Title :
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
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;
Conference_Titel :
Machine Vision and Image Processing Conference, 2008. IMVIP '08. International
Conference_Location :
Portrush
Print_ISBN :
978-0-7695-3332-2
DOI :
10.1109/IMVIP.2008.24
