Instance-based location estimation algorithm for a pedestrian in multiple color dynamic images

Yutaka Hatakeyama*, Akimichi Mitsuta, Kaoru Hirota

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Location estimation algorithm for a pedestrian is proposed for the real surveillance system based on color instances with color dynamic images under low illumination, where the proposed color instances consist of color-difference, moving possibility region, and previous detection objects in edge region using time series data. It provides useful detection result for too low illuminated situation. Experimental results for dynamic image taken under low illumination in streets show that detected frames with the proposed algorithm increase by 20% compared with detection result without color instances. The proposed algorithm is under consideration for use in a relatively poor security downtown area in Japan.

Original languageEnglish
Title of host publication2006 International Symposium on Intelligent Signal Processing and Communications, ISPACS'06
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages526-529
Number of pages4
ISBN (Print)0780397339, 9780780397330
DOIs
Publication statusPublished - 2006
Externally publishedYes
Event2006 International Symposium on Intelligent Signal Processing and Communications, ISPACS'06 - Yonago, Japan
Duration: 12 Dec 200615 Dec 2006

Publication series

Name2006 International Symposium on Intelligent Signal Processing and Communications, ISPACS'06

Conference

Conference2006 International Symposium on Intelligent Signal Processing and Communications, ISPACS'06
Country/TerritoryJapan
CityYonago
Period12/12/0615/12/06

Fingerprint

Dive into the research topics of 'Instance-based location estimation algorithm for a pedestrian in multiple color dynamic images'. Together they form a unique fingerprint.

Cite this