Real-time visual object tracking method having shielding sensing mechanism

Abstract

The invention provides a real-time visual object tracking method having shielding sensing mechanism, tracking results based on filter tracking algorithm based on correlation and Bayesian probability model tracking algorithm based on color statistical information are fused, position prediction of a target is performed, one-dimensional scale pyramid is independently trained to perform target scale estimation, in addition, a shielding sensing mechanism is designed, the mechanism can judge whether a target is partly or completely shielded, then an update strategy of the model and which kind of model utilized to track new frame are determined, tracker drifting caused by pollution of background information is avoided, and according to the above steps, the tracking algorithm is used for tracking the target persistently and iteratively. The above algorithm can be used for accurately tracking the target in real time, and a plurality of problems including deformation, rotation, shielding, size variation, illumination variation, motion blur and the like can be effectively handled.

Description

technical field [0001] The invention belongs to the field of target tracking, in particular to a real-time visual target tracking method with an occlusion perception mechanism. Background technique [0002] With the development of computer technology, object tracking has become a research hotspot in the field of computer vision due to its high application value in video surveillance, human-computer interaction, robots, etc. The rectangular frame of the target of interest in one frame of image estimates the state (position and size) of the selected target in each next frame of image. In recent years, a large number of target tracking algorithms have been proposed, but due to occlusion, background clutter, illumination changes, and target scale and shape changes in practical applications, it is still difficult to design a robust, long-term, real-time target tracking algorithm. The problem. [0003] The existing tracking algorithm based on the correlation filter can achieve g...

AI Technical Summary

Problems solved by technology

In recent years, a large number of target tracking algorithms have been proposed, but due to occlusion, background clutter, illumination changes, and target scale and shape changes in practical applications, it is still difficult to design a robust, long-term, real-time target tracking algorithm. The problem

[0003] The existing tracking algorithm based on the correlation filter can achieve good results in both tracking accuracy and speed, but because it is a kind of method based on strict templates, this kind of method cannot deal with the sharpness of the target very well. deformation, hyperplane rotation, etc., and cannot adapt to the scale change of the target

The probability model algorithm based on color statistical information can make up for the shortcomings of the above-mentioned correlation filtering algorithm to a certain extent. Color stats are prone to drifting issues with the tracker

[0004] The main reason for the drift problem is that the online classifier introduces noise when it is updated, and the noise will continue to accumulate during the prediction process, which eventually makes the algorithm unable to accurately track the target

Images