Enhanced Object Tracking using Davinci Processors
J. Navin Sankar1, S. Mary Joans2, S. J. Grace Shoba3, A. Arun4
1Navin Sankar J, PG Student/Applied Electronics, Velammal Engineering College, Chennai, India.
2Prof. S. Mary Joans, HOD, Electronics and Communication Department, Velammal Engineering College, Chennai, India.
3Mrs. S. J. Grace Shoba, Professor, Electronics and Communication Department, Velammal Engineering College, Chennai, India.
4Mr. A. Arun, Assistant.Proffessor.-II, Electronics and Communication Department, Velammal Engineering College, Chennai, India.
Manuscript received on February 05, 2013. | Revised Manuscript received on February 27, 2013. | Manuscript published on March 05, 2013. | PP: 112-115 | Volume-3 Issue-1, March 2013. | Retrieval Number: A1309033113/2013©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Modular tracking methodologies have shown the promises of great versatility and robustness. In a similar way, the proposed paper, Enhanced Object Tracking Using Davinci Processors, will also possess major challenge for emerging computer vision technology. The Continuously Adaptive Mean Shift [CAMSHIFT] Algorithm used here is based on the Mean Shift Algorithm for object tracking for a perceptual user interface. The main aim of this proposal is to determine the effectiveness of the CAMSHIFT Algorithm as a general purpose object tracking approach in the case where a small portion of image is assumed as region of interest. Then the object within the corresponding region of interest is tracked using CAMSHIFT algorithm. The algorithm performs well mainly on moving objects in video sequences and it is robust to changes in shape of the moving object. The Digital Video Development Platform [DM6437 EVM] is used to obtain the video from the camera and will use the Ethernet media access control address and video processing back end drivers for the real time transmission of the video captured. The video is received and processed at DM6446, where the CAMSHIFT algorithm is implemented and the video object tracking takes place. The experimental results obtained from the proposal proves the consistency and efficiency of the proposed algorithm.
Keywords: CAMSHIFT, CCS, DM6437, DM6446, LINUX, Ubuntu.