A Superpixel Spatial Intuitionistic Fuzzy C-Means Clustering Algorithm for Unsupervised Classification of High Spatial Resolution Remote Sensing Images
This paper proposes a superpixel spatial intuitionistic fuzzy C-means (SSIFCM) clustering algorithm to address the problems of misclassification, salt and pepper noise, and classification uncertainty arising in the pixel-level unsupervised classification of high spatial resolution remote sensing (HS...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/14/3490 |
| _version_ | 1797443963293007872 |
|---|---|
| author | Xinran Ji Liang Huang Bo-Hui Tang Guokun Chen Feifei Cheng |
| author_facet | Xinran Ji Liang Huang Bo-Hui Tang Guokun Chen Feifei Cheng |
| author_sort | Xinran Ji |
| collection | DOAJ |
| description | This paper proposes a superpixel spatial intuitionistic fuzzy C-means (SSIFCM) clustering algorithm to address the problems of misclassification, salt and pepper noise, and classification uncertainty arising in the pixel-level unsupervised classification of high spatial resolution remote sensing (HSRRS) images. To reduce information redundancy and ensure noise immunity and image detail preservation, we first use a superpixel segmentation to obtain the local spatial information of the HSRRS image. Secondly, based on the bias-corrected fuzzy C-means (BCFCM) clustering algorithm, the superpixel spatial intuitionistic fuzzy membership matrix is constructed by counting an intuitionistic fuzzy set and spatial function. Finally, to minimize the classification uncertainty, the local relation between adjacent superpixels is used to obtain the classification results according to the spectral features of superpixels. Four HSRRS images of different scenes in the aerial image dataset (AID) are selected to analyze the classification performance, and fifteen main existing unsupervised classification algorithms are used to make inter-comparisons with the proposed SSIFCM algorithm. The results show that the overall accuracy and Kappa coefficients obtained by the proposed SSIFCM algorithm are the best within the inter-comparison of fifteen algorithms, which indicates that the SSIFCM algorithm can effectively improve the classification accuracy of HSRRS image. |
| first_indexed | 2024-03-09T13:04:43Z |
| format | Article |
| id | doaj.art-66a657d82a9c4ac093ba6b94cd4e8917 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T13:04:43Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-66a657d82a9c4ac093ba6b94cd4e89172023-11-30T21:50:01ZengMDPI AGRemote Sensing2072-42922022-07-011414349010.3390/rs14143490A Superpixel Spatial Intuitionistic Fuzzy C-Means Clustering Algorithm for Unsupervised Classification of High Spatial Resolution Remote Sensing ImagesXinran Ji0Liang Huang1Bo-Hui Tang2Guokun Chen3Feifei Cheng4Faculty of Land Resource Engineering, Kunming University of Science and Technology, Kunming 650093, ChinaFaculty of Land Resource Engineering, Kunming University of Science and Technology, Kunming 650093, ChinaFaculty of Land Resource Engineering, Kunming University of Science and Technology, Kunming 650093, ChinaFaculty of Land Resource Engineering, Kunming University of Science and Technology, Kunming 650093, ChinaFaculty of Land Resource Engineering, Kunming University of Science and Technology, Kunming 650093, ChinaThis paper proposes a superpixel spatial intuitionistic fuzzy C-means (SSIFCM) clustering algorithm to address the problems of misclassification, salt and pepper noise, and classification uncertainty arising in the pixel-level unsupervised classification of high spatial resolution remote sensing (HSRRS) images. To reduce information redundancy and ensure noise immunity and image detail preservation, we first use a superpixel segmentation to obtain the local spatial information of the HSRRS image. Secondly, based on the bias-corrected fuzzy C-means (BCFCM) clustering algorithm, the superpixel spatial intuitionistic fuzzy membership matrix is constructed by