Object tracking system using evolutionary agent search

Teppei Inomata, Kouji Kimura, Masafumi Hagiwara

Research output: Contribution to journalArticle

Abstract

In computer vision, many systems for video surveillance have been studied and developed. Finding appropriate features is very important especially for robust object tracking. This paper proposes a new system employing an evolutionary technique to track moving objects such as pedestrian effectively. In the proposed system, a number of agents are generated for each object, and independently search and move to the predicted position from features of local region. Each agent can select the appropriate feature relevant for the scene and the object to track by an evolutionary method using two values of feature effectiveness: normality and separateness. We carried out experiments using some scenes in an outside parking. The proposed system showed much better performance compared with the conventional system and a system using particle filter.

Original languageEnglish
Pages (from-to)272-280
Number of pages9
JournalTransactions of the Japanese Society for Artificial Intelligence
Volume25
Issue number2
DOIs
Publication statusPublished - 2010

Fingerprint

Parking
Computer vision
Experiments

Keywords

  • Agent search
  • Evolutionary computer vision
  • Object tracking

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software

Cite this

Object tracking system using evolutionary agent search. / Inomata, Teppei; Kimura, Kouji; Hagiwara, Masafumi.

In: Transactions of the Japanese Society for Artificial Intelligence, Vol. 25, No. 2, 2010, p. 272-280.

Research output: Contribution to journalArticle

@article{18e31dfd94724361a5fbb91a57f5017a,
title = "Object tracking system using evolutionary agent search",
abstract = "In computer vision, many systems for video surveillance have been studied and developed. Finding appropriate features is very important especially for robust object tracking. This paper proposes a new system employing an evolutionary technique to track moving objects such as pedestrian effectively. In the proposed system, a number of agents are generated for each object, and independently search and move to the predicted position from features of local region. Each agent can select the appropriate feature relevant for the scene and the object to track by an evolutionary method using two values of feature effectiveness: normality and separateness. We carried out experiments using some scenes in an outside parking. The proposed system showed much better performance compared with the conventional system and a system using particle filter.",
keywords = "Agent search, Evolutionary computer vision, Object tracking",
author = "Teppei Inomata and Kouji Kimura and Masafumi Hagiwara",
year = "2010",
doi = "10.1527/tjsai.25.272",
language = "English",
volume = "25",
pages = "272--280",
journal = "Transactions of the Japanese Society for Artificial Intelligence",
issn = "1346-0714",
publisher = "Japanese Society for Artificial Intelligence",
number = "2",

}

TY - JOUR

T1 - Object tracking system using evolutionary agent search

AU - Inomata, Teppei

AU - Kimura, Kouji

AU - Hagiwara, Masafumi

PY - 2010

Y1 - 2010

N2 - In computer vision, many systems for video surveillance have been studied and developed. Finding appropriate features is very important especially for robust object tracking. This paper proposes a new system employing an evolutionary technique to track moving objects such as pedestrian effectively. In the proposed system, a number of agents are generated for each object, and independently search and move to the predicted position from features of local region. Each agent can select the appropriate feature relevant for the scene and the object to track by an evolutionary method using two values of feature effectiveness: normality and separateness. We carried out experiments using some scenes in an outside parking. The proposed system showed much better performance compared with the conventional system and a system using particle filter.

AB - In computer vision, many systems for video surveillance have been studied and developed. Finding appropriate features is very important especially for robust object tracking. This paper proposes a new system employing an evolutionary technique to track moving objects such as pedestrian effectively. In the proposed system, a number of agents are generated for each object, and independently search and move to the predicted position from features of local region. Each agent can select the appropriate feature relevant for the scene and the object to track by an evolutionary method using two values of feature effectiveness: normality and separateness. We carried out experiments using some scenes in an outside parking. The proposed system showed much better performance compared with the conventional system and a system using particle filter.

KW - Agent search

KW - Evolutionary computer vision

KW - Object tracking

UR - http://www.scopus.com/inward/record.url?scp=77955935756&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77955935756&partnerID=8YFLogxK

U2 - 10.1527/tjsai.25.272

DO - 10.1527/tjsai.25.272

M3 - Article

AN - SCOPUS:77955935756

VL - 25

SP - 272

EP - 280

JO - Transactions of the Japanese Society for Artificial Intelligence

JF - Transactions of the Japanese Society for Artificial Intelligence

SN - 1346-0714

IS - 2

ER -