Unsupervised Capsule Networks of High-Dimension Point Clouds classification

by   Quanfeng Xu, et al.

Three-dimensional point clouds learning is widely applied, but the point clouds are still unable to deal with classification and recognition tasks satisfactorily in the cases of irregular geometric structures and high-dimensional space. In 3D space, point clouds tend to have regular Euclidean structure because of their density. On the contrary, due to the high dimensionality, the spatial structure of high-dimensional space is more complex, and point clouds are mostly presented in non-European structure. Furthermore, among current 3D point clouds classification algorithms, Canonical Capsules algorithm based on Euclidean distance is difficult to decompose and identify non-Euclidean structures effectively. Thus, aiming at the point clouds classification task of non-Euclidean structure in 3D and high-dimensional space, this paper refers to the LLE algorithm based on geodesic distance for optimizing and proposes the unsupervised algorithm of high-dimensional point clouds capsule. In this paper, the geometric features of point clouds are considered in the extraction process, so as to transform the high-dimensional non-Euclidean structure into a lower-dimensional Euclidean structure with retaining spatial geometric features. To verify the feasibility of the unsupervised algorithm of high-dimensional point clouds capsule, experiments are conducted in Swiss Roll dataset, point clouds MNIST dataset and point clouds LFW dataset. The results show that (1) non-Euclidean structures can be can effectively identified by this model in Swiss Roll dataset; (2) a significant unsupervised learning effect is realized in point clouds MNIST dataset. In conclusion, the high-dimensional point clouds capsule unsupervised algorithm proposed in this paper is conducive to expand the application scenarios of current point clouds classification and recognition tasks.


page 13

page 14

page 16

page 18


Learning point embedding for 3D data processing

Among 2D convolutional networks on point clouds, point-based approaches ...

Finding Singular Features

We present a method for finding high density, low-dimensional structures...

A Two-stage Classification Method for High-dimensional Data and Point Clouds

High-dimensional data classification is a fundamental task in machine le...

Multiscale geometric feature extraction for high-dimensional and non-Euclidean data with application

A method for extracting multiscale geometric features from a data cloud ...

Learning Compact Geometric Features

We present an approach to learning features that represent the local geo...

Three iterations of (d-1)-WL test distinguish non isometric clouds of d-dimensional points

The Weisfeiler–Lehman (WL) test is a fundamental iterative algorithm for...

Justlookup: One Millisecond Deep Feature Extraction for Point Clouds By Lookup Tables

Deep models are capable of fitting complex high dimensional functions wh...

Please sign up or login with your details

Forgot password? Click here to reset