Target tracking method and system, storage medium and electronic terminal

Abstract

The present disclosure relates to the field of image processing, and in particular to a tracking method, a tracking system, a storage medium and an electronic terminal. The method includes: acquiring a current frame image; centering on the coordinates of the tracking target in the previous frame image on the current frame image, selecting candidate samples within a preset range; calculating the nearest neighbor similarity of each of the candidate samples degree, and select the candidate sample with the largest nearest neighbor similarity value as the candidate target; judge whether the candidate target is the tracking target according to the multiple frame images continuous with the current frame image; determine whether the candidate target is When the tracking target is used, the tracking is performed according to the coordinate information of the tracking target. The present disclosure can judge candidate samples in each frame of images to select candidate targets, and judge the candidate targets, so as to accurately acquire the tracking targets in each frame of images, and then realize long-term tracking of the tracking targets.

Description

technical field [0001] The present disclosure relates to the field of image processing, and in particular to a tracking method, a tracking system, a storage medium and an electronic terminal. Background technique [0002] In the infrared search and track system, it is an important research topic to track weak and small targets under the condition of low signal-to-noise ratio. Because the target is greatly affected by background noise and background clutter, and low-altitude targets are easily affected by ground objects, it brings great challenges to target tracking. [0003] Moreover, most of the existing target tracking methods can only track the target in a short period of time, and there are few studies on long-term stable tracking. However, in practical engineering applications, the long-term stable tracking of the target is more concerned. [0004] It should be noted that the information disclosed in the above background section is only for enhancing the understanding...

AI Technical Summary

Problems solved by technology

Because the target is greatly affected by background noise and background clutter, and low-altitude targets are easily affected by ground objects, it brings great challenges to target tracking

[0003] Moreover, most of the existing target tracking methods can only track the target in a short period of time, and there are few studies on long-term stable tracking.

Images