Robust motion tracking of multiple objects with kl-immpdaf

Jungduk Son, Hanseok Ko

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This paper describes how the image sequences taken by a stationary video camera may be effectively processed to detect and track moving objects against a stationary background in real-time. Our approach is first to isolate the moving objects in image sequences via a modified adaptive background estimation method and then perform token tracking of multiple objects based on features extracted from the processed image sequences. In feature based multiple object tracking, the most prominent tracking issues are track initialization, data association, occlusions due to traffic congestion, and object maneuvering. While there are limited past works addressing these problems, most relevant tracking systems proposed in the past are independently focused to either "occlusion" or "data association" only. In this paper, we propose the KL-IMMPDA (Kanade Lucas-Interacting Multiple Model Probabilistic Data Association) filtering approach for multiple-object tracking to collectively address the key issues. The proposed method essentially employs optical flow measurements for both detection and track initialization while the KL-IMMPDA filter is used to accept or reject measurements, which belong to other objects. The data association performed by the proposed KL-IMMPDA results in an effective tracking scheme, which is robust to partial occlusions and image clutter of object maneuvering. The simulation results show a significant performance improvement for tracking multiobjects in occlusion and maneuvering, when compared to other conventional trackers such as Kaiman filter.

Original languageEnglish
Pages (from-to)179-187
Number of pages9
JournalIEICE Transactions on Information and Systems
VolumeE84-D
Issue number1
Publication statusPublished - 2001 Dec 1

Fingerprint

Traffic congestion
Optical flows
Video cameras
Flow measurement
Statistical Models

Keywords

  • Image motion tracking
  • Kl-immpda filter
  • Multi-object tracking
  • Optical flow

ASJC Scopus subject areas

  • Information Systems
  • Computer Graphics and Computer-Aided Design
  • Software

Cite this

Robust motion tracking of multiple objects with kl-immpdaf. / Son, Jungduk; Ko, Hanseok.

In: IEICE Transactions on Information and Systems, Vol. E84-D, No. 1, 01.12.2001, p. 179-187.

Research output: Contribution to journalArticle

@article{84001754a33c483da1b93a8581f12b80,
title = "Robust motion tracking of multiple objects with kl-immpdaf",
abstract = "This paper describes how the image sequences taken by a stationary video camera may be effectively processed to detect and track moving objects against a stationary background in real-time. Our approach is first to isolate the moving objects in image sequences via a modified adaptive background estimation method and then perform token tracking of multiple objects based on features extracted from the processed image sequences. In feature based multiple object tracking, the most prominent tracking issues are track initialization, data association, occlusions due to traffic congestion, and object maneuvering. While there are limited past works addressing these problems, most relevant tracking systems proposed in the past are independently focused to either {"}occlusion{"} or {"}data association{"} only. In this paper, we propose the KL-IMMPDA (Kanade Lucas-Interacting Multiple Model Probabilistic Data Association) filtering approach for multiple-object tracking to collectively address the key issues. The proposed method essentially employs optical flow measurements for both detection and track initialization while the KL-IMMPDA filter is used to accept or reject measurements, which belong to other objects. The data association performed by the proposed KL-IMMPDA results in an effective tracking scheme, which is robust to partial occlusions and image clutter of object maneuvering. The simulation results show a significant performance improvement for tracking multiobjects in occlusion and maneuvering, when compared to other conventional trackers such as Kaiman filter.",
keywords = "Image motion tracking, Kl-immpda filter, Multi-object tracking, Optical flow",
author = "Jungduk Son and Hanseok Ko",
year = "2001",
month = "12",
day = "1",
language = "English",
volume = "E84-D",
pages = "179--187",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "1",

}

TY - JOUR

T1 - Robust motion tracking of multiple objects with kl-immpdaf

AU - Son, Jungduk

AU - Ko, Hanseok

PY - 2001/12/1

Y1 - 2001/12/1

N2 - This paper describes how the image sequences taken by a stationary video camera may be effectively processed to detect and track moving objects against a stationary background in real-time. Our approach is first to isolate the moving objects in image sequences via a modified adaptive background estimation method and then perform token tracking of multiple objects based on features extracted from the processed image sequences. In feature based multiple object tracking, the most prominent tracking issues are track initialization, data association, occlusions due to traffic congestion, and object maneuvering. While there are limited past works addressing these problems, most relevant tracking systems proposed in the past are independently focused to either "occlusion" or "data association" only. In this paper, we propose the KL-IMMPDA (Kanade Lucas-Interacting Multiple Model Probabilistic Data Association) filtering approach for multiple-object tracking to collectively address the key issues. The proposed method essentially employs optical flow measurements for both detection and track initialization while the KL-IMMPDA filter is used to accept or reject measurements, which belong to other objects. The data association performed by the proposed KL-IMMPDA results in an effective tracking scheme, which is robust to partial occlusions and image clutter of object maneuvering. The simulation results show a significant performance improvement for tracking multiobjects in occlusion and maneuvering, when compared to other conventional trackers such as Kaiman filter.

AB - This paper describes how the image sequences taken by a stationary video camera may be effectively processed to detect and track moving objects against a stationary background in real-time. Our approach is first to isolate the moving objects in image sequences via a modified adaptive background estimation method and then perform token tracking of multiple objects based on features extracted from the processed image sequences. In feature based multiple object tracking, the most prominent tracking issues are track initialization, data association, occlusions due to traffic congestion, and object maneuvering. While there are limited past works addressing these problems, most relevant tracking systems proposed in the past are independently focused to either "occlusion" or "data association" only. In this paper, we propose the KL-IMMPDA (Kanade Lucas-Interacting Multiple Model Probabilistic Data Association) filtering approach for multiple-object tracking to collectively address the key issues. The proposed method essentially employs optical flow measurements for both detection and track initialization while the KL-IMMPDA filter is used to accept or reject measurements, which belong to other objects. The data association performed by the proposed KL-IMMPDA results in an effective tracking scheme, which is robust to partial occlusions and image clutter of object maneuvering. The simulation results show a significant performance improvement for tracking multiobjects in occlusion and maneuvering, when compared to other conventional trackers such as Kaiman filter.

KW - Image motion tracking

KW - Kl-immpda filter

KW - Multi-object tracking

KW - Optical flow

UR - http://www.scopus.com/inward/record.url?scp=0035125783&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035125783&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0035125783

VL - E84-D

SP - 179

EP - 187

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 1

ER -