Fast GPU-based space-time correlation for activity recognition in video sequences

Author

Rofouei, Mahsan ; Moazeni, Maryam ; Sarrafzadeh, Majid

Author_Institution

Univ. of California Los Angeles, Los Angeles, CA

fYear

2008

Firstpage

33

Lastpage

38

Abstract

Action recognition is becoming an important component of many computer vision applications such as video surveillance, video indexing and browsing. However most of the space time approaches to action recognition are very computationally expensive which prevents us from using them in real-time applications. This paper describes how Graphic Processing Units (GPUs) can be used in the field of action recognition to speed up this process. We implement a space-time behavior based correlation scheme on NVIDIA Quadro FX 5600 GPU and gain a 50x speedup over its counterpart CPU implementation.

Keywords

computer graphics; computer vision; image recognition; image sequences; video signal processing; NVIDIA Quadro FX 5600 GPU; activity recognition; computer vision; graphic processing units; space-time correlation; video browsing; video indexing; video sequences; video surveillance; Acceleration; Application software; Central Processing Unit; Computational modeling; Computer vision; Field programmable gate arrays; Graphics; Video compression; Video sequences; Video surveillance;

fLanguage

English

Publisher

ieee

Conference_Titel

Embedded Systems for Real-Time Multimedia, 2008. ESTImedia 2008. IEEE/ACM/IFIP Workshop on

Conference_Location

Atlanta, GA

Print_ISBN

978-1-4244-2612-6

Type

conf

DOI

10.1109/ESTMED.2008.4696991

Filename

4696991