Target object tracking method based on color-structure features

Abstract

The invention provides a target object tracking method based on color-structure features. The method includes the steps that object detection is conducted on video images, and at least one object in the current image is acquired; super-pixel segmentation is conducted on the object according to pixel color information; according to super-pixels meeting preset conditions in the object, the color feature and the structure feature of the object are determined; the color feature and the structure feature of the object are compared and matched with the color structure and the structure color of an object to be tracked in an object model database, a target object to be tracked in the image is determined, and the position information of the target object in the current image of a video is recorded; in a next image of the video, the steps are repeated, the color structure and the structure feature of a target object are compared and matched with the color feature and the structure feature of the target object in the former image of the video, the target object to be tracked in the image is determined, and the position information of the target object is updated. By means of the method, the accuracy and the robustness of single-texture target tracking through a video tracking algorithm are effectively enhanced.

Description

technical field [0001] The invention relates to the technical fields of pattern recognition and computer vision, in particular to a method for tracking a target object based on color-structure features. Background technique [0002] Augmented reality (Augmented Reality, AR) technology can seamlessly integrate objects and information between the real world and the computer-generated virtual world. The information acquisition experience enhances people's understanding and perception of the real world. [0003] Video-based augmented reality technology has developed rapidly in recent years due to its low application cost and its universal application in various environmental scenarios. How to accurately track objects in the real world is one of the keys to realize the combination of virtual and real in augmented reality technology. As the basis for the realization of augmented reality technology, target tracking technology based on video images is currently widely used in secu...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to provide a target object tracking method based on color-structural features in view of the defects of high complexity and low accuracy in tracking moving objects in video images in the prior art. Combined with the recognition of the target object in the video image, by comparing and matching with the preset model database, the target object is determined and tracked, and the accuracy, real-time and robustness of the target tracking system based on the video image are improved.

Images