Object tracking and classification system using agent search

Teppei Inomata, Kouji Kimura, Masafumi Hagiwara

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Many methods for video surveillance have been developed. Robust tracking and high-performance classification are required for secure surveillance. In this paper, we propose a new recognition system that can track moving objects such as pedestrian, and classify them using a single camera in an open space parking. The proposed system can 1)perform robust object tracking and classification over occlusion and crossing; 2)look a local region of object image; and 3)integrate all processes into time series data flow. For object tracking, we developed a new agent tracking algorithm. A number of agents are generated for each object, and independently search and move to the future position by looking a local region's feature of their objects. Then they agents get fitness values, and the object ID of its local region is updated. For object classification, we forge a strong classifier from weak classifiers using AdaBoost. In practice, we recorded some scenes in an outside parking using a video camera, and tried to track objects and classified them into "person" or "vehicle". As a result, we achieved over 97% for tracking success rate, and over 87% for classification success rate.

Original languageEnglish
JournalIEEJ Transactions on Electronics, Information and Systems
Volume129
Issue number11
Publication statusPublished - 2009

Fingerprint

Parking
Classifiers
Adaptive boosting
Video cameras
Time series
Cameras

Keywords

  • Agent tracking algorithm
  • Boosting algorithm
  • Image sequence
  • Object classification
  • Object tracking

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

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

In: IEEJ Transactions on Electronics, Information and Systems, Vol. 129, No. 11, 2009.

Research output: Contribution to journalArticle

@article{8709639713f9433994380ca590121d4b,
title = "Object tracking and classification system using agent search",
abstract = "Many methods for video surveillance have been developed. Robust tracking and high-performance classification are required for secure surveillance. In this paper, we propose a new recognition system that can track moving objects such as pedestrian, and classify them using a single camera in an open space parking. The proposed system can 1)perform robust object tracking and classification over occlusion and crossing; 2)look a local region of object image; and 3)integrate all processes into time series data flow. For object tracking, we developed a new agent tracking algorithm. A number of agents are generated for each object, and independently search and move to the future position by looking a local region's feature of their objects. Then they agents get fitness values, and the object ID of its local region is updated. For object classification, we forge a strong classifier from weak classifiers using AdaBoost. In practice, we recorded some scenes in an outside parking using a video camera, and tried to track objects and classified them into {"}person{"} or {"}vehicle{"}. As a result, we achieved over 97{\%} for tracking success rate, and over 87{\%} for classification success rate.",
keywords = "Agent tracking algorithm, Boosting algorithm, Image sequence, Object classification, Object tracking",
author = "Teppei Inomata and Kouji Kimura and Masafumi Hagiwara",
year = "2009",
language = "English",
volume = "129",
journal = "IEEJ Transactions on Electronics, Information and Systems",
issn = "0385-4221",
publisher = "The Institute of Electrical Engineers of Japan",
number = "11",

}

TY - JOUR

T1 - Object tracking and classification system using agent search

AU - Inomata, Teppei

AU - Kimura, Kouji

AU - Hagiwara, Masafumi

PY - 2009

Y1 - 2009

N2 - Many methods for video surveillance have been developed. Robust tracking and high-performance classification are required for secure surveillance. In this paper, we propose a new recognition system that can track moving objects such as pedestrian, and classify them using a single camera in an open space parking. The proposed system can 1)perform robust object tracking and classification over occlusion and crossing; 2)look a local region of object image; and 3)integrate all processes into time series data flow. For object tracking, we developed a new agent tracking algorithm. A number of agents are generated for each object, and independently search and move to the future position by looking a local region's feature of their objects. Then they agents get fitness values, and the object ID of its local region is updated. For object classification, we forge a strong classifier from weak classifiers using AdaBoost. In practice, we recorded some scenes in an outside parking using a video camera, and tried to track objects and classified them into "person" or "vehicle". As a result, we achieved over 97% for tracking success rate, and over 87% for classification success rate.

AB - Many methods for video surveillance have been developed. Robust tracking and high-performance classification are required for secure surveillance. In this paper, we propose a new recognition system that can track moving objects such as pedestrian, and classify them using a single camera in an open space parking. The proposed system can 1)perform robust object tracking and classification over occlusion and crossing; 2)look a local region of object image; and 3)integrate all processes into time series data flow. For object tracking, we developed a new agent tracking algorithm. A number of agents are generated for each object, and independently search and move to the future position by looking a local region's feature of their objects. Then they agents get fitness values, and the object ID of its local region is updated. For object classification, we forge a strong classifier from weak classifiers using AdaBoost. In practice, we recorded some scenes in an outside parking using a video camera, and tried to track objects and classified them into "person" or "vehicle". As a result, we achieved over 97% for tracking success rate, and over 87% for classification success rate.

KW - Agent tracking algorithm

KW - Boosting algorithm

KW - Image sequence

KW - Object classification

KW - Object tracking

UR - http://www.scopus.com/inward/record.url?scp=72849125080&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=72849125080&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:72849125080

VL - 129

JO - IEEJ Transactions on Electronics, Information and Systems

JF - IEEJ Transactions on Electronics, Information and Systems

SN - 0385-4221

IS - 11

ER -