An Efficient Self-correcting Multi-target Tracking Method for Satellite Imagery

Abstract

The invention discloses an efficient satellite image self-correcting multi-target tracking method. The method comprises: inputting a satellite image, and preprocessing a video or an image sequence of the input satellite image; loading a video or an image sequence, and converting the image of each frame into a grayscale image; processing the video or image sequence by using a spatial filtering method; processing by using a multi-frame background motion estimation method to separate a foreground from a background; carrying out sub-pixel centroid positioning of a multi-space target in the foreground image; and realizing target matching tracking of front and rear frames by comprehensively utilizing cross-correlation information among multiple frames. According to the method, stable and effective tracking of the multi-space target is achieved, the calculation method of the centroid position is simplified according to the physical model characteristics of the space target, a forward tracking method and a backward tracking method which are mutually correlated among multiple frames are provided, self-correcting multi-target tracking is achieved, efficiency is high, and robustness is high.

Description

technical field [0001] The invention belongs to the field of digital image processing, and relates to an efficient satellite image self-correcting multi-target tracking method. Background technique [0002] The multi-space target tracking method refers to the method of positioning and tracking multiple targets in space based on the detection equipment of the artificial satellite on-orbit platform using image detection means combined with computer digital image processing technology. [0003] In the process of space target tracking, there are mainly the following technical difficulties: First, due to the long imaging distance of space targets, the space targets may not be within the accurate imaging plane range, and it is difficult to use high-speed and efficient methods to determine the position of space targets in the image. The coordinate position in . Second, due to the large change in the velocity of the space target, the existing methods have a high error rate, and it ...

AI Technical Summary

Problems solved by technology

[0003] In the process of space target tracking, there are mainly the following technical difficulties: First, due to the long imaging distance of space targets, the space targets may not be within the accurate imaging plane range, and it is difficult to determine the position of space targets in the image with high-speed and efficient methods. The coordinate position in

Second, due to the large change in the speed of the space target, the existing methods have a high error rate, and it is difficult to achieve stable tracking of the space target.

Fourth, the hardware conditions of spaceborne optical image detection equipment are limited, and it is impossible to realize real-time positioning and tracking of space targets

Fifth, since the detection equipment platform, the space target and the background are moving relative to each other at the same time, it is impossible to judge whether the moving target is a moving foreground or a deep space background

[0004] The main reason why the tracking method of space objects is difficult to run in real time is that the positioning and matching method of moving object points has a high time complexity, which requires a global traversal of multiple frames before and after. The information before and after is used to match the moving space target

Images