Evaluation of Power Insulator Detection Efficiency with the Use of Limited Training Dataset

Abstract

This article presents an analysis of the effectiveness of object detection in digital images with the application of a limited quantity of input. The possibility of using a limited set of learning data was achieved by developing a detailed scenario of the task, which strictly defined the conditions of detector operation in the considered case of a convolutional neural network. The described solution utilizes known architectures of deep neural networks in the process of learning and object detection. The article presents comparisons of results from detecting the most popular deep neural networks while maintaining a limited training set composed of a specific number of selected images from diagnostic video. The analyzed input material was recorded during an inspection flight conducted along high-voltage lines. The object detector was built for a power insulator. The main contribution of the presented papier is the evidence that a limited training set (in our case, just 60 training frames) could be used for object detection, assuming an outdoor scenario with low variability of environmental conditions. The decision of which network will generate the best result for such a limited training set is not a trivial task. Conducted research suggests that the deep neural networks will achieve different levels of effectiveness depending on the amount of training data. The most beneficial results were obtained for two convolutional neural networks: the faster region-convolutional neural network (faster R-CNN) and the region-based fully convolutional network (R-FCN). Faster R-CNN reached the highest AP (average precision) at a level of 0.8 for 60 frames. The R-FCN model gained a worse AP result; however, it can be noted that the relationship between the number of input samples and the obtained results has a significantly lower influence than in the case of other CNN models, which, in the authors’ assessment, is a desired feature in the case of a limited training set.

Insulator Faults Detection in Aerial Images from High-Voltage Transmission Lines Based on Deep Learning Model

“…It can be seen from Figure 7 that the average IoU becomes more and more stable with the increase in k values; when k = 9, the average IoU is 89.13%, and the average IoU varies slowly when the number k is bigger than 9. Finally, the clustering center k was set as 9 for dataset 'InSF-detection', and the initial anchor boxes for insulator faults detection were obtained as follows: (17,13), (23,15), (20,17), (25,17), (21,21), (24,19), (26,23), (23,26), and (30, 28), respectively. Specifically, 1331 simulated insulator fault images were collected using the above method.…”

“…Two-stage networks are regional suggestion methods which have a region regarding the proposal of interest and a separate region regarding the classification of the object, firstly generating candidate regions of interest, and then carrying on with the classification of extracted features. Typical two-stage networks include regions with convolutional neural networks (R-CNN) [21], fast R-CNN [22], faster R-CNN [23], region-based fully convolutional networks (R-FCN) [24], Mask R-CNN [25], and so on. In some public datasets, the detection accuracy of two-stage networks is slightly higher than that of one-stage networks; however, the detection speed of two-stage networks is far inferior to that of one-stage networks.…”

Insulators’ Identification and Missing Defect Detection in Aerial Images Based on Cascaded YOLO Models

“…First of all, the candidate regions are selected from the input image, and then the classification and regression are performed on the selected candidate regions. The representative algorithms of two-stage are faster regions with convolutional neural networks (faster R-CNN) [ 20 – 24 ], region-based fully convolutional networks (R-FCN) [ 25 ], mask R-CNN [ 26 ], and cascade R-CNN [ 27 – 29 ]. The application research of electrical equipment detection in transmission lines based on two-stage target detection algorithms is shown in Table 1 .…”

“…e representative algorithms of two-stage are faster regions with convolutional neural networks (faster R-CNN) [20][21][22][23][24], region-based fully convolutional networks (R-FCN) [25], mask R-CNN [26], and cascade R-CNN [27][28][29]. e application research of electrical equipment detection in transmission lines based on two-stage target detection algorithms is shown in Table 1.…”

Application of Data-Driven Iterative Learning Algorithm in Transmission Line Defect Detection

“…In recent years, deep learning methods produced an effective method for big data processing, and it has made a breakthrough in many different fields such as automatic speech recognition and target recognition [1][2][3][4][5]. At present, it has begun to promote the development of a new generation of artificial intelligence industry worldwide.…”