Markerless multi-view articulated pose estimation using adaptive hierarchical particle swarm optimisation

Spela Ivekovic; Vijay John; Emanuele Trucco

doi:10.1007/978-3-642-12239-2_25

Markerless multi-view articulated pose estimation using adaptive hierarchical particle swarm optimisation

Spela Ivekovic
, Vijay John
, Emanuele Trucco

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

6 Citations (Scopus)

Abstract

In this paper, we present a new adaptive approach to multi-view markerless articulated human body pose estimation from multi-view video sequences, using Particle Swarm Optimisation (PSO). We address the computational complexity of the recently developed hierarchical PSO (HPSO) approach, which successfully estimated a wide range of different motion with a fixed set of parameters, but incurred an unnecessary overhead in computational complexity. Our adaptive approach, called APSO, preserves the black-box property of the HPSO in that it requires no parameter value input from the user. Instead, it adaptively changes the value of the search parameters online, depending on the quality of the pose estimate in the preceding frame of the sequence. We experimentally compare our adaptive approach with HPSO on four different video sequences and show that the computational complexity can be reduced without sacrificing accuracy and without requiring any user input or prior knowledge about the estimated motion type.

Original language	English
Title of host publication	Applications of Evolutionary Computation
Subtitle of host publication	EvoApplicatons 2010: EvoCOMPLEX, EvoGAMES, EvoIASP, EvoINTELLIGENCE, EvoNUM, and EvoSTOC, Istanbul, Turkey, April 7-9, 2010, Proceedings, Part I
Editors	C. DiChic, S. Cagoni, C. Cotta, M. Ebner, A. Ekart, A. I. EsparciaAlcazar, C. K. Goh, J. J. Merelo, F. Neri, M. Preuss, J. Togelius, G. N. Yannakakis
Place of Publication	Berlin
Publisher	Springer
Pages	241-250
Number of pages	10
ISBN (Electronic)	9783642122392
ISBN (Print)	9783642122385
DOIs	https://doi.org/10.1007/978-3-642-12239-2_25
Publication status	Published - 2010
Event	EvoApplications 2010: European Conference on the Applications of Evolutionary Computation - Istanbul, Turkey Duration: 7 Apr 2010 → 9 Apr 2010 http://dces.essex.ac.uk/research/evostar/evoapps.html

Publication series

Name	Lecture notes in computer science
Publisher	Springer
Volume	6024
ISSN (Print)	0302-9743

Conference

Conference	EvoApplications 2010: European Conference on the Applications of Evolutionary Computation
Country/Territory	Turkey
City	Istanbul
Period	7/04/10 → 9/04/10
Internet address	http://dces.essex.ac.uk/research/evostar/evoapps.html

Keywords

HUMAN MOTION
TRACKING

Access to Document

10.1007/978-3-642-12239-2_25

http://library.dundee.ac.uk:80/F/?func=direct&local_base=DUN01&doc_number=000743497

Markerless multi-view articulated pose estimation using adaptive hierarchical particle swarm optimisation
Ivekovic, S., John, V. & Trucco, E., 2010.
Research output: Contribution to conference › Paper

EvoApplications 2010: European Conference on the Applications of Evolutionary Computation
Trucco, E. (Participant)
7 Apr 2010 → 9 Apr 2010
Activity: Participating in or organising an event types › Participation in conference

Cite this

Ivekovic, S., John, V., & Trucco, E. (2010). Markerless multi-view articulated pose estimation using adaptive hierarchical particle swarm optimisation. In C. DiChic, S. Cagoni, C. Cotta, M. Ebner, A. Ekart, A. I. EsparciaAlcazar, C. K. Goh, J. J. Merelo, F. Neri, M. Preuss, J. Togelius, & G. N. Yannakakis (Eds.), Applications of Evolutionary Computation: EvoApplicatons 2010: EvoCOMPLEX, EvoGAMES, EvoIASP, EvoINTELLIGENCE, EvoNUM, and EvoSTOC, Istanbul, Turkey, April 7-9, 2010, Proceedings, Part I (pp. 241-250). (Lecture notes in computer science; Vol. 6024). Springer . https://doi.org/10.1007/978-3-642-12239-2_25

