Implementation of observation dependent visual object tracking using C++

Abstract

Object tracking, an important task within the field of computer vision, is the problem of estimating the position and other relevant information of moving objects in image sequences. It is widely used in smart vision systems such as visual surveillance, visual navigation, human-computer interaction and video compression.

Several kinds of object tracking algorithms have been implemented, most of which, however, are only adoptable for some specific target and environment.

This project is about the implementation of visual object tracking algorithm based on the dependent Hidden Markov Model (ODHMM) framework where Structure Complexity Coefficient (SCC) models the observation dependency between consecutive frames.

The main scope for this project is to convert the algorithm to the platform based on C++ from the MATLAB program, and the libraries such as OpenCV and Eigen are used in the project.