Flying target detection method and system based on image processing

Abstract

The invention discloses a method and system for detecting a flying target based on image processing, which uses a local threshold segmentation method to obtain the foreground area of ​​an image, and analyzes the foreground area as a suspected target area, and classifies the foreground area according to the size of the foreground area. In the area, the target analysis and judgment of the three situations of clear target structure, blurred structure but clear position information, and image noise are carried out. When the target structure in the foreground area is judged to be clear, the image with clear target structure is used as the input of the trained classifier, and the output is obtained. Relevant information of the target; when it is judged that the target structure in the foreground area is blurred but the position information is clear, obtain images with equal time intervals before and after the current image, calculate the centroid coordinates of the three frames of images, and judge according to the vector relationship of the three centroid coordinates Whether the current image is a flying target; when judging the image noise in the foreground area, then directly give up further judgment on the image.

Description

technical field [0001] The invention relates to the technical field of unmanned aerial vehicle detection, in particular to a method and system for detecting a flying target based on image processing. Background technique [0002] Flying target detection methods are of great significance both in military and civil affairs. Traditional flying target detection is mainly realized by radar, but radar detection has disadvantages such as blind spots and susceptibility to interference. With the rapid development of unmanned aerial vehicle technology, various new types of aerial vehicles emerge in an endless stream, especially the unmanned aerial vehicles that have emerged in recent years, which have the characteristics of low flying altitude, slow flying speed, and small flying volume. The characteristics bring certain difficulties to the detection of UAVs. Due to the influence of ground radar clutter, it is difficult for traditional radars to identify such small targets. [0003]...

AI Technical Summary

Problems solved by technology

Traditional flying target detection is mainly realized by radar, but radar detection has shortcomings such as blind spots and susceptibility to interference

With the rapid development of unmanned aerial vehicle technology, various new types of aerial vehicles emerge in an endless stream, especially the unmanned aerial vehicles that have emerged in recent years, which have the characteristics of low flying altitude, slow flying speed, and small flying volume. The characteristics bring certain difficulties to the detection of UAVs. Due to the influence of ground radar clutter, it is difficult for traditional radars to identify such small targets.

Images