The evaluation of the Gaussian Mixture Probability Hypothesis Density approach for multi-target tracking

Jiandan  Chen; Oyekanlu Emmanuel Adebomi; Samuel Onidare; Wlodek Kulesza

doi:10.1109/IST.2010.5548541

The evaluation of the Gaussian Mixture Probability Hypothesis Density approach for multi-target tracking

Jiandan Chen, Oyekanlu Emmanuel Adebomi, Samuel Onidare, Wlodek Kulesza

Blekinge Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Citations (Scopus)

Abstract

This paper describes the performance of the Gaussian Mixture Probability Hypothesis Density (GM-PHD) filter for multiple human tracking in an intelligent vision system. Human movement trajectories were observed with a camera and tracked by the GM-PHD filter. The filter multi-target tracking ability was validated by two random motion trajectories in the paper. To evaluate the filter performance in relation to the target movement, the motion velocity and angular velocity as key evaluation factors were proposed. A circular motion model was implemented for simplified analysis of the filter tracking performance. The results indicate that the mean absolute error defined as the difference between the filter prediction and the ground truth is proportional to the motion speed and angular velocity of the target. The error is only slightly affected by the tracking targets' number.

Original language	English
Title of host publication	2010 IEEE International Conference on Imaging Systems and Techniques
Publisher	IEEE
Number of pages	4
ISBN (Electronic)	9781424464944, 9781424464937
ISBN (Print)	9781424464920
DOIs	https://doi.org/10.1109/IST.2010.5548541
Publication status	Published - 16 Aug 2010
Externally published	Yes
Event	2010 IEEE International Conference on Imaging Systems and Techniques - Thessaloniki, Greece Duration: 1 Jul 2010 → 2 Jul 2010 http://ist.ieee-ims.org/

Publication series

Name	IEEE International Workshop on Imaging Systems and Techniques
Publisher	IEEE
ISSN (Print)	1558-2809

Conference

Conference	2010 IEEE International Conference on Imaging Systems and Techniques
Abbreviated title	IST 2010
Country/Territory	Greece
City	Thessaloniki
Period	1/07/10 → 2/07/10
Internet address	http://ist.ieee-ims.org/

Access to Document

10.1109/IST.2010.5548541Licence: Unspecified

Cite this

@inproceedings{4d698e447d0b44aba7c2ef0fcc2828af,

title = "The evaluation of the Gaussian Mixture Probability Hypothesis Density approach for multi-target tracking",

abstract = "This paper describes the performance of the Gaussian Mixture Probability Hypothesis Density (GM-PHD) filter for multiple human tracking in an intelligent vision system. Human movement trajectories were observed with a camera and tracked by the GM-PHD filter. The filter multi-target tracking ability was validated by two random motion trajectories in the paper. To evaluate the filter performance in relation to the target movement, the motion velocity and angular velocity as key evaluation factors were proposed. A circular motion model was implemented for simplified analysis of the filter tracking performance. The results indicate that the mean absolute error defined as the difference between the filter prediction and the ground truth is proportional to the motion speed and angular velocity of the target. The error is only slightly affected by the tracking targets' number.",

keywords = "Human Tracking, Probability Hypothesis Density, Performance Evaluation, Vision System",

author = "Jiandan Chen and Adebomi, \{Oyekanlu Emmanuel\} and Samuel Onidare and Wlodek Kulesza",

year = "2010",

month = aug,

day = "16",

doi = "10.1109/IST.2010.5548541",

language = "English",

isbn = "9781424464920",

series = "IEEE International Workshop on Imaging Systems and Techniques",

publisher = "IEEE",

booktitle = "2010 IEEE International Conference on Imaging Systems and Techniques",

address = "United States",

note = "2010 IEEE International Conference on Imaging Systems and Techniques, IST 2010 ; Conference date: 01-07-2010 Through 02-07-2010",

url = "http://ist.ieee-ims.org/",

}

Chen, J, Adebomi, OE, Onidare, S & Kulesza, W 2010, The evaluation of the Gaussian Mixture Probability Hypothesis Density approach for multi-target tracking. in 2010 IEEE International Conference on Imaging Systems and Techniques., 5548541, IEEE International Workshop on Imaging Systems and Techniques, IEEE, 2010 IEEE International Conference on Imaging Systems and Techniques, Thessaloniki, Greece, 1/07/10. https://doi.org/10.1109/IST.2010.5548541

The evaluation of the Gaussian Mixture Probability Hypothesis Density approach for multi-target tracking. / Chen, Jiandan ; Adebomi, Oyekanlu Emmanuel; Onidare, Samuel et al.
2010 IEEE International Conference on Imaging Systems and Techniques. IEEE, 2010. 5548541 (IEEE International Workshop on Imaging Systems and Techniques).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - The evaluation of the Gaussian Mixture Probability Hypothesis Density approach for multi-target tracking

AU - Chen, Jiandan

AU - Adebomi, Oyekanlu Emmanuel

AU - Onidare, Samuel

AU - Kulesza, Wlodek

PY - 2010/8/16

Y1 - 2010/8/16

N2 - This paper describes the performance of the Gaussian Mixture Probability Hypothesis Density (GM-PHD) filter for multiple human tracking in an intelligent vision system. Human movement trajectories were observed with a camera and tracked by the GM-PHD filter. The filter multi-target tracking ability was validated by two random motion trajectories in the paper. To evaluate the filter performance in relation to the target movement, the motion velocity and angular velocity as key evaluation factors were proposed. A circular motion model was implemented for simplified analysis of the filter tracking performance. The results indicate that the mean absolute error defined as the difference between the filter prediction and the ground truth is proportional to the motion speed and angular velocity of the target. The error is only slightly affected by the tracking targets' number.

AB - This paper describes the performance of the Gaussian Mixture Probability Hypothesis Density (GM-PHD) filter for multiple human tracking in an intelligent vision system. Human movement trajectories were observed with a camera and tracked by the GM-PHD filter. The filter multi-target tracking ability was validated by two random motion trajectories in the paper. To evaluate the filter performance in relation to the target movement, the motion velocity and angular velocity as key evaluation factors were proposed. A circular motion model was implemented for simplified analysis of the filter tracking performance. The results indicate that the mean absolute error defined as the difference between the filter prediction and the ground truth is proportional to the motion speed and angular velocity of the target. The error is only slightly affected by the tracking targets' number.

KW - Human Tracking

KW - Probability Hypothesis Density

KW - Performance Evaluation

KW - Vision System

UR - https://www.scopus.com/pages/publications/77957834962

U2 - 10.1109/IST.2010.5548541

DO - 10.1109/IST.2010.5548541

M3 - Conference contribution

SN - 9781424464920

T3 - IEEE International Workshop on Imaging Systems and Techniques

BT - 2010 IEEE International Conference on Imaging Systems and Techniques

PB - IEEE

T2 - 2010 IEEE International Conference on Imaging Systems and Techniques

Y2 - 1 July 2010 through 2 July 2010

ER -

The evaluation of the Gaussian Mixture Probability Hypothesis Density approach for multi-target tracking

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this