Real-time detection and tracking framework and tracking method based on compressed sensing feature selection

Abstract

The invention provides a real-time detection tracking frame and tracking method based on compressed sensing feature selection. According to the tracking frame and tracking method, compressed features can be selected, and only the sample characteristic with a high distinction degree is used for classification. Real-time tracking can be achieved through the frame and method, the tracking failure phenomenon caused by selection of wrong features is avoided, the influence of bad features on the tracking result is effectively restrained, the tracking speed is obviously increased, and the tracking precision is obviously improved.

Description

technical field [0001] The invention relates to the field of target tracking, in particular to a real-time detection and tracking framework and tracking method based on compressed sensing feature selection. Background technique [0002] It is well known that target tracking is an important field in computer vision technology, and has important applications in military, medical, monitoring and human-computer interaction. In recent years, many methods have been used to solve the problem of target tracking, but due to the deformation of the target, the change of illumination, and the occlusion of the target, target tracking is still a difficult point. [0003] The current mainstream real-time tracking methods are all adaptive. Generally, tracking methods can be divided into two categories: generative methods and discriminative methods. The generation method can learn the feature model of the target, and then search the area where the target may be located, and use the learned...

AI Technical Summary

Problems solved by technology

However, since the randomly mapped features may not be suitable for classification, this will lead to the use of poorly differentiated features for classification, which will have an adverse impact on the effect of target tracking.

Images