3DSliceLeNet: Recognizing 3D Objects Using a Slice-Representation

Francisco Gomez‐Donoso

doi:10.1109/ACCESS.2022.3148387

2022-01-01

Francisco Gomez‐Donoso

Félix Escalona *

Sergio Orts‐Escolano

Alberto García-García

José García‐Rodríguez

Miguel Cazorla

DOI：10.1109/ACCESS.2022.3148387

原文链接

原文求助

摘要

En 中文

Convolutional Neural Networks (CNNs) have become the default paradigm for addressing classification problems, especially, but not only, in image recognition. This is mainly due to their high success rate. Although a number of approaches currently apply deep learning to the 3D shape recognition problem, they are either too slow for online use or too error-prone. To fill this gap, we propose 3DSliceLeNet, a deep learning architecture for point cloud classification. Our proposal converts the input point clouds into a two-dimensional representation by performing a slicing process and projecting the points to the principal planes, thus generating images that are used by the convolutional architecture. 3DSliceLeNet successfully achieves both high accuracy and low computational cost. A dense set of experiments has been conducted to validate our system under the ModelNet challenge, a large-scale 3D Computer Aided Design (CAD) model dataset. Our proposal achieves a success rate of 94.37% and an Area under Curve (AUC) of 0.978 on the ModelNet-10 classification task.

Keyword:

Three-dimensional displays

Solid modeling

Convolutional neural networks

Shape

Feature extraction

Computational modeling

Task analysis

Deep learning

3D object recognition

convolutional neural networks

Caffe