On the Contribution of Saliency in Visual Tracking

Iman Alikhani; Hamed Rezazadegan Tavakoli; Esa Rahtu; Jorma Laaksonen

On the Contribution of Saliency in Visual Tracking

Iman Alikhani, Hamed Rezazadegan Tavakoli, Esa Rahtu, Jorma Laaksonen

Tietotekniikan laitos

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussa › Conference article in proceedings › Scientific › vertaisarvioitu

Abstrakti

Visual target tracking is a long-standing problem in the domain of computer vision. There are numerous methods proposed over several years. A recent trend in visual tracking has been target representation and tracking using saliency models inspired by the attentive mechanism of the human. Motivated to investigate the usefulness of such target representation scheme, we study several target representation techniques for mean-shift tracking framework, where the feature space can include color, texture, saliency, and gradient orientation information. In particular, we study the usefulness of the joint distribution of color-texture, color-saliency, and color-orientation in comparison with the color distribution. The performance is evaluated using the visual object tracking (VOT) 2013 which provides a systematic mechanism and a database for the assessment of tracking algorithms. We summarize the results in terms of accuracy & robustness; and discuss the usefulness of saliency-based target t racking.

Alkuperäiskieli	Englanti
Otsikko	Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
Kustantaja	SciTePress
Sivut	17-21
Vuosikerta	4
ISBN (elektroninen)	978-989-758-175-5
Tila	Julkaistu - 2016
OKM-julkaisutyyppi	A4 Artikkeli konferenssijulkaisussa
Tapahtuma	Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Rome, Italia Kesto: 27 helmik. 2016 → 29 helmik. 2016 Konferenssinumero: 11

Conference

Conference	Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
Lyhennettä	VISIGRAPP
Maa/Alue	Italia
Kaupunki	Rome
Ajanjakso	27/02/2016 → 29/02/2016

Muut tiedostot ja linkit

http://www.scitepress.org/DigitalLibrary/PublicationsDetail.aspx?ID=lUQeFBQ0BJY=&t=1

Suomalainen laskennallisen päättelyn huippuyksikkö
Xu, Y., Rintanen, J., Kaski, S., Anwer, R., Parviainen, P., Soare, M., Vuollekoski, H., Rezazadegan Tavakoli, H., Peltola, T., Blomstedt, P., Puranen, S., Dutta, R., Gebser, M., Mononen, T., Bogaerts, B., Tasharrofi, S., Pesonen, H., Weinzierl, A. & Yang, Z.
01/01/2015 → 31/12/2017
Projekti: Academy of Finland: Other research funding

Science-IT
Mikko Hakala (Manager)
Perustieteiden korkeakoulu
Laitteistot/tilat: Facility

Siteeraa tätä

@inproceedings{55f7240a12d24c798baf89e37a7b615f,

title = "On the Contribution of Saliency in Visual Tracking",

abstract = "Visual target tracking is a long-standing problem in the domain of computer vision. There are numerous methods proposed over several years. A recent trend in visual tracking has been target representation and tracking using saliency models inspired by the attentive mechanism of the human. Motivated to investigate the usefulness of such target representation scheme, we study several target representation techniques for mean-shift tracking framework, where the feature space can include color, texture, saliency, and gradient orientation information. In particular, we study the usefulness of the joint distribution of color-texture, color-saliency, and color-orientation in comparison with the color distribution. The performance is evaluated using the visual object tracking (VOT) 2013 which provides a systematic mechanism and a database for the assessment of tracking algorithms. We summarize the results in terms of accuracy & robustness; and discuss the usefulness of saliency-based target t racking.",

keywords = "saliency, mean-shift tracking, target representation",

author = "Iman Alikhani and {Rezazadegan Tavakoli}, Hamed and Esa Rahtu and Jorma Laaksonen",

year = "2016",

language = "English",

volume = "4",

pages = "17--21",

booktitle = "Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications",

publisher = "SciTePress",

address = "Portugal",

note = "Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP ; Conference date: 27-02-2016 Through 29-02-2016",

}

Alikhani, I, Rezazadegan Tavakoli, H, Rahtu, E & Laaksonen, J 2016, On the Contribution of Saliency in Visual Tracking. julkaisussa Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. Vuosikerta 4, SciTePress, Sivut 17-21, Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, Rome, Italia, 27/02/2016.

On the Contribution of Saliency in Visual Tracking. / Alikhani, Iman; Rezazadegan Tavakoli, Hamed; Rahtu, Esa et al.
Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. Vuosikerta 4 SciTePress, 2016. s. 17-21.

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussa › Conference article in proceedings › Scientific › vertaisarvioitu

TY - GEN

T1 - On the Contribution of Saliency in Visual Tracking

AU - Alikhani, Iman

AU - Rezazadegan Tavakoli, Hamed

AU - Rahtu, Esa

AU - Laaksonen, Jorma

N1 - Conference code: 11

PY - 2016

Y1 - 2016

N2 - Visual target tracking is a long-standing problem in the domain of computer vision. There are numerous methods proposed over several years. A recent trend in visual tracking has been target representation and tracking using saliency models inspired by the attentive mechanism of the human. Motivated to investigate the usefulness of such target representation scheme, we study several target representation techniques for mean-shift tracking framework, where the feature space can include color, texture, saliency, and gradient orientation information. In particular, we study the usefulness of the joint distribution of color-texture, color-saliency, and color-orientation in comparison with the color distribution. The performance is evaluated using the visual object tracking (VOT) 2013 which provides a systematic mechanism and a database for the assessment of tracking algorithms. We summarize the results in terms of accuracy & robustness; and discuss the usefulness of saliency-based target t racking.

AB - Visual target tracking is a long-standing problem in the domain of computer vision. There are numerous methods proposed over several years. A recent trend in visual tracking has been target representation and tracking using saliency models inspired by the attentive mechanism of the human. Motivated to investigate the usefulness of such target representation scheme, we study several target representation techniques for mean-shift tracking framework, where the feature space can include color, texture, saliency, and gradient orientation information. In particular, we study the usefulness of the joint distribution of color-texture, color-saliency, and color-orientation in comparison with the color distribution. The performance is evaluated using the visual object tracking (VOT) 2013 which provides a systematic mechanism and a database for the assessment of tracking algorithms. We summarize the results in terms of accuracy & robustness; and discuss the usefulness of saliency-based target t racking.

KW - saliency

KW - mean-shift tracking

KW - target representation

UR - http://www.scitepress.org/DigitalLibrary/PublicationsDetail.aspx?ID=lUQeFBQ0BJY=&t=1

M3 - Conference article in proceedings

VL - 4

SP - 17

EP - 21

BT - Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications

PB - SciTePress

T2 - Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications

Y2 - 27 February 2016 through 29 February 2016

ER -

On the Contribution of Saliency in Visual Tracking

Abstrakti

Conference

Muut tiedostot ja linkit

Sormenjälki

Projektit

Suomalainen laskennallisen päättelyn huippuyksikkö

Laitteet

Science-IT

Siteeraa tätä