Distribution line pin defect detection method based on improved ALI and Faster-RCNN

Abstract

A distribution line pin defect detection method based on improved ALI and Faster-RCNN comprises the following steps: collecting pin defect images of a distribution line, manually marking the pin defect image data, and constructing a training sample set; building network structures, wherein the first network structure is an adversarial learning inference network, the basic structure of the first network structure is composed of an inference network, a generative network and a judger, and the second network structure is a Faster-RCNN network; carrying out detection model training according to the obtained training sample, and completing training after training for a specified number of steps; and inputting an image to be detected into the trained adversarial learning inference network, outputting a high-quality reconstructed pin image, and finally completing defect identification through the trained Faster-RCNN network. According to the method, detail information such as local textures and edges of the distribution line pin image can be enhanced to improve image quality, and accurate features are extracted in combination with a target detection algorithm to realize intelligent detection of pin defects.

Description

technical field [0001] The invention relates to the technical field of image recognition of distribution line equipment, in particular to a detection method for pin defects of distribution lines based on improved ALI and Faster-RCNN. Background technique [0002] With the increasing development of UAV technology, UAV inspection has gradually replaced manual inspection and has become the main power defect inspection method. The pins have the function of preventing the misalignment of the connecting parts in the line. In the relatively bad weather environment and mechanical vibration, the pins may fall off and other phenomena, which seriously affect the normal operation of the line. Due to the large number and small size of the pins, inspection personnel need to repeatedly confirm the pins in the drone inspection images, which not only brings a huge workload, but also has a high rate of false positives and misjudgments. In view of the existing problems, it is necessary to stu...

AI Technical Summary

Problems solved by technology

[0004] Although the above method can accurately identify the target object, there are still some deficiencies: after the image data is convoluted, the explicit information features of the image have rich semantic information, and the implicit information cannot be well represented, which makes some Pins are not easily recognized by the detection model, so the detection accuracy of pin defects using deep learning algorithms is low

Images