Presentation 2006-10-20
Simultaneous Recognition of Multiple Moving Objects Using Cubic Higher-Order Local Autocorrelation
Yasuyuki SHIMOHATA, Nobuyuki OTSU,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Moving objects recognition is an important problem in video surveillance applications, ITS(Intelligent Transport Systems), robot vision and so on. In this paper, we propose a method to recognize multiple moving objects simultaneously by using the Cubic Higher-Order Local Autocorrelation (CHLAC) and taking advantage of the idea that feature values can be expressed by linear coupling of each moving object's feature values because of the additivity of the CHLAC. In experiments, we apply this method to recognition of multiple pedestrian and counting the number of them to verify the effectiveness, and also we show that our method have a robustness to changes for object scale and speed.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) CHLAC (Cubic Higher-Order Local Autocorrelation) / additivity / multiple moving objects / simultaeous recognition / pedestrian counting
Paper # PRMU2006-104
Date of Issue

Conference Information
Committee PRMU
Conference Date 2006/10/13(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Simultaneous Recognition of Multiple Moving Objects Using Cubic Higher-Order Local Autocorrelation
Sub Title (in English)
Keyword(1) CHLAC (Cubic Higher-Order Local Autocorrelation)
Keyword(2) additivity
Keyword(3) multiple moving objects
Keyword(4) simultaeous recognition
Keyword(5) pedestrian counting
1st Author's Name Yasuyuki SHIMOHATA
1st Author's Affiliation Graduate School of Information Science and Technology, University of Tokyo()
2nd Author's Name Nobuyuki OTSU
2nd Author's Affiliation Graduate School of Information Science and Technology, University of Tokyo:National Institute of Advanced Industrial Science and Technology
Date 2006-10-20
Paper # PRMU2006-104
Volume (vol) vol.106
Number (no) 301
Page pp.pp.-
#Pages 6
Date of Issue