A scale adaptive Kalman filter method based on quaternion correlation in object tracking

Abstract

We proposed a scale adaptive Kalman filter algorithm based on quaternion correlation of color image. Kalman filter is used to predict the object motion direction and define the searching window. In the searching window, the correlation of object and the image is calculated to get the accurate position of the object. Scale adaptive method is efficient to the situation of object size changing. Experiments results showed that the algorithm can detect the object correctly even the size of the object changed.