Multi-target tracking by using particle filtering and a social force model

Ata Ur Rehman; Syed Mohsen Naqvi; Lyudmila Mihaylova; Jonathon A. Chambers

Multi-target tracking by using particle filtering and a social force model

Ata Ur Rehman, Syed Mohsen Naqvi, Lyudmila Mihaylova, Jonathon A. Chambers

Research output: Book chapter/Published conference paper › Conference paper › peer-review

Abstract

This paper presents a particle filter for multiple target tracking. The main contribution of this work is in the proposed likelihood function accounting for the interactions between the objects. The filter likelihood function is calculated by combining a social force model for human behaviour with image features such as colour and motion. The added social force model contributes to coping with occlusions between the objects. The performance of the developed algorithm is validated on real video data. The results demonstrate the algorithm accuracy during complex interactions between the objects.

Original language	English
Title of host publication	FUSION 2014 - 17th International Conference on Information Fusion
Publisher	IEEE, Institute of Electrical and Electronics Engineers
ISBN (Electronic)	9788490123553
Publication status	Published - 03 Oct 2014
Event	17th International Conference on Information Fusion, FUSION 2014 - Congress Hall, Salamanca, Spain Duration: 07 Jul 2014 → 10 Jul 2014 http://www.fusion2014.org/

Publication series

Name	FUSION 2014 - 17th International Conference on Information Fusion

Conference

Conference	17th International Conference on Information Fusion, FUSION 2014
Country/Territory	Spain
City	Salamanca
Period	07/07/14 → 10/07/14
Other	The 17th International Conference on Information Fusion (Fusion 2014) will be held in Salamanca, Spain. This event will provide a forum to discuss the latest research in Information Fusion its impacts for industry and institutions. It intends to bring together researchers and developers from industry and the academic world to report on the latest scientific and technical advances on this frame. to discuss and debate the major issues, and to showcase the latest systems using these technologies. Authors are invited to submit papers to this conference describing advances and applications in Information Fusion, with submission of non-traditional topics encouraged. The presented papers shall be included in the IEEE Xplore and EI Compendex databases.
Internet address	http://www.fusion2014.org/

Cite this

@inproceedings{a3b6a2dd26f54390ba5012e3c1191cc7,

title = "Multi-target tracking by using particle filtering and a social force model",

abstract = "This paper presents a particle filter for multiple target tracking. The main contribution of this work is in the proposed likelihood function accounting for the interactions between the objects. The filter likelihood function is calculated by combining a social force model for human behaviour with image features such as colour and motion. The added social force model contributes to coping with occlusions between the objects. The performance of the developed algorithm is validated on real video data. The results demonstrate the algorithm accuracy during complex interactions between the objects.",

keywords = "multi-target tracking, particle filter, social force model",

author = "Rehman, {Ata Ur} and Naqvi, {Syed Mohsen} and Lyudmila Mihaylova and Chambers, {Jonathon A.}",

year = "2014",

month = oct,

day = "3",

language = "English",

series = "FUSION 2014 - 17th International Conference on Information Fusion",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

booktitle = "FUSION 2014 - 17th International Conference on Information Fusion",

address = "United States",

note = "17th International Conference on Information Fusion, FUSION 2014 ; Conference date: 07-07-2014 Through 10-07-2014",

url = "http://www.fusion2014.org/",

}

Rehman, AU, Naqvi, SM, Mihaylova, L & Chambers, JA 2014, Multi-target tracking by using particle filtering and a social force model. in FUSION 2014 - 17th International Conference on Information Fusion., 6916228, FUSION 2014 - 17th International Conference on Information Fusion, IEEE, Institute of Electrical and Electronics Engineers, 17th International Conference on Information Fusion, FUSION 2014, Salamanca, Spain, 07/07/14.

Multi-target tracking by using particle filtering and a social force model. / Rehman, Ata Ur; Naqvi, Syed Mohsen; Mihaylova, Lyudmila et al.
FUSION 2014 - 17th International Conference on Information Fusion. IEEE, Institute of Electrical and Electronics Engineers, 2014. 6916228 (FUSION 2014 - 17th International Conference on Information Fusion).

Research output: Book chapter/Published conference paper › Conference paper › peer-review

TY - GEN

T1 - Multi-target tracking by using particle filtering and a social force model

AU - Rehman, Ata Ur

AU - Naqvi, Syed Mohsen

AU - Mihaylova, Lyudmila

AU - Chambers, Jonathon A.

PY - 2014/10/3

Y1 - 2014/10/3

N2 - This paper presents a particle filter for multiple target tracking. The main contribution of this work is in the proposed likelihood function accounting for the interactions between the objects. The filter likelihood function is calculated by combining a social force model for human behaviour with image features such as colour and motion. The added social force model contributes to coping with occlusions between the objects. The performance of the developed algorithm is validated on real video data. The results demonstrate the algorithm accuracy during complex interactions between the objects.

AB - This paper presents a particle filter for multiple target tracking. The main contribution of this work is in the proposed likelihood function accounting for the interactions between the objects. The filter likelihood function is calculated by combining a social force model for human behaviour with image features such as colour and motion. The added social force model contributes to coping with occlusions between the objects. The performance of the developed algorithm is validated on real video data. The results demonstrate the algorithm accuracy during complex interactions between the objects.

KW - multi-target tracking

KW - particle filter

KW - social force model

UR - http://www.scopus.com/inward/record.url?scp=84910641700&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84910641700&partnerID=8YFLogxK

M3 - Conference paper

AN - SCOPUS:84910641700

T3 - FUSION 2014 - 17th International Conference on Information Fusion

BT - FUSION 2014 - 17th International Conference on Information Fusion

PB - IEEE, Institute of Electrical and Electronics Engineers

T2 - 17th International Conference on Information Fusion, FUSION 2014

Y2 - 7 July 2014 through 10 July 2014

ER -

Multi-target tracking by using particle filtering and a social force model

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this