Human behavior recognition based on fractal conditional random field

Author

Zhuowen Lv ; Kejun Wang

Author_Institution

Coll. of Autom., Harbin Eng. Univ., Harbin, China

fYear

2013

fDate

25-27 May 2013

Firstpage

1506

Lastpage

1510

Abstract

In order to meet the demand of visual behavior recognition, we introduce Fractal Conditional Random Field (FCRF) model. FCRF model has improved Latent-Dynamic Conditional Random Field (LDCRF), and proposed the concept of fractal labels that define the integrity and directionality of human behavior. FCRF model overcomes real-time issues of the Hidden Conditional Random Field (HCRF) and the problem of label bias when the behavior transform. The experimental results show that the algorithm proposed in this paper has better recognition performance than Conditional Random Field (CRF), HCRF and LDCRF.

Keywords

fractals; gesture recognition; statistical analysis; FCRF model; HCRF; LDCRF; fractal conditional random field model; fractal labels; hidden conditional random field; human behavior directionality; human behavior integrity; human behavior recognition; label bias problem; latent-dynamic conditional random field; visual behavior recognition; Adaptation models; Fractals; Hidden Markov models; Mathematical model; Testing; Training; Video sequences; CRF; FCRF; HCRF; LDCRF; behavior recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Control and Decision Conference (CCDC), 2013 25th Chinese

Conference_Location

Guiyang

Print_ISBN

978-1-4673-5533-9

Type

conf

DOI

10.1109/CCDC.2013.6561166

Filename

6561166