Robust Object Tracking Based on Modified Mean-Shift Algorithm

Abstract

In this article, aiming at the flaws in traditional Mean-shift algorithm for object tracking, we improve the traditional algorithm based on the fusion of Grayscale and Gradient using a layered approach. This algorithm can describe the object more exactly by using Grayscale and Gradient dual tracking factors in object tracking; And it makes up the flaws in traditional Mean-shift algorithm for information expression of spatial location by using layered approach and spatial histogram in describing object. Experimental results show that modified Mean-shift algorithm is superior to traditional Mean-shift algorithm in object tracking with better Robustness and precision, and it can suit deformation, spin, interference, shield and more complex tracking problems.