A Rechecking Method for Tracking Loss of Weak and Small Targets Based on Multi-peak Judgment

Abstract

The invention discloses a weak target tracking loss re-examination method based on multi-peak determination. When the tracked target is lost, the target re-examination search field is selected in the image to be detected; the gray Gaussian distribution of the frame image before the tracking target is lost is calculated. Feature F, in the search domain, analyze the frequency domain response value of the gray-level Gaussian distribution feature F to obtain a frequency domain response map, which is defined by the size of the tracking target, and sequentially extract 4-7 regions containing local peaks in the frequency domain response map And record the peak information of these areas; replace the tracking target image information in the lost previous frame image to the center position of the search domain, and calculate the response value of the gray Gaussian distribution feature F of the tracking target and the center position of the replaced search domain δ; compare the difference between the above 4-7 peak information and δ, find the peak position with the smallest difference and a difference ratio less than 20% as the position information of the tracking target reexamination, the present invention can quickly and effectively track the lost tracking target Determine location information.

Description

technical field [0001] The invention belongs to the technical field of target detection and tracking, and in particular relates to a rechecking method for weak and small target tracking loss based on multi-peak determination. Background technique [0002] Target tracking is the process of determining the target position information in continuous frame images, and it is an important content in computer vision research. According to the relationship between the camera and the moving target, target detection can be divided into target detection under static background and dynamic background. For the detection of moving objects when the background is not moving, there are mainly background subtraction method, frame difference method and optical flow method. For the target detection of background motion, the global motion parameters between adjacent frames of the video image are often obtained through the global motion compensation method, and the current image is matched with t...

AI Technical Summary

Problems solved by technology

[0003] During the target tracking process, background clutter, light and dark changes, partial or complete occlusion, target attitude changes, and rapid target movement in the video image will all lead to the failure of continuous target tracking.

Images