A method and system for tracking deformable objects based on saliency

Abstract

The invention discloses a deformable object tracking algorithm based on visual saliency and its system. The method includes the following steps: S1: Manually calibrate the target area; S2: Obtain the local saliency including the foreground target through the image segmentation algorithm based on visual saliency S3: Segment the foreground area; S4: Establish the target foreground model; S5: Initialize the foreground model through the color histogram tracker based on color features; S6: Obtain candidate targets and It makes a judgment; S7: obtain the final position of the target; S8: learn and update the target. While performing saliency processing, the present invention also considers the calculation efficiency of the algorithm, and automatically segments the foreground information through the method of the local size window, establishes a softening model through the foreground information matrix, and generates a color histogram corresponding to the model, and performs the histogram Graph matching increases the judgment ability of the tracker, and at the same time continuously learns a new model of the target through the learner.

Description

technical field [0001] The invention relates to a saliency-based deformation object tracking method and system thereof. Background technique [0002] In recent years, with the rapid development of machine learning and pattern recognition related fields, the development of computer vision technology has been greatly promoted, and a large number of engineering practice and algorithm papers have sprung up like mushrooms. CVPR, ECCV, and ICC, the core journals in the field of computer vision, have a large number of highly innovative and influential excellent papers. Among them, online learning, as a machine learning method, has been more and more introduced into the field of computer vision, and a series of online learning targets can be developed, and the template model can be continuously updated, so as to achieve faster and more robust Algorithmic technology for tracking. [0003] Computer Vision The target tracking problem of computer vision based on online learning can be...

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to overcome the deficiencies of the prior art, provide a method and system for tracking deformed objects based on saliency, and solve the problem of using rigid templates to model targets in the prior art, which often deforms and has irregular appearance Objects are modeled by applying a rectangular frame template with a mismatched shape, which will inevitably lead to wrong learning of background pixels, making it very easy to be disturbed by background changes during the tracking process. If the target itself is also deformed at the same time, it is very easy Issues causing tracking to fail

Images