Feature-based tracking on a multi-omnidirectional camera dataset

Banş Evrim Demiröz; Ismail Ari; Orhan Eroǧlu; Albert Ali Salah; Laie Akarun

doi:10.1109/ISCCSP.2012.6217867

Feature-based tracking on a multi-omnidirectional camera dataset

Banş Evrim Demiröz, Ismail Ari, Orhan Eroǧlu, Albert Ali Salah, Laie Akarun

Bogazici University

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

Abstract

Omnidirectional cameras have a lot of potential for surveillance and ambient intelligence applications, since they provide increased coverage with fewer cameras. We introduce the new BOMNI dataset, collected with two omnidirectional cameras simultaneously. The dataset contains single subject and multi-subject interaction scenarios, as well as actions relevant for ambient assisted living, such as falling down. We describe evaluation protocols on this dataset, and provide benchmarking baseline results for two tracking systems based on bounding box and interest point matching after foreground-background segmentation, respectively.

Original language	English
Title of host publication	5th International Symposium on Communications Control and Signal Processing, ISCCSP 2012
DOIs	https://doi.org/10.1109/ISCCSP.2012.6217867
Publication status	Published - 27 Jul 2012
Event	5th International Symposium on Communications Control and Signal Processing, ISCCSP 2012 - Rome, Italy Duration: 2 May 2012 → 4 May 2012

Conference

Conference	5th International Symposium on Communications Control and Signal Processing, ISCCSP 2012
Country/Territory	Italy
City	Rome
Period	2/05/12 → 4/05/12

Keywords

AAL dataset
Image sequence analysis
Object tracking
Omnidirectional cameras
Video surveillance

Access to Document

10.1109/ISCCSP.2012.6217867

Cite this

@inproceedings{3bc988d0990e4f838c8913969eb8c8da,

title = "Feature-based tracking on a multi-omnidirectional camera dataset",

abstract = "Omnidirectional cameras have a lot of potential for surveillance and ambient intelligence applications, since they provide increased coverage with fewer cameras. We introduce the new BOMNI dataset, collected with two omnidirectional cameras simultaneously. The dataset contains single subject and multi-subject interaction scenarios, as well as actions relevant for ambient assisted living, such as falling down. We describe evaluation protocols on this dataset, and provide benchmarking baseline results for two tracking systems based on bounding box and interest point matching after foreground-background segmentation, respectively.",

keywords = "AAL dataset, Image sequence analysis, Object tracking, Omnidirectional cameras, Video surveillance",

author = "Demir{\"o}z, {Ban{\c s} Evrim} and Ismail Ari and Orhan Eroǧlu and Salah, {Albert Ali} and Laie Akarun",

year = "2012",

month = jul,

day = "27",

doi = "10.1109/ISCCSP.2012.6217867",

language = "English",

isbn = "9781467302760",

booktitle = "5th International Symposium on Communications Control and Signal Processing, ISCCSP 2012",

note = "5th International Symposium on Communications Control and Signal Processing, ISCCSP 2012 ; Conference date: 02-05-2012 Through 04-05-2012",

}

Demiröz, BE, Ari, I, Eroǧlu, O, Salah, AA & Akarun, L 2012, Feature-based tracking on a multi-omnidirectional camera dataset. in 5th International Symposium on Communications Control and Signal Processing, ISCCSP 2012., 6217867, 5th International Symposium on Communications Control and Signal Processing, ISCCSP 2012, Rome, Italy, 2/05/12. https://doi.org/10.1109/ISCCSP.2012.6217867

TY - GEN

T1 - Feature-based tracking on a multi-omnidirectional camera dataset

AU - Demiröz, Banş Evrim

AU - Ari, Ismail

AU - Eroǧlu, Orhan

AU - Salah, Albert Ali

AU - Akarun, Laie

PY - 2012/7/27

Y1 - 2012/7/27

N2 - Omnidirectional cameras have a lot of potential for surveillance and ambient intelligence applications, since they provide increased coverage with fewer cameras. We introduce the new BOMNI dataset, collected with two omnidirectional cameras simultaneously. The dataset contains single subject and multi-subject interaction scenarios, as well as actions relevant for ambient assisted living, such as falling down. We describe evaluation protocols on this dataset, and provide benchmarking baseline results for two tracking systems based on bounding box and interest point matching after foreground-background segmentation, respectively.

AB - Omnidirectional cameras have a lot of potential for surveillance and ambient intelligence applications, since they provide increased coverage with fewer cameras. We introduce the new BOMNI dataset, collected with two omnidirectional cameras simultaneously. The dataset contains single subject and multi-subject interaction scenarios, as well as actions relevant for ambient assisted living, such as falling down. We describe evaluation protocols on this dataset, and provide benchmarking baseline results for two tracking systems based on bounding box and interest point matching after foreground-background segmentation, respectively.

KW - AAL dataset

KW - Image sequence analysis

KW - Object tracking

KW - Omnidirectional cameras

KW - Video surveillance

UR - http://www.scopus.com/inward/record.url?scp=84864152692&partnerID=8YFLogxK

U2 - 10.1109/ISCCSP.2012.6217867

DO - 10.1109/ISCCSP.2012.6217867

M3 - Conference contribution

AN - SCOPUS:84864152692

SN - 9781467302760

BT - 5th International Symposium on Communications Control and Signal Processing, ISCCSP 2012

T2 - 5th International Symposium on Communications Control and Signal Processing, ISCCSP 2012

Y2 - 2 May 2012 through 4 May 2012

ER -

Feature-based tracking on a multi-omnidirectional camera dataset

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this