counting an intuitionistic fuzzy set and spatial function. Finally, to minimize the classification uncertainty, the local relation between adjacent superpixels is used to obtain the classification results according to the spectral features of superpixels. Four HSRRS images of different scenes in the aerial image dataset (AID) are selected to analyze the classification performance, and fifteen main existing unsupervised classification algorithms are used to make inter-comparisons with the proposed SSIFCM algorithm. The results show that the overall accuracy and Kappa coefficients obtained by the proposed SSIFCM algorithm are the best within the inter-comparison of fifteen algorithms, which indicates that the SSIFCM algorithm can effectively improve the classification accuracy of HSRRS image.https://www.mdpi.com/2072-4292/14/14/3490intuitionistic fuzzy C-means clusteringsuperpixelclassificationhigh spatial resolutionremote sensing image |
| spellingShingle | Xinran Ji Liang Huang Bo-Hui Tang Guokun Chen Feifei Cheng A Superpixel Spatial Intuitionistic Fuzzy C-Means Clustering Algorithm for Unsupervised Classification of High Spatial Resolution Remote Sensing Images Remote Sensing intuitionistic fuzzy C-means clustering superpixel classification high spatial resolution remote sensing image |
| title | A Superpixel Spatial Intuitionistic Fuzzy C-Means Clustering Algorithm for Unsupervised Classification of High Spatial Resolution Remote Sensing Images |
| title_full | A Superpixel Spatial Intuitionistic Fuzzy C-Means Clustering Algorithm for Unsupervised Classification of High Spatial Resolution Remote Sensing Images |
| title_fullStr | A Superpixel Spatial Intuitionistic Fuzzy C-Means Clustering Algorithm for Unsupervised Classification of High Spatial Resolution Remote Sensing Images |
| title_full_unstemmed | A Superpixel Spatial Intuitionistic Fuzzy C-Means Clustering Algorithm for Unsupervised Classification of High Spatial Resolution Remote Sensing Images |
| title_short | A Superpixel Spatial Intuitionistic Fuzzy C-Means Clustering Algorithm for Unsupervised Classification of High Spatial Resolution Remote Sensing Images |
| title_sort | superpixel spatial intuitionistic fuzzy c means clustering algorithm for unsupervised classification of high spatial resolution remote sensing images |
| topic | intuitionistic fuzzy C-means clustering superpixel classification high spatial resolution remote sensing image |
| url | https://www.mdpi.com/2072-4292/14/14/3490 |
| work_keys_str_mv | AT xinranji asuperpixelspatialintuitionisticfuzzycmeansclusteringalgorithmforunsupervisedclassificationofhighspatialresolutionremotesensingimages AT lianghuang asuperpixelspatialintuitionisticfuzzycmeansclusteringalgorithmforunsupervisedclassificationofhighspatialresolutionremotesensingimages AT bohuitang asuperpixelspatialintuitionisticfuzzycmeansclusteringalgorithmforunsupervisedclassificationofhighspatialresolutionremotesensingimages AT guokunchen asuperpixelspatialintuitionisticfuzzycmeansclusteringalgorithmforunsupervisedclassificationofhighspatialresolutionremotesensingimages AT feifeicheng asuperpixelspatialintuitionisticfuzzycmeansclusteringalgorithmforunsupervisedclassificationofhighspatialresolutionremotesensingimages AT xinranji superpixelspatialintuitionisticfuzzycmeansclusteringalgorithmforunsupervisedclassificationofhighspatialresolutionremotesensingimages AT lianghuang superpixelspatialintuitionisticfuzzycmeansclusteringalgorithmforunsupervisedclassificationofhighspatialresolutionremotesensingimages AT bohuitang superpixelspatialintuitionisticfuzzycmeansclusteringalgorithmforunsupervisedclassificationofhighspatialresolutionremotesensingimages AT guokunchen superpixelspatialintuitionisticfuzzycmeansclusteringalgorithmforunsupervisedclassificationofhighspatialresolutionremotesensingimages AT feifeicheng superpixelspatialintuitionisticfuzzycmeansclusteringalgorithmforunsupervisedclassificationofhighspatialresolutionremotesensingimages |