Recognition of Periodic Motions Using One-Dimensional Contour Based Features

Author

Ghaderian, Meraj ; Behrad, Alireza ; Kaboodi, Samere Abbasi Dine

Author_Institution

Fac. of Eng., Shahed Univ., Tehran, Iran

fYear

2011

fDate

16-17 Nov. 2011

Firstpage

1

Lastpage

5

Abstract

In this article, a new method for detecting periodic motions in image sequences based on one-dimensional features is presented. The method starts by the detection of moving object in the consecutive frames. Then the contours of the moving target are extracted and one-dimensional features are constituted. The features are based on the calculated distance from target contour to its bounding box sides in four directions. By applying the autocorrelation to the calculated distances, four one-dimensional curves are obtained and the periodicity of the target motion is evaluated. The proposed algorithm was tested with a database of 100 videos and experimental results showed the efficiency of the proposed algorithm.

Keywords

correlation methods; feature extraction; image recognition; image sequences; object detection; autocorrelation; bounding box sides; image sequences; moving target extraction; one-dimensional contour based features; one-dimensional curves; periodic motion detection; periodic motion recognition; target contour; Algorithm design and analysis; Classification algorithms; Correlation; Databases; Feature extraction; Humans; Videos;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Vision and Image Processing (MVIP), 2011 7th Iranian

Conference_Location

Tehran

Print_ISBN

978-1-4577-1533-4

Type

conf

DOI

10.1109/IranianMVIP.2011.6121615

Filename

6121615