dc.contributor.author | Chen, Qiong | |
dc.contributor.author | Huang, Mengxing | |
dc.contributor.author | Wang, Hao | |
dc.date.accessioned | 2021-06-01T12:08:56Z | |
dc.date.available | 2021-06-01T12:08:56Z | |
dc.date.created | 2021-02-17T03:56:07Z | |
dc.date.issued | 2021 | |
dc.identifier.citation | IEEE Transactions on Geoscience and Remote Sensing. 2021, . | en_US |
dc.identifier.issn | 0196-2892 | |
dc.identifier.uri | https://hdl.handle.net/11250/2757233 | |
dc.description.abstract | Feature discretization is one of the most relevant techniques for data preprocessing in remote sensing research area. Its main goal is to transform the continuous features of images into discrete ones to improve the efficiency of intelligent image processing algorithms, thus helping experts to more easily understand and use the acquired remote sensing data. In this article, we focus on feature discretization for classification of high-resolution remote sensing images in coastal areas. In these images, interactions among multiple bands exist, noises interfere, and maritime domain-specific prior knowledge is difficult to get. To address these challenges, we propose a hybrid metric method, based on information entropy and chi-square test, to calculate the stability of the discrete interval and the similarity of adjacent intervals. In addition, we use the degree of dependence among knowledge from the rough set theory as the evaluation criterion for discretization schemes and then scan each band in turn with the strategy of first splitting then merging, to obtain the optimal set of discrete features. Our method has been compared with the best state-of-the-art discretization algorithms on the GF-2 and Landsat 8 satellite datasets. Experiments show that the proposed method achieves better classification accuracy for high-resolution remote sensing images in coastal areas. It can not only effectively mine the correlation between features but also filter the outliers in bands, thus producing as few discrete intervals as possible while ensuring data consistency. | en_US |
dc.language.iso | eng | en_US |
dc.publisher | IEEE | en_US |
dc.title | A Feature Discretization Method for Classification of High-Resolution Remote Sensing Images in Coastal Areas | en_US |
dc.type | Journal article | en_US |
dc.type | Peer reviewed | en_US |
dc.description.version | acceptedVersion | en_US |
dc.source.pagenumber | 15 | en_US |
dc.source.journal | IEEE Transactions on Geoscience and Remote Sensing | en_US |
dc.identifier.doi | 10.1109/TGRS.2020.3016526 | |
dc.identifier.cristin | 1890667 | |
dc.description.localcode | Publisher embargo applies until Febuary 15, 2023, © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes,creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | en_US |
cristin.ispublished | false | |
cristin.fulltext | postprint | |
cristin.qualitycode | 2 | |