Moving object tracking using multiple views and data association

Youngshin Ahn; Ahmed Mohammed; Jaeho Choi

Moving object tracking using multiple views and data association

Youngshin Ahn
, Ahmed Mohammed
, Jaeho Choi

Division of Electronic Engineering

Jeonbuk National University
Jimma University Ethiopia

Research output: Contribution to conference › Conference paper › peer-review

Abstract

In this paper, a moving object tracking method using multiple views of the same scene taken by three cameras are presented. The object of interest is the pedestrian in the street. Unlike the single view method, the proposed multi-view method can effectively exploit extra information available in the other views when the object of interest in one of the views falls into an occlusion or clutter environment. Making a relation of an object detected in one view with the ones in the other views is critical and it is obtained by data association. The simulation results show a significant performance improvement over the conventional one.

Original language	English
Title of host publication	4th International Workshop on Computer Science and Engineering - Summer, WCSE 2014
State	Published - 2014
Event	4th International Workshop on Computer Science and Engineering - Summer, WCSE 2014 - Dubai, United Arab Emirates Duration: 2014.08.22 → 2014.08.23

Conference

Conference	4th International Workshop on Computer Science and Engineering - Summer, WCSE 2014
Country/Territory	United Arab Emirates
City	Dubai
Period	14.08.22 → 14.08.23

Keywords

Data association
Moving object detection and tracking
Multiple views

Quacquarelli Symonds(QS) Subject Topics

Computer Science & Information Systems

Cite this

@inproceedings{8e81c84518e445dfa6549ee48f3769b3,

title = "Moving object tracking using multiple views and data association",

abstract = "In this paper, a moving object tracking method using multiple views of the same scene taken by three cameras are presented. The object of interest is the pedestrian in the street. Unlike the single view method, the proposed multi-view method can effectively exploit extra information available in the other views when the object of interest in one of the views falls into an occlusion or clutter environment. Making a relation of an object detected in one view with the ones in the other views is critical and it is obtained by data association. The simulation results show a significant performance improvement over the conventional one.",

keywords = "Data association, Moving object detection and tracking, Multiple views",

author = "Youngshin Ahn and Ahmed Mohammed and Jaeho Choi",

year = "2014",

language = "English",

booktitle = "4th International Workshop on Computer Science and Engineering - Summer, WCSE 2014",

note = "4th International Workshop on Computer Science and Engineering - Summer, WCSE 2014 ; Conference date: 22-08-2014 Through 23-08-2014",

}

TY - GEN

T1 - Moving object tracking using multiple views and data association

AU - Ahn, Youngshin

AU - Mohammed, Ahmed

AU - Choi, Jaeho

PY - 2014

Y1 - 2014

N2 - In this paper, a moving object tracking method using multiple views of the same scene taken by three cameras are presented. The object of interest is the pedestrian in the street. Unlike the single view method, the proposed multi-view method can effectively exploit extra information available in the other views when the object of interest in one of the views falls into an occlusion or clutter environment. Making a relation of an object detected in one view with the ones in the other views is critical and it is obtained by data association. The simulation results show a significant performance improvement over the conventional one.

AB - In this paper, a moving object tracking method using multiple views of the same scene taken by three cameras are presented. The object of interest is the pedestrian in the street. Unlike the single view method, the proposed multi-view method can effectively exploit extra information available in the other views when the object of interest in one of the views falls into an occlusion or clutter environment. Making a relation of an object detected in one view with the ones in the other views is critical and it is obtained by data association. The simulation results show a significant performance improvement over the conventional one.

KW - Data association

KW - Moving object detection and tracking

KW - Multiple views

UR - https://www.scopus.com/pages/publications/84924943477

M3 - Conference paper

AN - SCOPUS:84924943477

BT - 4th International Workshop on Computer Science and Engineering - Summer, WCSE 2014

T2 - 4th International Workshop on Computer Science and Engineering - Summer, WCSE 2014

Y2 - 22 August 2014 through 23 August 2014

ER -

Moving object tracking using multiple views and data association

Abstract

Conference

Keywords

Quacquarelli Symonds(QS) Subject Topics

Other files and links

Fingerprint

Cite this