Mean Shift tracking method for resisting similar color and illumination variation interference

Abstract

The invention discloses a Mean Shift tracking method for resisting similar color and illumination variation interference. Starting with an object representing method, relations between an object pixel value and eight neighborhood pixel gray level values are fully used for expanding a local significance operator LSN, and a local significance texture operator-local ternary number is provided so that the distinguishing capacity of the object representing method in the similar color background can be improved. In order to further improve the distinguishing capacity of texture characteristics, an object mask is generated through extraction of key pixel points on edges, lines and angular points, and then LTN characteristics of the object pixel in the mask are combined with chrominance information less affected by illumination variation, so that a new object model is obtained to improve the capacity for resisting the similar color and the illumination variation. Finally, the object model is embedded into a Mean Shift tracking frame, and the task of tracking an object can still be finished continuously and stably under the condition that the similar background color and illumination variation interference exist in the scene.

Description

technical field [0001] The invention belongs to the technical field of computer vision, in particular to a Mean Shift tracking method that resists interference from similar colors and illumination changes. Background technique [0002] Target tracking refers to the positioning of the target in the next frame of the sequence based on parameters such as the position of the region of interest in the current frame of the video sequence. It is an important link in the field of computer vision. It has a wide range of applications in military and civilian fields. In realistic tracking scenarios, the background color may be similar to the target to be tracked and affect the accuracy of tracking, and the overall change of illumination will also interfere with the stability of tracking. Continuous and accurate target tracking has become a research hotspot in the field of computer vision in recent years. difficulty. [0003] At present, in the field of target tracking, the nuclear tr...

AI Technical Summary

Problems solved by technology

The disadvantage of the color-saliency target model extracted by Tavakoli et al. is that each saliency level of the LSN operator may contain a variety of different local texture structures and cannot distinguish these different local texture structures. Distinguish targets in similar scenes, and the RGB color model is greatly affected by changes in light intensity, which affects the tracking stability of the algorithm under light changes such as outdoors

Images