Tracking of Individuals in Very Long Video Sequences

Preben Fihl, Rasmus Corlin, Sangho Park, Thomas B. Moeslund, Mohan M. Trivedi

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

4 Citationer (Scopus)
307 Downloads (Pure)

Resumé

In this paper we present an approach for automatically detecting and tracking humans in very long video sequences. The detection is based on background subtraction using a multi-mode Codeword method. We enhance this method both in terms of representation and in terms of automatically updating the background allowing for handling gradual and rapid changes. Tracking is conducted by building appearance-based models and matching these over time. Tests show promising detection and tracking results in a ten hour video sequence.
OriginalsprogEngelsk
TitelAdvances in Visual Computing
Antal sider10
Vol/bindSpringer
ForlagSpringer
Publikationsdato2006
Sider60-69
ISBN (Trykt)9783540486282
StatusUdgivet - 2006
Begivenhed2nd International Symposium on Visual Computing - Lake Tahoe, USA
Varighed: 6 nov. 20068 nov. 2006
Konferencens nummer: 2

Konference

Konference2nd International Symposium on Visual Computing
Nummer2
LandUSA
ByLake Tahoe
Periode06/11/200608/11/2006
NavnLecture Notes in Computer Science
Nummer1
Vol/bind4291/2006
ISSN0302-9743

Citer dette

Fihl, P., Corlin, R., Park, S., Moeslund, T. B., & Trivedi, M. M. (2006). Tracking of Individuals in Very Long Video Sequences. I Advances in Visual Computing (Bind Springer, s. 60-69). Springer. Lecture Notes in Computer Science, Nr. 1, Bind. 4291/2006
Fihl, Preben ; Corlin, Rasmus ; Park, Sangho ; Moeslund, Thomas B. ; Trivedi, Mohan M. / Tracking of Individuals in Very Long Video Sequences. Advances in Visual Computing. Bind Springer Springer, 2006. s. 60-69 (Lecture Notes in Computer Science; Nr. 1, Bind 4291/2006).
@inproceedings{b8c5ef108a8311dbbb3d000ea68e967b,
title = "Tracking of Individuals in Very Long Video Sequences",
abstract = "In this paper we present an approach for automatically detecting and tracking humans in very long video sequences. The detection is based on background subtraction using a multi-mode Codeword method. We enhance this method both in terms of representation and in terms of automatically updating the background allowing for handling gradual and rapid changes. Tracking is conducted by building appearance-based models and matching these over time. Tests show promising detection and tracking results in a ten hour video sequence.",
author = "Preben Fihl and Rasmus Corlin and Sangho Park and Moeslund, {Thomas B.} and Trivedi, {Mohan M.}",
year = "2006",
language = "English",
isbn = "9783540486282",
volume = "Springer",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
number = "1",
pages = "60--69",
booktitle = "Advances in Visual Computing",
address = "Germany",

}

Fihl, P, Corlin, R, Park, S, Moeslund, TB & Trivedi, MM 2006, Tracking of Individuals in Very Long Video Sequences. i Advances in Visual Computing. bind Springer, Springer, Lecture Notes in Computer Science, nr. 1, bind 4291/2006, s. 60-69, 2nd International Symposium on Visual Computing, Lake Tahoe, USA, 06/11/2006.

Tracking of Individuals in Very Long Video Sequences. / Fihl, Preben; Corlin, Rasmus; Park, Sangho; Moeslund, Thomas B.; Trivedi, Mohan M.

Advances in Visual Computing. Bind Springer Springer, 2006. s. 60-69 (Lecture Notes in Computer Science; Nr. 1, Bind 4291/2006).

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

TY - GEN

T1 - Tracking of Individuals in Very Long Video Sequences

AU - Fihl, Preben

AU - Corlin, Rasmus

AU - Park, Sangho

AU - Moeslund, Thomas B.

AU - Trivedi, Mohan M.

PY - 2006

Y1 - 2006

N2 - In this paper we present an approach for automatically detecting and tracking humans in very long video sequences. The detection is based on background subtraction using a multi-mode Codeword method. We enhance this method both in terms of representation and in terms of automatically updating the background allowing for handling gradual and rapid changes. Tracking is conducted by building appearance-based models and matching these over time. Tests show promising detection and tracking results in a ten hour video sequence.

AB - In this paper we present an approach for automatically detecting and tracking humans in very long video sequences. The detection is based on background subtraction using a multi-mode Codeword method. We enhance this method both in terms of representation and in terms of automatically updating the background allowing for handling gradual and rapid changes. Tracking is conducted by building appearance-based models and matching these over time. Tests show promising detection and tracking results in a ten hour video sequence.

M3 - Article in proceeding

SN - 9783540486282

VL - Springer

T3 - Lecture Notes in Computer Science

SP - 60

EP - 69

BT - Advances in Visual Computing

PB - Springer

ER -

Fihl P, Corlin R, Park S, Moeslund TB, Trivedi MM. Tracking of Individuals in Very Long Video Sequences. I Advances in Visual Computing. Bind Springer. Springer. 2006. s. 60-69. (Lecture Notes in Computer Science; Nr. 1, Bind 4291/2006).