Ivekovic, Spela ; John, Vijay ; Trucco, Emanuele. / Markerless multi-view articulated pose estimation using adaptive hierarchical particle swarm optimisation. Applications of Evolutionary Computation: EvoApplicatons 2010: EvoCOMPLEX, EvoGAMES, EvoIASP, EvoINTELLIGENCE, EvoNUM, and EvoSTOC, Istanbul, Turkey, April 7-9, 2010, Proceedings, Part I. editor / C. DiChic ; S. Cagoni ; C. Cotta ; M. Ebner ; A. Ekart ; A. I. EsparciaAlcazar ; C. K. Goh ; J. J. Merelo ; F. Neri ; M. Preuss ; J. Togelius ; G. N. Yannakakis. Berlin : Springer , 2010. pp. 241-250 (Lecture notes in computer science).

@inproceedings{537970f16ae0447888288af61667a9de,

title = "Markerless multi-view articulated pose estimation using adaptive hierarchical particle swarm optimisation",

abstract = "In this paper, we present a new adaptive approach to multi-view markerless articulated human body pose estimation from multi-view video sequences, using Particle Swarm Optimisation (PSO). We address the computational complexity of the recently developed hierarchical PSO (HPSO) approach, which successfully estimated a wide range of different motion with a fixed set of parameters, but incurred an unnecessary overhead in computational complexity. Our adaptive approach, called APSO, preserves the black-box property of the HPSO in that it requires no parameter value input from the user. Instead, it adaptively changes the value of the search parameters online, depending on the quality of the pose estimate in the preceding frame of the sequence. We experimentally compare our adaptive approach with HPSO on four different video sequences and show that the computational complexity can be reduced without sacrificing accuracy and without requiring any user input or prior knowledge about the estimated motion type.",

keywords = "HUMAN MOTION, TRACKING",

author = "Spela Ivekovic and Vijay John and Emanuele Trucco",

year = "2010",

doi = "10.1007/978-3-642-12239-2\_25",

language = "English",

isbn = "9783642122385",

series = "Lecture notes in computer science",

publisher = "Springer ",

pages = "241--250",

editor = "C. DiChic and S. Cagoni and C. Cotta and M. Ebner and A. Ekart and EsparciaAlcazar, \{A. I.\} and Goh, \{C. K.\} and Merelo, \{J. J.\} and F. Neri and M. Preuss and J. Togelius and Yannakakis, \{G. N.\}",

booktitle = "Applications of Evolutionary Computation",

note = "EvoApplications 2010: European Conference on the Applications of Evolutionary Computation ; Conference date: 07-04-2010 Through 09-04-2010",

url = "http://dces.essex.ac.uk/research/evostar/evoapps.html",

}

Ivekovic, S, John, V & Trucco, E 2010, Markerless multi-view articulated pose estimation using adaptive hierarchical particle swarm optimisation. in C DiChic, S Cagoni, C Cotta, M Ebner, A Ekart, AI EsparciaAlcazar, CK Goh, JJ Merelo, F Neri, M Preuss, J Togelius & GN Yannakakis (eds), Applications of Evolutionary Computation: EvoApplicatons 2010: EvoCOMPLEX, EvoGAMES, EvoIASP, EvoINTELLIGENCE, EvoNUM, and EvoSTOC, Istanbul, Turkey, April 7-9, 2010, Proceedings, Part I. Lecture notes in computer science, vol. 6024, Springer , Berlin, pp. 241-250, EvoApplications 2010: European Conference on the Applications of Evolutionary Computation , Istanbul, Turkey, 7/04/10. https://doi.org/10.1007/978-3-642-12239-2_25

Markerless multi-view articulated pose estimation using adaptive hierarchical particle swarm optimisation. / Ivekovic, Spela; John, Vijay; Trucco, Emanuele.
Applications of Evolutionary Computation: EvoApplicatons 2010: EvoCOMPLEX, EvoGAMES, EvoIASP, EvoINTELLIGENCE, EvoNUM, and EvoSTOC, Istanbul, Turkey, April 7-9, 2010, Proceedings, Part I. ed. / C. DiChic; S. Cagoni; C. Cotta; M. Ebner; A. Ekart; A. I. EsparciaAlcazar; C. K. Goh; J. J. Merelo; F. Neri; M. Preuss; J. Togelius; G. N. Yannakakis. Berlin: Springer , 2010. p. 241-250 (Lecture notes in computer science; Vol. 6024).

