Cargando…

Feature Selection Method Based on High-Resolution Remote Sensing Images and the Effect of Sensitive Features on Classification Accuracy

With the advent of high spatial resolution remote sensing imagery, numerous image features can be utilized. Applying a reasonable feature selection approach is critical to effectively reduce feature redundancy and improve the efficiency and accuracy of classification. This paper proposes a novel fea...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhou, Yi, Zhang, Rui, Wang, Shixin, Wang, Futao
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2018
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6068868/
https://www.ncbi.nlm.nih.gov/pubmed/29932436
http://dx.doi.org/10.3390/s18072013
_version_ 1783343365347082240
author Zhou, Yi
Zhang, Rui
Wang, Shixin
Wang, Futao
author_facet Zhou, Yi
Zhang, Rui
Wang, Shixin
Wang, Futao
author_sort Zhou, Yi
collection PubMed
description With the advent of high spatial resolution remote sensing imagery, numerous image features can be utilized. Applying a reasonable feature selection approach is critical to effectively reduce feature redundancy and improve the efficiency and accuracy of classification. This paper proposes a novel feature selection approach, in which ReliefF, genetic algorithm, and support vector machine (RFGASVM) are integrated to extract buildings. We adopt the ReliefF algorithm to preliminary filter high-dimensional features in the feature database. After eliminating the sorted features, the feature subset and the C and γ parameters of support vector machine (SVM) are encoded into the chromosome of the genetic algorithm. A fitness function is constructed considering the sample identification accuracy, the number of selected features, and the feature cost. The proposed method was applied to high-resolution images obtained from different sensors, GF-2, BJ-2, and unmanned aerial vehicles (UAV). The confusion matrix, precision, recall and F1-score were applied to assess the accuracy. The results showed that the proposed method achieved feature reduction, and the overall accuracy (OA) was more than 85%, with Kappa coefficient values of 0.80, 0.83 and 0.85, respectively. The precision of each image was more than 85%. The time efficiency of the proposed method was two-fold greater than SVM with all the features. The RFGASVM method has the advantages of large feature reduction and high extraction performance and can be applied in feature selection.
format Online
Article
Text
id pubmed-6068868
institution National Center for Biotechnology Information
language English
publishDate 2018
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-60688682018-08-07 Feature Selection Method Based on High-Resolution Remote Sensing Images and the Effect of Sensitive Features on Classification Accuracy Zhou, Yi Zhang, Rui Wang, Shixin Wang, Futao Sensors (Basel) Article With the advent of high spatial resolution remote sensing imagery, numerous image features can be utilized. Applying a reasonable feature selection approach is critical to effectively reduce feature redundancy and improve the efficiency and accuracy of classification. This paper proposes a novel feature selection approach, in which ReliefF, genetic algorithm, and support vector machine (RFGASVM) are integrated to extract buildings. We adopt the ReliefF algorithm to preliminary filter high-dimensional features in the feature database. After eliminating the sorted features, the feature subset and the C and γ parameters of support vector machine (SVM) are encoded into the chromosome of the genetic algorithm. A fitness function is constructed considering the sample identification accuracy, the number of selected features, and the feature cost. The proposed method was applied to high-resolution images obtained from different sensors, GF-2, BJ-2, and unmanned aerial vehicles (UAV). The confusion matrix, precision, recall and F1-score were applied to assess the accuracy. The results showed that the proposed method achieved feature reduction, and the overall accuracy (OA) was more than 85%, with Kappa coefficient values of 0.80, 0.83 and 0.85, respectively. The precision of each image was more than 85%. The time efficiency of the proposed method was two-fold greater than SVM with all the features. The RFGASVM method has the advantages of large feature reduction and high extraction performance and can be applied in feature selection. MDPI 2018-06-22 /pmc/articles/PMC6068868/ /pubmed/29932436 http://dx.doi.org/10.3390/s18072013 Text en © 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Zhou, Yi
Zhang, Rui
Wang, Shixin
Wang, Futao
Feature Selection Method Based on High-Resolution Remote Sensing Images and the Effect of Sensitive Features on Classification Accuracy
title Feature Selection Method Based on High-Resolution Remote Sensing Images and the Effect of Sensitive Features on Classification Accuracy
title_full Feature Selection Method Based on High-Resolution Remote Sensing Images and the Effect of Sensitive Features on Classification Accuracy
title_fullStr Feature Selection Method Based on High-Resolution Remote Sensing Images and the Effect of Sensitive Features on Classification Accuracy
title_full_unstemmed Feature Selection Method Based on High-Resolution Remote Sensing Images and the Effect of Sensitive Features on Classification Accuracy
title_short Feature Selection Method Based on High-Resolution Remote Sensing Images and the Effect of Sensitive Features on Classification Accuracy
title_sort feature selection method based on high-resolution remote sensing images and the effect of sensitive features on classification accuracy
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6068868/
https://www.ncbi.nlm.nih.gov/pubmed/29932436
http://dx.doi.org/10.3390/s18072013
work_keys_str_mv AT zhouyi featureselectionmethodbasedonhighresolutionremotesensingimagesandtheeffectofsensitivefeaturesonclassificationaccuracy
AT zhangrui featureselectionmethodbasedonhighresolutionremotesensingimagesandtheeffectofsensitivefeaturesonclassificationaccuracy
AT wangshixin featureselectionmethodbasedonhighresolutionremotesensingimagesandtheeffectofsensitivefeaturesonclassificationaccuracy
AT wangfutao featureselectionmethodbasedonhighresolutionremotesensingimagesandtheeffectofsensitivefeaturesonclassificationaccuracy