MLNet: Multi-level Classification Network

The point cloud classification network only uses point cloud structure features or edge features to construct the feature vector, so that the classification accuracy is low. To solve this problem, this paper proposes a multi-level classification network. First, the original point cloud is divided in...

Full description

Saved in:
Bibliographic Details
Published in:Journal of physics. Conference series 2021-01, Vol.1748 (3), p.32038
Main Authors: Xue, Doudou, Cheng, Yinglei, Wen, Pei, Zhang, Liyin
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
Artificial neural networks
Classification
Construction
Feature extraction
Machine learning
Physics
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The point cloud classification network only uses point cloud structure features or edge features to construct the feature vector, so that the classification accuracy is low. To solve this problem, this paper proposes a multi-level classification network. First, the original point cloud is divided into small samples using the preprocessing algorithm to obtain batch input and improve training efficiency; then construct structural features and edge features for point cloud feature extraction, and obtain local fine-grained descriptions through multi-level expressions within and between points; then design a convolutional neural network for feature learning. With the deepening of the network level, the degree of feature abstraction level is higher and higher, and the degree of distinction increases, so as to effectively improve the accuracy. Using the Vaihingen dataset to test the MLMS-Net network, the accuracy rate reached 85.4%.
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/1748/3/032038