NormalNet: A voxel-based CNN for 3D object classification and retrieval

C. Wang; M. Cheng; F. Sohel; M. Bennamoun; J. Li

doi:10.1016/j.neucom.2018.09.075

Back

NormalNet: A voxel-based CNN for 3D object classification and retrieval

Journal article

Open access

Peer reviewed

NormalNet: A voxel-based CNN for 3D object classification and retrieval

C. Wang, M. Cheng, F. Sohel, M. Bennamoun and J. Li

Neurocomputing, Vol.323, pp.139-147

2018

DOI: https://doi.org/10.1016/j.neucom.2018.09.075

Files and links (2)

pdf

3D objects.pdfDownload View

Author’s Version Open Access

url

Link to Published Version *Subscription may be requiredView

Abstract

A common approach to tackle 3D object recognition tasks is to project 3D data to multiple 2D images. Projection only captures the outline of the object, and discards the internal information that may be crucial for the recognition. In this paper, we stay in 3D and concentrate on tapping the potential of 3D representations. We present NormalNet, a voxel-based convolutional neural network (CNN) designed for 3D object recognition. The network uses normal vectors of the object surfaces as input, which demonstrate stronger discrimination capability than binary voxels. We propose a reflection-convolution-concatenation (RCC) module to realize the conv layers, which extracts distinguishable features for 3D vision tasks while reducing the number of parameters significantly. We further improve the performance of NormalNet by combining two networks, which take normal vectors and voxels as input respectively. We carry out a series of experiments that validate the design of the network and achieve competitive performance in 3D object classification and retrieval tasks.

Details

Title: NormalNet: A voxel-based CNN for 3D object classification and retrieval
Authors/Creators: C. Wang (Author/Creator) - Xiamen University
M. Cheng (Author/Creator) - Xiamen University
F. Sohel (Author/Creator) - Murdoch University
M. Bennamoun (Author/Creator) - The University of Western Australia
J. Li (Author/Creator) - Xiamen University
Publication Details: Neurocomputing, Vol.323, pp.139-147
Publisher: Elsevier BV
Identifiers: 991005541454507891
Murdoch Affiliation: School of Engineering and Information Technology
Language: English
Resource Type: Journal article

Metrics

482 File views/ downloads

216 Record Views

119 Times Cited - Web of Science

InCites Highlights

These are selected metrics from InCites Benchmarking & Analytics tool, related to this output

Collaboration types: Domestic collaboration; International collaboration
Citation topics: 4 Electrical Engineering, Electronics & Computer Science; 4.17 Computer Vision & Graphics; 4.17.2798 Stereo Depth Estimation
Web Of Science research areas: Computer Science, Artificial Intelligence
ESI research areas: Computer Science