Dynamically visual learning for people identification with sparsely distributed cameras

Hidenori Tanaka, Itaru Kitahara, Hideo Saito, Hiroshi Murase, Kiyoshi Kogure, Norihiro Hagita

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

We propose a dynamic visual learning method that aims to identify people by using sparsely distributed multiple surveillance cameras. In the proposed method, virtual viewpoint images are synthesized by interpolating the sparsely distributed images with a simple 3D shape model of the human head, so that virtual densely distributed multiple images can be obtained. The multiple images generate an initial eigenspace in the initial learning step. In the following additional learning step, other distributed cameras capture additional images that update the eigenspace to improve the recognition performance. The discernment capability for personal identification of the proposed method is demonstrated experimentally.

Original languageEnglish
Title of host publicationLecture Notes in Computer Science
EditorsH. Kalviainen, J. Parkkinen, A. Kaarna
Pages130-140
Number of pages11
Volume3540
Publication statusPublished - 2005
Event14th Scandinavian Conference on Image Analysis, SCIA 2005 - Joensuu, Finland
Duration: 2005 Jun 192005 Jun 22

Other

Other14th Scandinavian Conference on Image Analysis, SCIA 2005
CountryFinland
CityJoensuu
Period05/6/1905/6/22

Fingerprint

Cameras

ASJC Scopus subject areas

  • Computer Science (miscellaneous)

Cite this

Tanaka, H., Kitahara, I., Saito, H., Murase, H., Kogure, K., & Hagita, N. (2005). Dynamically visual learning for people identification with sparsely distributed cameras. In H. Kalviainen, J. Parkkinen, & A. Kaarna (Eds.), Lecture Notes in Computer Science (Vol. 3540, pp. 130-140)

Dynamically visual learning for people identification with sparsely distributed cameras. / Tanaka, Hidenori; Kitahara, Itaru; Saito, Hideo; Murase, Hiroshi; Kogure, Kiyoshi; Hagita, Norihiro.

Lecture Notes in Computer Science. ed. / H. Kalviainen; J. Parkkinen; A. Kaarna. Vol. 3540 2005. p. 130-140.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Tanaka, H, Kitahara, I, Saito, H, Murase, H, Kogure, K & Hagita, N 2005, Dynamically visual learning for people identification with sparsely distributed cameras. in H Kalviainen, J Parkkinen & A Kaarna (eds), Lecture Notes in Computer Science. vol. 3540, pp. 130-140, 14th Scandinavian Conference on Image Analysis, SCIA 2005, Joensuu, Finland, 05/6/19.
Tanaka H, Kitahara I, Saito H, Murase H, Kogure K, Hagita N. Dynamically visual learning for people identification with sparsely distributed cameras. In Kalviainen H, Parkkinen J, Kaarna A, editors, Lecture Notes in Computer Science. Vol. 3540. 2005. p. 130-140
Tanaka, Hidenori ; Kitahara, Itaru ; Saito, Hideo ; Murase, Hiroshi ; Kogure, Kiyoshi ; Hagita, Norihiro. / Dynamically visual learning for people identification with sparsely distributed cameras. Lecture Notes in Computer Science. editor / H. Kalviainen ; J. Parkkinen ; A. Kaarna. Vol. 3540 2005. pp. 130-140
@inproceedings{a7aabbd8b263475ea5b6f20a63b77e25,
title = "Dynamically visual learning for people identification with sparsely distributed cameras",
abstract = "We propose a dynamic visual learning method that aims to identify people by using sparsely distributed multiple surveillance cameras. In the proposed method, virtual viewpoint images are synthesized by interpolating the sparsely distributed images with a simple 3D shape model of the human head, so that virtual densely distributed multiple images can be obtained. The multiple images generate an initial eigenspace in the initial learning step. In the following additional learning step, other distributed cameras capture additional images that update the eigenspace to improve the recognition performance. The discernment capability for personal identification of the proposed method is demonstrated experimentally.",
author = "Hidenori Tanaka and Itaru Kitahara and Hideo Saito and Hiroshi Murase and Kiyoshi Kogure and Norihiro Hagita",
year = "2005",
language = "English",
volume = "3540",
pages = "130--140",
editor = "H. Kalviainen and J. Parkkinen and A. Kaarna",
booktitle = "Lecture Notes in Computer Science",

}

TY - GEN

T1 - Dynamically visual learning for people identification with sparsely distributed cameras

AU - Tanaka, Hidenori

AU - Kitahara, Itaru

AU - Saito, Hideo

AU - Murase, Hiroshi

AU - Kogure, Kiyoshi

AU - Hagita, Norihiro

PY - 2005

Y1 - 2005

N2 - We propose a dynamic visual learning method that aims to identify people by using sparsely distributed multiple surveillance cameras. In the proposed method, virtual viewpoint images are synthesized by interpolating the sparsely distributed images with a simple 3D shape model of the human head, so that virtual densely distributed multiple images can be obtained. The multiple images generate an initial eigenspace in the initial learning step. In the following additional learning step, other distributed cameras capture additional images that update the eigenspace to improve the recognition performance. The discernment capability for personal identification of the proposed method is demonstrated experimentally.

AB - We propose a dynamic visual learning method that aims to identify people by using sparsely distributed multiple surveillance cameras. In the proposed method, virtual viewpoint images are synthesized by interpolating the sparsely distributed images with a simple 3D shape model of the human head, so that virtual densely distributed multiple images can be obtained. The multiple images generate an initial eigenspace in the initial learning step. In the following additional learning step, other distributed cameras capture additional images that update the eigenspace to improve the recognition performance. The discernment capability for personal identification of the proposed method is demonstrated experimentally.

UR - http://www.scopus.com/inward/record.url?scp=26444570344&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=26444570344&partnerID=8YFLogxK

M3 - Conference contribution

VL - 3540

SP - 130

EP - 140

BT - Lecture Notes in Computer Science

A2 - Kalviainen, H.

A2 - Parkkinen, J.

A2 - Kaarna, A.

ER -