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

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

2 Citations (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.

Original language	English
Title of host publication	IEEE International Conference on Image Processing (ICIP), 2016
Number of pages	4
Publisher	IEEE
Publication date	28 Sept 2016
Pages	231-235
ISBN (Print)	978-1-4673-9962-3
ISBN (Electronic)	978-1-4673-9961-6
DOIs	https://doi.org/10.1109/ICIP.2016.7532353
Publication status	Published - 28 Sept 2016
Event	IEEE International Conference on Image Processing - Arizona, Phoenix, United States Duration: 25 Sept 2016 → 28 Sept 2016 http://2016.ieeeicip.org/

Conference

Conference	IEEE International Conference on Image Processing
Location	Arizona
Country/Territory	United States
City	Phoenix
Period	25/09/2016 → 28/09/2016
Internet address	http://2016.ieeeicip.org/

Access to Document

10.1109/ICIP.2016.7532353

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

@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

Conference

Access to Document

AUB Link

Other files and links

Fingerprint

Cite this