Aerial photographed video target tracking method based on related filtering and significance testing

Abstract

The invention relates to an aerial photographed video target tracking method based on related filtering and significance testing. Through the tracking method based on related filtering and significance testing, a direction gradient histogram characteristic and a gray-scale characteristic are utilized for realizing high robustness of a tracking result to factors such as illumination change, noise and shield. Particularly when a target is severely shielded and tracking failure occurs, the aerial photographed video target tracking method realizes target detection through a redetection mechanism, so that long-time continuous tracking of the target can be realized. Furthermore, a significance detecting method based on a residual spectrum theory realizes simple and quick calculation. Redetection to the target can be realized through a relatively low calculation cost. A requirement for real-time performance of an algorithm in aerial photographing video tracking can be effectively satisfied.

Description

technical field [0001] The invention relates to an aerial video target tracking method based on correlation filtering and saliency detection Background technique [0002] At present, aerial video tracking technology has been widely used in military and civil fields. Compared with videos shot by fixed platforms or handheld devices, aerial videos have their own unique properties. First of all, the camera moves at high speed with the UAV, and there are transformations such as translation and rotation between the images of the aerial video sequence, and the scenes in the video are complex and changeable, and the target is easily disturbed by occlusion and noise; in addition, because the UAV sometimes Flying at a high altitude of thousands of meters or even tens of thousands of meters, the proportion of moving objects in the image is very small, which brings great challenges to aerial video processing. In recent years, a large number of tracking methods based on correlation fil...

AI Technical Summary

Problems solved by technology

[0004] In order to avoid the deficiencies of the prior art, the present invention proposes an aerial video object tracking method based on correlation filtering and saliency detection, which solves the problem of the drift of the appearance model caused by the severe occlusion of the moving object in the aerial video, which easily leads to tracking failure. The problem

Images