Adaptive Compressive Tracking Algorithm Based on SIFT Features

Abstract

In order to solve the compressive tracking algorithm cannot solve the change of scale and rotation in object tracking, an adaptive compressive tracking algorithm based on SIFT features is proposed. Firstly, we using SIFT feature extracted the scale-space extremes points of the object model and the tracking frame, Then the scale and rotation angle of the object being tracked were calculated by using the scale and angle information which was provided by the feature points correctly matched between model and the frame, we calculate the main-orientation information of the object and the scale of object according those refined scale-space extremes point, then using compressive sense tracking algorithm to locate the tracking object according the scale and orientation. This algorithm can tracking the object adaptively the change of direction and scale. Experimental results show that the proposed algorithm has good tracking effect when the scale or the angle of the object changes.