Color-Based Point Cloud Classification Using a Novel Gaussian Mixed Modeling-Based Approach versus a Deep Neural Network
The classification of point clouds is an important research topic due to the increasing speed, accuracy, and detail of their acquisition. Classification using only color is basically absent in the literature; the few available papers provide only algorithms with limited usefulness (transformation of...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-12-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/16/1/115 |
_version_ | 1797358216197177344 |
---|---|
author | Martin Štroner Rudolf Urban Lenka Línková |
author_facet | Martin Štroner Rudolf Urban Lenka Línková |
author_sort | Martin Štroner |
collection | DOAJ |
description | The classification of point clouds is an important research topic due to the increasing speed, accuracy, and detail of their acquisition. Classification using only color is basically absent in the literature; the few available papers provide only algorithms with limited usefulness (transformation of three-dimensional color information to a one-dimensional one, such as intensity or vegetation indices). Here, we proposed two methods for classifying point clouds in RGB space (without using spatial information) and evaluated the classification success since it allows a computationally undemanding classification potentially applicable to a wide range of scenes. The first is based on Gaussian mixture modeling, modified to exploit specific properties of the RGB space (a finite number of integer combinations, with these combinations repeated in the same class) to automatically determine the number of spatial normal distributions needed to describe a class (mGMM). The other method is based on a deep neural network (DNN), for which different configurations (number of hidden layers and number of neurons in the layers) and different numbers of training subsets were tested. Real measured data from three sites with different numbers of classified classes and different “complexity” of classification in terms of color distinctiveness were used for testing. Classification success rates averaged 99.0% (accuracy) and 96.2% (balanced accuracy) for the mGMM method and averaged 97.3% and 96.7% (balanced accuracy) for the DNN method in terms of the best parameter combinations identified. |
first_indexed | 2024-03-08T14:58:40Z |
format | Article |
id | doaj.art-b5dd74825e7047dc84ee9a720a932f6c |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-08T14:58:40Z |
publishDate | 2023-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-b5dd74825e7047dc84ee9a720a932f6c2024-01-10T15:07:29ZengMDPI AGRemote Sensing2072-42922023-12-0116111510.3390/rs16010115Color-Based Point Cloud Classification Using a Novel Gaussian Mixed Modeling-Based Approach versus a Deep Neural NetworkMartin Štroner0Rudolf Urban1Lenka Línková2Department of Special Geodesy, Faculty of Civil Engineering, Czech Technical University in Prague, Thákurova 7, 166 29 Prague, Czech RepublicDepartment of Special Geodesy, Faculty of Civil Engineering, Czech Technical University in Prague, Thákurova 7, 166 29 Prague, Czech RepublicDepartment of Special Geodesy, Faculty of Civil Engineering, Czech Technical University in Prague, Thákurova 7, 166 29 Prague, Czech RepublicThe classification of point clouds is an important research topic due to the increasing speed, accuracy, and detail of their acquisition. Classification using only color is basically absent in the literature; the few available papers provide only algorithms with limited usefulness (transformation of three-dimensional color information to a one-dimensional one, such as intensity or vegetation indices). Here, we proposed two methods for classifying point clouds in RGB space (without using spatial information) and evaluated the classification success since it allows a computationally undemanding classification potentially applicable to a wide range of scenes. The first is based on Gaussian mixture modeling, modified to exploit specific properties of the RGB space (a finite number of integer combinations, with these combinations repeated in the same class) to automatically determine the number of spatial normal distributions needed to describe a class (mGMM). The other method is based on a deep neural network (DNN), for which different configurations (number of hidden layers and number of neurons in the layers) and different numbers of training subsets were tested. Real measured data from three sites with different numbers of classified classes and different “complexity” of classification in terms of color distinctiveness were used for testing. Classification success rates averaged 99.0% (accuracy) and 96.2% (balanced accuracy) for the mGMM method and averaged 97.3% and 96.7% (balanced accuracy) for the DNN method in terms of the best parameter combinations identified.https://www.mdpi.com/2072-4292/16/1/115point cloudclassificationcolordeep neural networkGaussian mixed modelmachine learning |
spellingShingle | Martin Štroner Rudolf Urban Lenka Línková Color-Based Point Cloud Classification Using a Novel Gaussian Mixed Modeling-Based Approach versus a Deep Neural Network Remote Sensing point cloud classification color deep neural network Gaussian mixed model machine learning |
title | Color-Based Point Cloud Classification Using a Novel Gaussian Mixed Modeling-Based Approach versus a Deep Neural Network |
title_full | Color-Based Point Cloud Classification Using a Novel Gaussian Mixed Modeling-Based Approach versus a Deep Neural Network |
title_fullStr | Color-Based Point Cloud Classification Using a Novel Gaussian Mixed Modeling-Based Approach versus a Deep Neural Network |
title_full_unstemmed | Color-Based Point Cloud Classification Using a Novel Gaussian Mixed Modeling-Based Approach versus a Deep Neural Network |
title_short | Color-Based Point Cloud Classification Using a Novel Gaussian Mixed Modeling-Based Approach versus a Deep Neural Network |
title_sort | color based point cloud classification using a novel gaussian mixed modeling based approach versus a deep neural network |
topic | point cloud classification color deep neural network Gaussian mixed model machine learning |
url | https://www.mdpi.com/2072-4292/16/1/115 |
work_keys_str_mv | AT martinstroner colorbasedpointcloudclassificationusinganovelgaussianmixedmodelingbasedapproachversusadeepneuralnetwork AT rudolfurban colorbasedpointcloudclassificationusinganovelgaussianmixedmodelingbasedapproachversusadeepneuralnetwork AT lenkalinkova colorbasedpointcloudclassificationusinganovelgaussianmixedmodelingbasedapproachversusadeepneuralnetwork |