster R-CNN, an end-to-end and high recognition accuracy deep learning algorithm, is used to build detection models with transfer learning and fine-tuning. The results show that the detection method can accurately identify the defect categories in the Wire_10 dataset and is robust to aerial images with complex backgrounds and different lighting. The proposed method can effectively and accurately identify defects in the automatic inspection of transmission lines. INDEX TERMS Transmission line defects, deep learning, aerial image, robustness.

Detecting Power Lines Using Point Instance Network for Distribution Line Inspection

“…For instance, the weights from the RetinaNet object detector [34], which was originally pretrained on ImageNet, are fine-tuned to automatically map roadside utility poles with crossarms from Google Street View images [35]. Faster R-CNN [36], an endto-end deep learning algorithm that was also pretrained on the ImageNet dataset, was used in [37] to build a detection model that can accurately identify transmission line faults categories. Lastly, the Mask R-CNN [38], also pretrained on ImageNet, was improved to develop a segmentation algorithm that can detect power lines [39].…”

Detection of bird species related to transmission line faults based on lightweight convolutional neural network

“…The camera moves relative to the targets during shooting, resulting in a blurred image [19]. However, the essence of image blur is the result of convolution with the point spread function (PSF), that is $$\begin{equation}g(x,y) = f(x,y) * h(x,y) + n(x,y)\end{equation}$$where f ( x , y ) and g ( x , y ) respectively represents the input image and that after motion blur, h ( x , y ) is the blurring function of PSF that convolves an original image, and n ( x , y ) is the additive noise function.…”

“…Traditional selection method of anchors is difficult to improve the accuracy, so this paper adopts the method of calculating the anchors in YOLOv2 [31], and uses the K‐means clustering algorithm to cluster the artificially labelled real bounding boxes in the training set, so as to obtain the best size of anchors. Then six anchors were selected according to the average IoU to predict the bounding box, thus to improve the detection accuracy [19]. The distance function formula for clustering is $$\begin{equation}d(box,centroid) = 1 - {\rm{IoU(}}box,centroid{\rm{)}}\end{equation}$$where, box represents the bounding box labelled in training samples, and centroid is the number of cluster centres, which is set as 9 here.…”

Thermal Defect Detection for Substation Equipment Based on Infrared Image Using Convolutional Neural Network

“…After pre-processing, the image of the substation equipment still contains irrelevant information, such as time and watermark. The processing speed, efficiency, and accuracy will be affected due to the image containing dense pixel information [36,37]. Therefore, it is necessary to locate and segment the RoI from the background.…”