Presentation 2014-03-06
Object Tracking in Crowded Scenes by Dependent Dirichlet Process Hidden Markov Model
Katsuya KONDO, Takuya OKAMOTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In crowded scenes where it is generally difficult to track moving objects, detection and tracking of objects are very challenging tasks. In this report, we detect objects by focusing on object's shape and intensity distribution. And we propose a method of individually tracking many objects in crowded scenes. This method applies Dependent Dirichlet Process Hidden Markov Model to the optical flows of moving objects. Each object is detected by calculating quadratic form of adaptive ring filter output and it is classified by a support vector machine. Also, movement line is obtained by tracking an object. Some experimental results show that the huge flows can be analyzed, and each object can be individually tracked in crowded scenes.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Hidden Markov Model / Flow Analysis / Object Tracking / Crowded Scenes
Paper # SIS2013-60
Date of Issue

Conference Information
Committee SIS
Conference Date 2014/2/27(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 Smart Info-Media Systems (SIS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Object Tracking in Crowded Scenes by Dependent Dirichlet Process Hidden Markov Model
Sub Title (in English)
Keyword(1) Hidden Markov Model
Keyword(2) Flow Analysis
Keyword(3) Object Tracking
Keyword(4) Crowded Scenes
1st Author's Name Katsuya KONDO
1st Author's Affiliation Dept. Information and Electronics, Graduate School of Eng. Tottori University()
2nd Author's Name Takuya OKAMOTO
2nd Author's Affiliation Dept. Information and Electronics, Graduate School of Eng. Tottori University
Date 2014-03-06
Paper # SIS2013-60
Volume (vol) vol.113
Number (no) 467
Page pp.pp.-
#Pages 4
Date of Issue