Intrusion object recognition and space distance measurement in safety area of high voltage transmission lines

Abstract

In this paper, the research work of image recognition is carried out in the face of the detection of illegal intrusion objects in power transmission lines. By analyzing the current intelligent monitoring and real-time prediction related technologies, Based on the image data of binocular camera, the method of identifying illegal foreign objects is mainly studied under the condition of constructing line space equation. The research on identification method proposes the use of continuous inter-frame difference method and background difference method to detect foreign object recognition, which can effectively overcome the problem of missed detection of static foreign objects, shadow misdetection and inability to locate foreign objects in the foreign object detection algorithm based on image difference. And using the point cloud to calculate the spatial distance, it can accurately obtain the distance from the invading foreign object to the line. And the feasibility of the verification method on site.