Image Correlation Based Tracking in Video Frames

Single or multi target tracking is one of the extensively studied areas in the field of computer vision. Object detection between successive frames a key step in tracking algorithm. This paper proposes a method which uses image correlation between two images for target detection in the consecutive frames. This Image tracking method focuses on a frequency domain based approach using two dimensional Fourier transforms for image correlation. It implements phase correlation which is subclass of correlation. It is based on the Fourier shift property of Fourier transform. This technique identifies the position of a template image within the larger picture. This approach allows accurate image placement and the subsequent path of the image through a video scene can be followed. The solution can be implemented to provide results to provide the path of the image tracked. Keywords—Object tracking, phase correlation, cross