Date of Award

May 2018

Degree Name

Master of Science (MS)

Department

Electrical Engineering and Computer Science

Advisor(s)

Senem Velipasalar

Keywords

3D data, capsule networks, convolutional neural networks, deep learning, Neural networks, object recognition

Subject Categories

Engineering

Abstract

The proliferation of 3D sensors induced 3D computer vision research for many application areas including virtual reality, autonomous navigation and surveillance. Recently, dierent methods have been proposed for 3D object classication. Many of the existing 2D and 3D classication methods rely on convolutional neural networks (CNNs), which are very successful in extracting features from the data. However, CNNs cannot address the spatial relationship between features due to the max-pooling layers, and they require vast amount of data for training. In this work, we propose a model architecture for 3D object classication, 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 use ModelNet database, a comprehensive clean collection of 3D CAD models for objects, to train and test the 3D CapsNet model. We then compare our approach with ShapeNet, a deep belief network for object classication based on CNNs, and show that our method provides performance improvement especially when training data size gets smaller.

Access

Open Access

Included in

Engineering Commons

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.