Date of Award
Master of Science (MS)
Electrical Engineering and Computer Science
3D data, capsule networks, convolutional neural networks, deep learning, Neural networks, object recognition
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.
Ahmad, Ayesha, "Object Recognition in 3D data using Capsules" (2018). Theses - ALL. 195.