DocumentCode :
692057
Title :
Dynamic Texture Classification Based on Motion Statistical Feature Matrix
Author :
Yulong Qiao ; Ying Zhao ; Xianrui Song
Author_Institution :
Sch. of Inf. & Commun. Eng., Univ. of Harbin Eng. Univ., Harbin, China
fYear :
2013
fDate :
16-18 Oct. 2013
Firstpage :
535
Lastpage :
538
Abstract :
Dynamic texture is an extension of texture to the spatio-temporal domain. The motion property is one of the most important characteristics in dynamic texture analysis. This paper proposes a dynamic texture classification method based on the block-based motion estimation method and the statistical feature matrix. The method makes use of the block-based motion estimation method to estimate the motion vector of the dynamic texture, and constructs the statistical feature matrix by computing the complex covariance and dissimilarity of the motion vectors, which is used to describe the dynamic texture. The classification method is evaluated on two benchmark dynamic texture databases. The experimental results demonstrate the effectiveness of the introduced method.
Keywords :
covariance analysis; feature extraction; image classification; image texture; motion estimation; block-based motion estimation method; complex covariance; dynamic texture analysis; dynamic texture classification method; motion property; motion statistical feature matrix; motion vector dissimilarity; motion vector estimation; spatio-temporal domain; Dynamics; Feature extraction; Heuristic algorithms; Motion estimation; Support vector machine classification; Vectors; Videos; Dynamic texture classification; Motion estimation; Pattern recognition; Statistical feature matrix;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Information Hiding and Multimedia Signal Processing, 2013 Ninth International Conference on
Conference_Location :
Beijing
Type :
conf
DOI :
10.1109/IIH-MSP.2013.138
Filename :
6846694
Link To Document :
بازگشت