TARGET OBJECT TRACKING METHOD BASED ON COLOR-STRUCTURE FEATURES

摘要

The present invention provides a target object tracking method based on color-structure features aiming at the defects in the prior art that moving object tracking in video images has high complexity and low accuracy. The method includes: performing an object detection on video images, obtaining at least one object in the current frame image of the video, performing a super pixel segmentation on the object to determine the color feature and structure feature of the object; through comparing and matching on the color feature and structure feature with the objects to be tracked in a predetermined object model database, determining the object to be tracked in the current frame image and recording the location information of the target object in the current frame image; according to the color feature and structure feature of the target object in the current frame image, tracking the target object in the next frame image of the video and updating the location information of the target object. The present invention effectively enhances the accuracy and robustness of single-texture target tracking through a video tracking algorithm.