Behaviour Analysis and Prediction in Image Sequences Using Rough Sets

Author

Herrera, A. ; Beck, A. ; Bell, D. ; Miller, P. ; Wu, Q. ; Yan, W.

Author_Institution

Sch. of Electron. & Electr. Eng. & Comput. Sci., Queen´´s Univ. Belfast, Belfast

fYear

2008

fDate

3-5 Sept. 2008

Firstpage

71

Lastpage

76

Abstract

In this paper, a rough set based data mining technique is extended and applied to learn behaviour patterns of moving objects in videos. An intelligent image analysis system is proposed to discover knowledge from video collections. The system is applied to synthetic image sequences containing motions of a predator and prey behaving according to a set of rules. The results show that the system is able to discover the rules governing the predator behaviour and is also able to predict the predator´s final decision using the rules discovered.

Keywords

data mining; image motion analysis; image sequences; learning (artificial intelligence); rough set theory; video signal processing; behaviour analysis; behaviour prediction; data mining; intelligent image analysis system; knowledge discovery; moving object behaviour pattern; rough set; synthetic image sequence; video collection; Hidden Markov models; Image analysis; Image sequence analysis; Image sequences; Object detection; Rough sets; Telecommunication traffic; Traffic control; Vehicle dynamics; Videos;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Vision and Image Processing Conference, 2008. IMVIP '08. International

Conference_Location

Portrush

Print_ISBN

978-0-7695-3332-2

Type

conf

DOI

10.1109/IMVIP.2008.24

Filename

4624387