Can diversity amongst learners improve online object tracking?

Georg Nebehay, Walter Chibamu, Peter R. Lewis, Arjun Chandra, Roman Pflugfelder, Xin Yao

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present a novel analysis of the state of the art in object tracking with respect to diversity found in its main component, an ensemble classifier that is updated in an online manner. We employ established measures for diversity and performance from the rich literature on ensemble classification and online learning, and present a detailed evaluation of diversity and performance on benchmark sequences in order to gain an insight into how the tracking performance can be improved.
LanguageEnglish
Title of host publicationMultiple classifier systems
Subtitle of host publication11th International Workshop, MCS 2013, Nanjing, China, May 15-17, 2013. Proceedings
EditorsZhi-Hua Zhou, Fabio Roli, Josef Kittler
Place of PublicationBerlin (DE)
PublisherSpringer
Pages212-223
Number of pages12
ISBN (Electronic)978-3-642-38067-9
ISBN (Print)978-3-642-38066-2
DOIs
Publication statusPublished - 2013
Event11th international workshop on Multiple Classifier Systems - Nanjing, China
Duration: 15 May 201317 May 2013

Publication series

NameLecture notes in computer science
PublisherSpinger
Volume7872
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Workshop

Workshop11th international workshop on Multiple Classifier Systems
Abbreviated titleMCS 2013
CountryChina
CityNanjing
Period15/05/1317/05/13

Fingerprint

Classifiers

Cite this

Nebehay, G., Chibamu, W., Lewis, P. R., Chandra, A., Pflugfelder, R., & Yao, X. (2013). Can diversity amongst learners improve online object tracking? In Z-H. Zhou, F. Roli, & J. Kittler (Eds.), Multiple classifier systems: 11th International Workshop, MCS 2013, Nanjing, China, May 15-17, 2013. Proceedings (pp. 212-223). (Lecture notes in computer science; Vol. 7872). Berlin (DE): Springer. https://doi.org/10.1007/978-3-642-38067-9_19
Nebehay, Georg ; Chibamu, Walter ; Lewis, Peter R. ; Chandra, Arjun ; Pflugfelder, Roman ; Yao, Xin. / Can diversity amongst learners improve online object tracking?. Multiple classifier systems: 11th International Workshop, MCS 2013, Nanjing, China, May 15-17, 2013. Proceedings. editor / Zhi-Hua Zhou ; Fabio Roli ; Josef Kittler. Berlin (DE) : Springer, 2013. pp. 212-223 (Lecture notes in computer science).
@inproceedings{0f1145dbf4c44b6cae1f7cdb960218fe,
title = "Can diversity amongst learners improve online object tracking?",
abstract = "We present a novel analysis of the state of the art in object tracking with respect to diversity found in its main component, an ensemble classifier that is updated in an online manner. We employ established measures for diversity and performance from the rich literature on ensemble classification and online learning, and present a detailed evaluation of diversity and performance on benchmark sequences in order to gain an insight into how the tracking performance can be improved.",
author = "Georg Nebehay and Walter Chibamu and Lewis, {Peter R.} and Arjun Chandra and Roman Pflugfelder and Xin Yao",
year = "2013",
doi = "10.1007/978-3-642-38067-9_19",
language = "English",
isbn = "978-3-642-38066-2",
series = "Lecture notes in computer science",
publisher = "Springer",
pages = "212--223",
editor = "Zhi-Hua Zhou and Fabio Roli and Josef Kittler",
booktitle = "Multiple classifier systems",
address = "Germany",

}

Nebehay, G, Chibamu, W, Lewis, PR, Chandra, A, Pflugfelder, R & Yao, X 2013, Can diversity amongst learners improve online object tracking? in Z-H Zhou, F Roli & J Kittler (eds), Multiple classifier systems: 11th International Workshop, MCS 2013, Nanjing, China, May 15-17, 2013. Proceedings. Lecture notes in computer science, vol. 7872, Springer, Berlin (DE), pp. 212-223, 11th international workshop on Multiple Classifier Systems, Nanjing, China, 15/05/13. https://doi.org/10.1007/978-3-642-38067-9_19

Can diversity amongst learners improve online object tracking? / Nebehay, Georg; Chibamu, Walter; Lewis, Peter R.; Chandra, Arjun; Pflugfelder, Roman; Yao, Xin.

Multiple classifier systems: 11th International Workshop, MCS 2013, Nanjing, China, May 15-17, 2013. Proceedings. ed. / Zhi-Hua Zhou; Fabio Roli; Josef Kittler. Berlin (DE) : Springer, 2013. p. 212-223 (Lecture notes in computer science; Vol. 7872).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Can diversity amongst learners improve online object tracking?

AU - Nebehay, Georg

AU - Chibamu, Walter

AU - Lewis, Peter R.

AU - Chandra, Arjun

AU - Pflugfelder, Roman

AU - Yao, Xin

PY - 2013

Y1 - 2013

N2 - We present a novel analysis of the state of the art in object tracking with respect to diversity found in its main component, an ensemble classifier that is updated in an online manner. We employ established measures for diversity and performance from the rich literature on ensemble classification and online learning, and present a detailed evaluation of diversity and performance on benchmark sequences in order to gain an insight into how the tracking performance can be improved.

AB - We present a novel analysis of the state of the art in object tracking with respect to diversity found in its main component, an ensemble classifier that is updated in an online manner. We employ established measures for diversity and performance from the rich literature on ensemble classification and online learning, and present a detailed evaluation of diversity and performance on benchmark sequences in order to gain an insight into how the tracking performance can be improved.

UR - http://www.scopus.com/inward/record.url?scp=84892921779&partnerID=8YFLogxK

UR - http://link.springer.com/chapter/10.1007%2F978-3-642-38067-9_19

U2 - 10.1007/978-3-642-38067-9_19

DO - 10.1007/978-3-642-38067-9_19

M3 - Conference contribution

SN - 978-3-642-38066-2

T3 - Lecture notes in computer science

SP - 212

EP - 223

BT - Multiple classifier systems

A2 - Zhou, Zhi-Hua

A2 - Roli, Fabio

A2 - Kittler, Josef

PB - Springer

CY - Berlin (DE)

ER -

Nebehay G, Chibamu W, Lewis PR, Chandra A, Pflugfelder R, Yao X. Can diversity amongst learners improve online object tracking? In Zhou Z-H, Roli F, Kittler J, editors, Multiple classifier systems: 11th International Workshop, MCS 2013, Nanjing, China, May 15-17, 2013. Proceedings. Berlin (DE): Springer. 2013. p. 212-223. (Lecture notes in computer science). https://doi.org/10.1007/978-3-642-38067-9_19