Presentation 2014-03-06
Particle Filter based on Observation Model with Adaptive Local Features and its Application to Human Tracking
Sangeun LEE, Keiichi HORIO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, adaptation algorithm for reliable appearance model (RAM), which is a observation model in particle filter for object tracking, is proposed. RAM is a set of features constructed of color and shape information in local areas randomly selected in an image. RAM exhibits robust tracing even when changes of occlusion or illumination condition occur in video scene. However, RAM is not useful for shape change of an object. In this report, adaptation algorithm, in which inadequate local features are automatically extracted and are updated to adequate ones, are discussed.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) object tracking / particle filter / reliable appearance model / adaptation algorithm
Paper # SIS2013-59
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) Particle Filter based on Observation Model with Adaptive Local Features and its Application to Human Tracking
Sub Title (in English)
Keyword(1) object tracking
Keyword(2) particle filter
Keyword(3) reliable appearance model
Keyword(4) adaptation algorithm
1st Author's Name Sangeun LEE
1st Author's Affiliation Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology()
2nd Author's Name Keiichi HORIO
2nd Author's Affiliation Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology
Date 2014-03-06
Paper # SIS2013-59
Volume (vol) vol.113
Number (no) 467
Page pp.pp.-
#Pages 4
Date of Issue