GPU-accelerated scene categorization under multiscale category-specific visual word strategy

Author

Chu, Wei-Ta ; Tseng, Sheng-Chung

Author_Institution

Nat. Chung Cheng Univ., Chiayi, Taiwan

fYear

2012

fDate

25-30 March 2012

Firstpage

885

Lastpage

888

Abstract

We utilize GPU to accelerate an essential component for computer vision and multimedia information retrieval, i.e. scene categorization. To construct bag of word models, we modify calculation of Euclidean distance so that feature clustering and visual word quantization can be processed in a parallel manner. We provide details of GPU implementations and conduct comprehensive experiments to verify the efficiency of GPU on multimedia analysis.

Keywords

computer vision; graphics processing units; information retrieval; multimedia computing; pattern clustering; Euclidean distance; GPU implementations; GPU-accelerated scene categorization; bag of word models; comprehensive experiments; computer vision; feature clustering; multimedia analysis; multimedia information retrieval; multiscale category-specific visual word strategy; visual word quantization; Feature extraction; Graphics processing unit; Indexes; Instruction sets; Vector quantization; Vectors; Visualization; GPU; multiscale category-specific visual words; scene categorization;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on

Conference_Location

Kyoto

ISSN

1520-6149

Print_ISBN

978-1-4673-0045-2

Electronic_ISBN

1520-6149

Type

conf

DOI

10.1109/ICASSP.2012.6288026

Filename

6288026