Real time CAMSHIFT tracking algorithm using TMS320DM6437 EVM

Abstract

Object tracking in real time is one of the most important topics in the field of computer Vision. The work undertaken in this dissertation is mainly focused on development of a reliable and robust real time tracking system that can track the object of interest in the video acquired from a stationary or moving camera. The proposed algorithm is a real time algorithm that operates in 25 frames per second depending on the input video properties and probability distribution of the intensity of the tracked object. The Digital Video Development Platform DM6437 EVM is used to obtain the real time video sequence and process the frame to extract the object using the CAMSHIFT algorithm. The information obtained from the frame is extracted and mean shift algorithm is used to search the object with in the frame. The experimental results obtained from the proposal prove the consistency and real time performance of the proposed algorithm.