Extracting Motion Features of Objects Based on Full Pixel Matching

Author

Aota, Hisato ; Yaguchi, Yuichi ; Iseki, Kenta ; Oka, Ryuichi

Author_Institution

Image Process. Lab., Univ. of Aizu, Aizu-Wakamatsu, Japan

Volume

2

fYear

2009

fDate

11-14 Oct. 2009

Firstpage

300

Lastpage

305

Abstract

This paper proposes an approach to extract motion features from sequences of images of human behavior.A novel algorithm called two-dimensional continuous dynamic programming (2DCDP) is proposed, which can obtain a set of correspondence data for all pixels between sequential images.The 2DCDP algorithm performs segmentation-free detection of objects in an input image from representations in reference image. The output of the 2DCDP algorithm describes a complete vector field that indicates detailed motion of objects.Experiments were performed to show the precision of he motion features extraction.

Keywords

dynamic programming; feature extraction; image motion analysis; image segmentation; image sequences; full pixel matching; human behavior; images sequences; object motion features extraction; segmentation-free detection; sequential images; two-dimensional continuous dynamic programming; vector field; Data mining; Dynamic programming; Feature extraction; Humans; Image motion analysis; Image processing; Image segmentation; Information technology; Motion analysis; Pixel; Image Processing; Motion Recognition.;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer and Information Technology, 2009. CIT '09. Ninth IEEE International Conference on

Conference_Location

Xiamen

Print_ISBN

978-0-7695-3836-5

Type

conf

DOI

10.1109/CIT.2009.37

Filename

5329077