Semantic segmentation-based aerial photography transmission line broken strand identification method and system

Abstract

The invention discloses an aerial photography power transmission line broken strand identification method and device based on semantic segmentation. The method comprises the steps: acquiring aerial photography power transmission line sample images to form a sample library; constructing a semantic segmentation convolutional neural network model, and training the constructed semantic segmentation convolutional neural network model by using the aerial power transmission line sample image; using the trained semantic segmentation convolutional neural network model to detect an aerial power transmission line image to be detected, and outputting a segmentation mask graph of a detected normal conductor and a suspected broken strand; and judging whether a detection result is correct or not by utilizing a spatial context relationship between the normal wire and the broken strand according to the segmented mask pattern. According to the invention, the accuracy and the detection efficiency are improved, manual detection is avoided, and manpower and material resources are saved.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a semantic segmentation-based method and system for identifying scattered and broken strands of an aerial transmission line. Background technique [0002] In actual daily work, in order to grasp the operation status of the line and eliminate potential hidden dangers of the line in time, my country's power system spends huge manpower, material resources and financial resources on inspections every year. The traditional inspection management method can no longer meet the requirements of line management. Manual line inspection is not only labor-intensive, but also time-consuming and inefficient. Some line sections are restricted by terrain factors and even cannot be inspected. The inspection mode has been difficult to meet the requirements of reliable and efficient lean management. Therefore, it is of great significance to study how to use a new, intelligent and ef...

AI Technical Summary

Problems solved by technology

This operation needs to retrieve the materials in the database for each detection. Not only is the operation repeated, but also there are a lot of errors in the detection results. Most of them need to be identified and detected by manpower in the later stage, which consumes resources and reduces efficiency.

Images