Image tracking method and device

Abstract

The invention discloses an image tracking method and device, and the method includes: an image tracking method. The tracking method includes: determining a plurality of original areas corresponding to different target images in the video; expanding the boundaries of the original areas in the video according to a predetermined ratio to obtain a plurality of target areas, so that the multiple target areas are located The range of the image is greater than the range of the image where the multiple original areas are located; the multiple target areas are scaled to a predetermined size to obtain multiple predetermined target areas. The present invention expands the window of the original tracking object by a certain proportion, and then scales it to a fixed size, thereby greatly reducing the number of detection and search windows, and aiming at the commonality of similar multiple targets, all target images share the same Learners, online models and detectors to improve the tracking efficiency of target images.

Description

technical field [0001] The present invention relates to the field of image tracking, in particular to an image tracking method and device. Background technique [0002] Existing image tracking methods are mainly based on image processing algorithms (such as TLD algorithm) to realize the real-time tracking of images, while the image tracking method based on TLD algorithm needs a long time when tracking a single target image. In the existing image processing system, it is generally necessary to track the states of multiple target objects (target images) in the video, so for the existing TLD-based image tracking method when tracking multiple target images, then as figure 1 As shown, it is necessary to set up corresponding detectors, learners, and online models for each tracking object (ie, target image) to realize tracking of multiple target images, and this method takes a long time when tracking one target image , if this method is applied to track multiple target images in t...

AI Technical Summary

Problems solved by technology

[0002] Existing image tracking methods are mainly based on image processing algorithms (such as TLD algorithm) to realize the real-time tracking of images, while the image tracking method based on TLD algorithm needs a long time when tracking a single target image. In the existing image processing system, it is generally necessary to track the states of multiple target objects (target images) in the video, so for the existing TLD-based image tracking method when tracking multiple target images, then as figure 1 As shown, it is necessary to set up corresponding detectors, learners, and online models for each tracking object (ie, target image) to realize tracking of multiple target images, and this method takes a long time when tracking one target image , if this method is applied to track multiple target images in the video, it will obviously reduce the efficiency of image tracking, which is not conducive to subsequent image processing

[0003] For the above-mentioned problems in related technologies, no effective solution has been proposed yet

Images