Object classification from 3D volumetric data with 3D capsule networks

Burak Kakillioglu, Ayesha Ahmad, Senem Velipasalar

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The proliferation of 3D sensors induced 3D computer vision research for many application areas including virtual reality, autonomous navigation and surveillance. Recently, different methods have been proposed for 3D object classification. Many of the existing 2D and 3D classification methods rely on convolutional neural networks (CNNs), which are very successful in extracting features from the data. However, CNNs cannot sufficiently address the spatial relationship between features due to the max-pooling layers, and they require vast amount of training data. In this paper, we propose a model architecture for 3D object classification, which is an extension of Capsule Networks (CapsNets) to 3D data. Our proposed architecture called 3D CapsNet, takes advantage of the fact that a CapsNet preserves the orientation and spatial relationship of the extracted features, and thus requires less data to train the network. We compare our approach with ShapeNet on the ModelNet database, and show that our method provides performance improvement especially when training data size gets smaller.

Original languageEnglish (US)
Title of host publication2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages385-389
Number of pages5
ISBN (Electronic)9781728112954
DOIs
StatePublished - Feb 20 2019
Event2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Anaheim, United States
Duration: Nov 26 2018Nov 29 2018

Publication series

Name2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings

Conference

Conference2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018
CountryUnited States
CityAnaheim
Period11/26/1811/29/18

Fingerprint

Neural networks
Virtual reality
Computer vision
Navigation
Sensors

Keywords

  • 3D object
  • Capsule networks
  • Classification
  • Deep learning
  • Modelnet

ASJC Scopus subject areas

  • Information Systems
  • Signal Processing

Cite this

Kakillioglu, B., Ahmad, A., & Velipasalar, S. (2019). Object classification from 3D volumetric data with 3D capsule networks. In 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings (pp. 385-389). [8646333] (2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/GlobalSIP.2018.8646333

Object classification from 3D volumetric data with 3D capsule networks. / Kakillioglu, Burak; Ahmad, Ayesha; Velipasalar, Senem.

2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 385-389 8646333 (2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kakillioglu, B, Ahmad, A & Velipasalar, S 2019, Object classification from 3D volumetric data with 3D capsule networks. in 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings., 8646333, 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 385-389, 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018, Anaheim, United States, 11/26/18. https://doi.org/10.1109/GlobalSIP.2018.8646333
Kakillioglu B, Ahmad A, Velipasalar S. Object classification from 3D volumetric data with 3D capsule networks. In 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. p. 385-389. 8646333. (2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings). https://doi.org/10.1109/GlobalSIP.2018.8646333
Kakillioglu, Burak ; Ahmad, Ayesha ; Velipasalar, Senem. / Object classification from 3D volumetric data with 3D capsule networks. 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 385-389 (2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings).
@inproceedings{b43910f7d6fd42d0b56114b6468a0407,
title = "Object classification from 3D volumetric data with 3D capsule networks",
abstract = "The proliferation of 3D sensors induced 3D computer vision research for many application areas including virtual reality, autonomous navigation and surveillance. Recently, different methods have been proposed for 3D object classification. Many of the existing 2D and 3D classification methods rely on convolutional neural networks (CNNs), which are very successful in extracting features from the data. However, CNNs cannot sufficiently address the spatial relationship between features due to the max-pooling layers, and they require vast amount of training data. In this paper, we propose a model architecture for 3D object classification, which is an extension of Capsule Networks (CapsNets) to 3D data. Our proposed architecture called 3D CapsNet, takes advantage of the fact that a CapsNet preserves the orientation and spatial relationship of the extracted features, and thus requires less data to train the network. We compare our approach with ShapeNet on the ModelNet database, and show that our method provides performance improvement especially when training data size gets smaller.",
keywords = "3D object, Capsule networks, Classification, Deep learning, Modelnet",
author = "Burak Kakillioglu and Ayesha Ahmad and Senem Velipasalar",
year = "2019",
month = "2",
day = "20",
doi = "10.1109/GlobalSIP.2018.8646333",
language = "English (US)",
series = "2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "385--389",
booktitle = "2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings",

}

TY - GEN

T1 - Object classification from 3D volumetric data with 3D capsule networks

AU - Kakillioglu, Burak

AU - Ahmad, Ayesha

AU - Velipasalar, Senem

PY - 2019/2/20

Y1 - 2019/2/20

N2 - The proliferation of 3D sensors induced 3D computer vision research for many application areas including virtual reality, autonomous navigation and surveillance. Recently, different methods have been proposed for 3D object classification. Many of the existing 2D and 3D classification methods rely on convolutional neural networks (CNNs), which are very successful in extracting features from the data. However, CNNs cannot sufficiently address the spatial relationship between features due to the max-pooling layers, and they require vast amount of training data. In this paper, we propose a model architecture for 3D object classification, which is an extension of Capsule Networks (CapsNets) to 3D data. Our proposed architecture called 3D CapsNet, takes advantage of the fact that a CapsNet preserves the orientation and spatial relationship of the extracted features, and thus requires less data to train the network. We compare our approach with ShapeNet on the ModelNet database, and show that our method provides performance improvement especially when training data size gets smaller.

AB - The proliferation of 3D sensors induced 3D computer vision research for many application areas including virtual reality, autonomous navigation and surveillance. Recently, different methods have been proposed for 3D object classification. Many of the existing 2D and 3D classification methods rely on convolutional neural networks (CNNs), which are very successful in extracting features from the data. However, CNNs cannot sufficiently address the spatial relationship between features due to the max-pooling layers, and they require vast amount of training data. In this paper, we propose a model architecture for 3D object classification, which is an extension of Capsule Networks (CapsNets) to 3D data. Our proposed architecture called 3D CapsNet, takes advantage of the fact that a CapsNet preserves the orientation and spatial relationship of the extracted features, and thus requires less data to train the network. We compare our approach with ShapeNet on the ModelNet database, and show that our method provides performance improvement especially when training data size gets smaller.

KW - 3D object

KW - Capsule networks

KW - Classification

KW - Deep learning

KW - Modelnet

UR - http://www.scopus.com/inward/record.url?scp=85063086612&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063086612&partnerID=8YFLogxK

U2 - 10.1109/GlobalSIP.2018.8646333

DO - 10.1109/GlobalSIP.2018.8646333

M3 - Conference contribution

T3 - 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings

SP - 385

EP - 389

BT - 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -