Content-adaptive pyramid representation for 3D object classification

Tsampikos Kounalakis; Nikolaos Boulgouris; Georgios Triantafyllidis

doi:10.1109/ICIP.2016.7532353

Content-adaptive pyramid representation for 3D object classification

Tsampikos Kounalakis, Nikolaos Boulgouris, Georgios Triantafyllidis

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

2 Citationer (Scopus)

Abstract

In this paper we introduce a novel representation for the classification of 3D images. Unlike most current approaches, our representation is not based on a fixed pyramid but adapts to image content and uses image regions instead of rectangular pyramid scales. Image characteristics, such as depth and color, are used for defining regions within images. Multiple region scales are formed in order to construct the proposed pyramid image representation. The proposed method achieves excellent results in comparison to conventional representations.

Originalsprog	Engelsk
Titel	IEEE International Conference on Image Processing (ICIP), 2016
Antal sider	4
Forlag	IEEE
Publikationsdato	28 sep. 2016
Sider	231-235
ISBN (Trykt)	978-1-4673-9962-3
ISBN (Elektronisk)	978-1-4673-9961-6
DOI	https://doi.org/10.1109/ICIP.2016.7532353
Status	Udgivet - 28 sep. 2016
Begivenhed	IEEE International Conference on Image Processing - Arizona, Phoenix, USA Varighed: 25 sep. 2016 → 28 sep. 2016 http://2016.ieeeicip.org/

Konference

Konference	IEEE International Conference on Image Processing
Lokation	Arizona
Land/Område	USA
By	Phoenix
Periode	25/09/2016 → 28/09/2016
Internetadresse	http://2016.ieeeicip.org/

Adgang til dokumentet

10.1109/ICIP.2016.7532353

AUB Link

Søg efter materialet i Aalborg Universitetsbiblioteks søgemaskine

Andre filer og links

http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7532353&isnumber=7532277

Citationsformater

@inproceedings{626bc6c24d5a482cb69a4a38a2e84c33,

title = "Content-adaptive pyramid representation for 3D object classification",

abstract = "In this paper we introduce a novel representation for the classification of 3D images. Unlike most current approaches, our representation is not based on a fixed pyramid but adapts to image content and uses image regions instead of rectangular pyramid scales. Image characteristics, such as depth and color, are used for defining regions within images. Multiple region scales are formed in order to construct the proposed pyramid image representation. The proposed method achieves excellent results in comparison to conventional representations.",

author = "Tsampikos Kounalakis and Nikolaos Boulgouris and Georgios Triantafyllidis",

year = "2016",

month = sep,

day = "28",

doi = "10.1109/ICIP.2016.7532353",

language = "English",

isbn = "978-1-4673-9962-3",

pages = "231--235",

booktitle = "IEEE International Conference on Image Processing (ICIP), 2016",

publisher = "IEEE",

address = "United States",

note = "IEEE International Conference on Image Processing , ICIP ; Conference date: 25-09-2016 Through 28-09-2016",

url = "http://2016.ieeeicip.org/",

}

TY - GEN

T1 - Content-adaptive pyramid representation for 3D object classification

AU - Kounalakis, Tsampikos

AU - Boulgouris, Nikolaos

AU - Triantafyllidis, Georgios

PY - 2016/9/28

Y1 - 2016/9/28

N2 - In this paper we introduce a novel representation for the classification of 3D images. Unlike most current approaches, our representation is not based on a fixed pyramid but adapts to image content and uses image regions instead of rectangular pyramid scales. Image characteristics, such as depth and color, are used for defining regions within images. Multiple region scales are formed in order to construct the proposed pyramid image representation. The proposed method achieves excellent results in comparison to conventional representations.

AB - In this paper we introduce a novel representation for the classification of 3D images. Unlike most current approaches, our representation is not based on a fixed pyramid but adapts to image content and uses image regions instead of rectangular pyramid scales. Image characteristics, such as depth and color, are used for defining regions within images. Multiple region scales are formed in order to construct the proposed pyramid image representation. The proposed method achieves excellent results in comparison to conventional representations.

UR - http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7532353&isnumber=7532277

U2 - 10.1109/ICIP.2016.7532353

DO - 10.1109/ICIP.2016.7532353

M3 - Article in proceeding

SN - 978-1-4673-9962-3

SP - 231

EP - 235

BT - IEEE International Conference on Image Processing (ICIP), 2016

PB - IEEE

T2 - IEEE International Conference on Image Processing

Y2 - 25 September 2016 through 28 September 2016

ER -

Content-adaptive pyramid representation for 3D object classification

Abstract

Konference

Adgang til dokumentet

AUB Link

Andre filer og links

Fingeraftryk

Citationsformater