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

TY - GEN

T1 - Markerless multi-view articulated pose estimation using adaptive hierarchical particle swarm optimisation

AU - Ivekovic, Spela

AU - John, Vijay

AU - Trucco, Emanuele

PY - 2010

Y1 - 2010

N2 - In this paper, we present a new adaptive approach to multi-view markerless articulated human body pose estimation from multi-view video sequences, using Particle Swarm Optimisation (PSO). We address the computational complexity of the recently developed hierarchical PSO (HPSO) approach, which successfully estimated a wide range of different motion with a fixed set of parameters, but incurred an unnecessary overhead in computational complexity. Our adaptive approach, called APSO, preserves the black-box property of the HPSO in that it requires no parameter value input from the user. Instead, it adaptively changes the value of the search parameters online, depending on the quality of the pose estimate in the preceding frame of the sequence. We experimentally compare our adaptive approach with HPSO on four different video sequences and show that the computational complexity can be reduced without sacrificing accuracy and without requiring any user input or prior knowledge about the estimated motion type.

AB - In this paper, we present a new adaptive approach to multi-view markerless articulated human body pose estimation from multi-view video sequences, using Particle Swarm Optimisation (PSO). We address the computational complexity of the recently developed hierarchical PSO (HPSO) approach, which successfully estimated a wide range of different motion with a fixed set of parameters, but incurred an unnecessary overhead in computational complexity. Our adaptive approach, called APSO, preserves the black-box property of the HPSO in that it requires no parameter value input from the user. Instead, it adaptively changes the value of the search parameters online, depending on the quality of the pose estimate in the preceding frame of the sequence. We experimentally compare our adaptive approach with HPSO on four different video sequences and show that the computational complexity can be reduced without sacrificing accuracy and without requiring any user input or prior knowledge about the estimated motion type.

KW - HUMAN MOTION

KW - TRACKING

U2 - 10.1007/978-3-642-12239-2_25

DO - 10.1007/978-3-642-12239-2_25

M3 - Conference contribution

SN - 9783642122385

T3 - Lecture notes in computer science

SP - 241

EP - 250

BT - Applications of Evolutionary Computation

A2 - DiChic, C.

A2 - Cagoni, S.

A2 - Cotta, C.

A2 - Ebner, M.

A2 - Ekart, A.

A2 - EsparciaAlcazar, A. I.

A2 - Goh, C. K.

A2 - Merelo, J. J.

A2 - Neri, F.

A2 - Preuss, M.

A2 - Togelius, J.

A2 - Yannakakis, G. N.

PB - Springer

CY - Berlin

T2 - EvoApplications 2010: European Conference on the Applications of Evolutionary Computation

Y2 - 7 April 2010 through 9 April 2010

ER -

Ivekovic S, John V, Trucco E. Markerless multi-view articulated pose estimation using adaptive hierarchical particle swarm optimisation. In DiChic C, Cagoni S, Cotta C, Ebner M, Ekart A, EsparciaAlcazar AI, Goh CK, Merelo JJ, Neri F, Preuss M, Togelius J, Yannakakis GN, editors, Applications of Evolutionary Computation: EvoApplicatons 2010: EvoCOMPLEX, EvoGAMES, EvoIASP, EvoINTELLIGENCE, EvoNUM, and EvoSTOC, Istanbul, Turkey, April 7-9, 2010, Proceedings, Part I. Berlin: Springer . 2010. p. 241-250. (Lecture notes in computer science). doi: 10.1007/978-3-642-12239-2_25

Markerless multi-view articulated pose estimation using adaptive hierarchical particle swarm optimisation

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Research output

Markerless multi-view articulated pose estimation using adaptive hierarchical particle swarm optimisation

Activities

EvoApplications 2010: European Conference on the Applications of Evolutionary Computation

Cite this