Mean Shift Tracking Algorithm Based on Tensor Gradient Histogram

The tracking performance of the Mean Shift algorithm based on color histogram declines rapidly when the object is similar to the background color,light changes.This paper develops a Mean Shift tracking algorithm based on tensor gradient histogram,which combines the three-dimensional space of gradient tensor RGB into a one-dimensional space,in the effective protection of the original vector direction.The experimental results show that,the developed method is less time-consuming and not sensitive to light and color changes.The algorithm here is more suitable for the tracking on the condition of confusion and occasions.