NurbsNet: A Nurbs approach for 3d object recognition

Felix Escalona; Diego Viejo; Robert B. Fisher; Miguel Cazorla

doi:10.1109/IJCNN48605.2020.9207135

NurbsNet: A Nurbs approach for 3d object recognition

Felix Escalona, Diego Viejo, Robert B. Fisher, Miguel Cazorla

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

With the emergence of low cost 3D sensors, the focus is moving towards the recognition and scene understanding of tridimensional data. This kind of representation is really challenging in terms of computation, and it needs the development of new strategies and algorithms to be handled and interpreted.

In this work, we propose NurbsNet, a novel approach for 3D object classification based on local similarities with free form surfaces modeled as Nurbs.

The proposal has been tested in ModelNet10 and ModelNet40 with results that are promising with less training iterations than state-of-the-art methods and very low memory consumption.

Original language	English
Title of host publication	2020 International Joint Conference on Neural Networks (IJCNN)
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Number of pages	7
ISBN (Electronic)	978-1-7281-6926-2
ISBN (Print)	978-1-7281-6927-9
DOIs	https://doi.org/10.1109/IJCNN48605.2020.9207135
Publication status	Published - 28 Sep 2020
Event	The International Joint Conference on Neural Networks 2020 - Glasgow, United Kingdom Duration: 19 Jul 2020 → 24 Jul 2020 https://wcci2020.org/

Publication series

Name
Publisher	IEEE
ISSN (Print)	2161-4393
ISSN (Electronic)	2161-4407

Conference

Conference	The International Joint Conference on Neural Networks 2020
Abbreviated title	IJCNN 2020
Country	United Kingdom
City	Glasgow
Period	19/07/20 → 24/07/20
Internet address	https://wcci2020.org/

Keywords

3d object recognition
neural networks
Nurbs

Access to Document

10.1109/IJCNN48605.2020.9207135Licence: All Rights Reserved

NurbsNet_ESCALONA_DOA200320_AFVAccepted author manuscript, 709 KBLicence: All Rights Reserved

https://ieeexplore.ieee.org/document/9207135Licence: All Rights Reserved

Fingerprint Dive into the research topics of 'NurbsNet: A Nurbs approach for 3d object recognition'. Together they form a unique fingerprint.

Cite this

@inproceedings{d49250eb02394d759c4e8ead55ba82e6,

title = "NurbsNet: A Nurbs approach for 3d object recognition",

abstract = "With the emergence of low cost 3D sensors, the focus is moving towards the recognition and scene understanding of tridimensional data. This kind of representation is really challenging in terms of computation, and it needs the development of new strategies and algorithms to be handled and interpreted.In this work, we propose NurbsNet, a novel approach for 3D object classification based on local similarities with free form surfaces modeled as Nurbs.The proposal has been tested in ModelNet10 and ModelNet40 with results that are promising with less training iterations than state-of-the-art methods and very low memory consumption.",

keywords = "3d object recognition, neural networks, Nurbs",

author = "Felix Escalona and Diego Viejo and Fisher, {Robert B.} and Miguel Cazorla",

year = "2020",

month = sep,

day = "28",

doi = "10.1109/IJCNN48605.2020.9207135",

language = "English",

isbn = "978-1-7281-6927-9",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

booktitle = "2020 International Joint Conference on Neural Networks (IJCNN)",

address = "United States",

note = "The International Joint Conference on Neural Networks 2020, IJCNN 2020 ; Conference date: 19-07-2020 Through 24-07-2020",

url = "https://wcci2020.org/",

}

Escalona, F, Viejo, D, Fisher, RB & Cazorla, M 2020, NurbsNet: A Nurbs approach for 3d object recognition. in 2020 International Joint Conference on Neural Networks (IJCNN). Institute of Electrical and Electronics Engineers (IEEE), The International Joint Conference on Neural Networks 2020, Glasgow, United Kingdom, 19/07/20. https://doi.org/10.1109/IJCNN48605.2020.9207135

TY - GEN

T1 - NurbsNet: A Nurbs approach for 3d object recognition

AU - Escalona, Felix

AU - Viejo, Diego

AU - Fisher, Robert B.

AU - Cazorla, Miguel

PY - 2020/9/28

Y1 - 2020/9/28

N2 - With the emergence of low cost 3D sensors, the focus is moving towards the recognition and scene understanding of tridimensional data. This kind of representation is really challenging in terms of computation, and it needs the development of new strategies and algorithms to be handled and interpreted.In this work, we propose NurbsNet, a novel approach for 3D object classification based on local similarities with free form surfaces modeled as Nurbs.The proposal has been tested in ModelNet10 and ModelNet40 with results that are promising with less training iterations than state-of-the-art methods and very low memory consumption.

AB - With the emergence of low cost 3D sensors, the focus is moving towards the recognition and scene understanding of tridimensional data. This kind of representation is really challenging in terms of computation, and it needs the development of new strategies and algorithms to be handled and interpreted.In this work, we propose NurbsNet, a novel approach for 3D object classification based on local similarities with free form surfaces modeled as Nurbs.The proposal has been tested in ModelNet10 and ModelNet40 with results that are promising with less training iterations than state-of-the-art methods and very low memory consumption.

KW - 3d object recognition

KW - neural networks

KW - Nurbs

U2 - 10.1109/IJCNN48605.2020.9207135

DO - 10.1109/IJCNN48605.2020.9207135

M3 - Conference contribution

SN - 978-1-7281-6927-9

BT - 2020 International Joint Conference on Neural Networks (IJCNN)

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - The International Joint Conference on Neural Networks 2020

Y2 - 19 July 2020 through 24 July 2020

ER -