Presentation 2007-09-27
Moving Objects Tracking by Time-series Processing based on Region Estimation using Intensity and Motion
Masaya IKEDA, Kan OKUBO, Norio TAGAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) For tracking moving objects, template matching method is usually used. However, it cannot cope with shape changes of a target object in images sufficiently. Especially, for the case that there are multiple objects, the target object may be missed since occlusion often arises and objects suddenly disappear or appear. Although moving region detection can be done by the background subtraction or the temporal subtraction, in order to recognize the detected regions at the multiple frames as the same object, the tracking procedure without the above shortcoming is required. On the other hand, to discriminate multiple objects in still images, the label assignment based on the MAP estimation using object's feature is convenient. In this study, we propose a method which enables to stably track moving objects by extending the above MAP assignment and using the detected results at the previous frame as a prior information. Additionally, we confirm that using the both of color and motion information the tracking performance of the proposed method improves than using the each of them singly.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) moving object detection / tracking / intensity / optical flow / occlusion
Paper # CQ2007-37,OIS2007-27,IE2007-34
Date of Issue

Conference Information
Committee CQ
Conference Date 2007/9/20(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 Communication Quality (CQ)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Moving Objects Tracking by Time-series Processing based on Region Estimation using Intensity and Motion
Sub Title (in English)
Keyword(1) moving object detection
Keyword(2) tracking
Keyword(3) intensity
Keyword(4) optical flow
Keyword(5) occlusion
1st Author's Name Masaya IKEDA
1st Author's Affiliation Graduate School of System Design, Tokyo Metropolitan University()
2nd Author's Name Kan OKUBO
2nd Author's Affiliation Graduate School of System Design, Tokyo Metropolitan University
3rd Author's Name Norio TAGAWA
3rd Author's Affiliation Graduate School of System Design, Tokyo Metropolitan University
Date 2007-09-27
Paper # CQ2007-37,OIS2007-27,IE2007-34
Volume (vol) vol.107
Number (no) 229
Page pp.pp.-
#Pages 6
Date of Issue