An improved algorithmofmedian flow for visual object tracking and its implementation on TI OMAP

Author

Varfolomieiev, A. ; Lysenko, O.

Author_Institution

Kyiv Polytech. Inst., Nat. Tech. Univ. of Ukraine, Kiev, Ukraine

fYear

2012

fDate

13-14 Sept. 2012

Firstpage

261

Lastpage

265

Abstract

An improved algorithm of median flow used for visual object tracking is described. The improvement consists in adaptive selection of aperture window size and number of pyramid levels at optical flow estimation. It can increase the tracking efficiency as compared to the basic algorithm, especially when dealing with small objects. The proposed version of the algorithm has been realized with the aid of OpenCV library and tested on OMAP35x EVM and BeagleBoard-xM based on Texas Instruments OMAP3530 and DM3730 processors respectively. Analysis of improved median flow was performed over actual video sequences. The results obtained show versatility and computational robustness of the algorithm, which makes it promising for embedded application based on ARM processors.

Keywords

image sequences; object tracking; video signal processing; ARM processors; BeagleBoard-xM; OMAP35x EVM; OpenCV library; TI OMAP; aperture window size; embedded application; median flow; optical flow estimation; pyramid levels; video sequences; visual object tracking;

fLanguage

English

Publisher

ieee

Conference_Titel

Education and Research Conference (EDERC), 2012 5th European DSP

Conference_Location

Amsterdam

Print_ISBN

978-1-4673-4595-8

Electronic_ISBN

978-1-4673-4595-8

Type

conf

DOI

10.1109/EDERC.2012.6532268

Filename

6532268