Color Object Tracking

A color object tracking method based on the object and background colors.

This code is a matlab implementation of a color object tracking method based on the object and background colors.
The code runs on Windows/Linux with MATLAB R2011-2013.
A test sequence "test.avi" is included so you can simply run Demo.m
Object center locations are saved in output.mat
----------------------------------------------------------------------
This code presents an object tracking method based on the object and background colors. A three dimensional feature vector is used to describe color feature (R, G, B) of each pixel. A quantized histogram of that feature value of pixels on the selected object and a quantized histogram of pixels from the neighborhood surrounding the object are developed. The RGB based joint probability density function of the selected object region and that of a neighborhood surrounding the object are used to separate object from background. An adaptive color model of separated object is developed to detect the object in subsequent frames while simple Mean-shift procedure on binary images is used to track the object (it is actually a simple centroid shift on the binary map of object detection result).
----------------------------------------------------------------------
This code is used in the following paper: Alireza Asvadi, MohammadReza Karami and Yasser Baleghi, "Object Tracking Using Adaptive Object Color Modeling" in Proceedings of the 4th conference on information and knowledge technology (IKT2012), Babol, Iran, May 2012.