Tracing method for video movement objective self-adapting window

Abstract

The invention discloses a tracking method of a video frequency moving object target self-adapting window, relating to machine vision and pattern recognition technique. A frame image of a video frequency sequence is read into a postpositional memory zone, and staring position and size information of a tracked object is obtained in the frame, then distribution statistical information of a target signature is extracted to build a gauss mixed model as an object template, a mean vector and a covariance matrix in gauss mixed distribution are used to describe the position and the size of the object, then the next frame image of the video frequency sequence is read into the postpositional memory zone. In a new frame video frequency image, a parameter estimation method is used to obtain object gauss mized model parameters in the current frame in iterative computation and find candidate template similar to the object template, and the final model parameters obtained in iteration are used to update the tracking window for realizing self-adaption of the tracked window. According to the tracking method of the video frequency moving object target self-adapting window, tracking reliability is greatly increased, which is widely applied in the fields of robot technology, vision navigation, automatic supervision, traffic control and the like.

Description

technical field [0001] The invention relates to machine vision and pattern recognition technology, in particular to a tracking method of video moving target adaptive window. Background technique [0002] In the application of automatic monitoring, traffic management, visual navigation, robotics and many other fields, video moving target tracking is one of the hot issues in the field of machine vision and pattern recognition. The problem of how to represent the continuous correspondence of object regions in each frame of a video sequence while in motion. But this problem can be solved by transforming it into a problem of matching object regions in successive frames. [0003] Among the existing matching tracking methods, there is a method called the mean-shift method, which refers to using the histogram weighted by the kernel function to describe the image target, and using the similarity function to measure the initial frame target model The similarity with the current fram...

AI Technical Summary

Problems solved by technology

[0004] However, a defect of the mean shift method is that the window width of the kernel function cannot change with the size of the target, so that when the size of the target changes greatly in the image, the target tracking window cannot accurately describe the target size and position, thus lead to tracking errors, often resulting in the loss of tracking targets

[0005] The improved algorithm and technology of the self-adaptive tracking window have been disclosed in the application document with the publication number CN1619593A, but it is only applicable to video sequences synthesized by color or multi-image sensors. The genetic algorithm adopted is used for complex similarity calculations, and the calculation cost is large, which is not conducive to realizing the real-time tracking of the target; the improved algorithm of the adaptive tracking window of the mean shift method is also disclosed in the application document with the publication number CN1794264A. The tracking method used in the patent is an inaccurate description of the window width of the tracked target. When the target size changes in the video sequence, this tracking method cannot accurately estimate the target size. As the tracking continues, it is easy to cause tracking fail

Images