Band Selection via Band Density Prominence Clustering for Hyperspectral Image Classification
Band clustering has been widely used for hyperspectral band selection (BS). However, selecting an appropriate band to represent a band cluster is a key issue. Density peak clustering (DPC) provides an effective means for this purpose, referred to as DPC-based BS (DPC-BS). It uses two indicators, clu...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/6/942 |
| _version_ | 1797239468966543360 |
|---|---|
| author | Chein-I Chang Yi-Mei Kuo Kenneth Yeonkong Ma |
| author_facet | Chein-I Chang Yi-Mei Kuo Kenneth Yeonkong Ma |
| author_sort | Chein-I Chang |
| collection | DOAJ |
| description | Band clustering has been widely used for hyperspectral band selection (BS). However, selecting an appropriate band to represent a band cluster is a key issue. Density peak clustering (DPC) provides an effective means for this purpose, referred to as DPC-based BS (DPC-BS). It uses two indicators, cluster density and cluster distance, to rank all bands for BS. This paper reinterprets cluster density and cluster distance as band local density (BLD) and band distance (BD) and also introduces a new concept called band prominence value (BPV) as a third indicator. Combining BLD and BD with BPV derives new band prioritization criteria for BS, which can extend the currently used DPC-BS to a new DPC-BS method referred to as band density prominence clustering (BDPC). By taking advantage of the three key indicators of BDPC, i.e., cut-off band distance <i>b<sub>c</sub></i>, <i>k</i> nearest neighboring-band local density, and BPV, two versions of BDPC can be derived called <i>b<sub>c</sub></i>-BDPC and <i>k</i>-BDPC, both of which are quite different from existing DPC-based BS methods in three aspects. One is that the parameter <i>b<sub>c</sub></i> of <i>b<sub>c</sub></i>-BDPC and the parameter <i>k</i> of <i>k</i>-BDPC can be automatically determined by the number of clusters and virtual dimensionality (VD), respectively. Another is that instead of using Euclidean distance, a spectral discrimination measure is used to calculate BD as well as inter-band correlation. The most important and significant aspect is a novel idea that combines BPV with BLD and BD to derive new band prioritization criteria for BS. Extensive experiments demonstrate that BDPC generally performs better than DPC-BS as well as many current state-of-the art BS methods. |
| first_indexed | 2024-04-24T17:52:01Z |
| format | Article |
| id | doaj.art-b8d30c7c2155471989d8f987a74b7281 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-04-24T17:52:01Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-b8d30c7c2155471989d8f987a74b72812024-03-27T14:02:26ZengMDPI AGRemote Sensing2072-42922024-03-0116694210.3390/rs16060942Band Selection via Band Density Prominence Clustering for Hyperspectral Image ClassificationChein-I Chang0Yi-Mei Kuo1Kenneth Yeonkong Ma2Center for Hyperspectral Imaging in Remote Sensing (CHIRS), Information and Technology College, Dalian Maritime University, Dalian 116026, ChinaRemote Sensing Signal and Image Processing Laboratory, Department of Computer Science and Electrical Engineering, University of Maryland, Baltimore County (UMBC), MD 21250, USARemote Sensing Signal and Image Processing Laboratory, Department of Computer Science and Electrical Engineering, University of Maryland, Baltimore County (UMBC), MD 21250, USABand clustering has been widely used for hyperspectral band selection (BS). However, selecting an appropriate band to represent a band cluster is a key issue. Density peak clustering (DPC) provides an effective means for this purpose, referred to as DPC-based BS (DPC-BS). It uses two indicators, cluster density and cluster distance, to rank all bands for BS. This paper reinterprets cluster density and cluster distance as band local density (BLD) and band distance (BD) and also introduces a new concept called band prominence value (BPV) as a third indicator. Combining BLD and BD with BPV derives new band prioritization criteria for BS, which can extend the currently used DPC-BS to a new DPC-BS method referred to as band density prominence clustering (BDPC). By taking advantage of the three key indicators of BDPC, i.e., cut-off band distance <i>b<sub>c</sub></i>, <i>k</i> nearest neighboring-band local density, and BPV, two versions of BDPC can be derived called <i>b<sub>c</sub></i>-BDPC and <i>k</i>-BDPC, both of which are quite different from existing DPC-based BS methods in three aspects. One is that the parameter <i>b<sub>c</sub></i> of <i>b<sub>c</sub></i>-BDPC and the parameter <i>k</i> of <i>k</i>-BDPC can be automatically determined by the number of clusters and virtual dimensionality (VD), respectively. Another is that instead of using Euclidean distance, a spectral discrimination measure is used to calculate BD as well as inter-band correlation. The most important and significant aspect is a novel idea that combines BPV with BLD and BD to derive new band prioritization criteria for BS. Extensive experiments demonstrate that BDPC generally performs better than DPC-BS as well as many current state-of-the art BS methods.https://www.mdpi.com/2072-4292/16/6/942band density prominent peak clustering (BDPC)band distance (BD)band local density (BLD)band prominence value (BPV)band selection (BS)hyperspectral image classification (HSIC) |
| spellingShingle | Chein-I Chang Yi-Mei Kuo Kenneth Yeonkong Ma Band Selection via Band Density Prominence Clustering for Hyperspectral Image Classification Remote Sensing band density prominent peak clustering (BDPC) band distance (BD) band local density (BLD) band prominence value (BPV) band selection (BS) hyperspectral image classification (HSIC) |
| title | Band Selection via Band Density Prominence Clustering for Hyperspectral Image Classification |
| title_full | Band Selection via Band Density Prominence Clustering for Hyperspectral Image Classification |
| title_fullStr | Band Selection via Band Density Prominence Clustering for Hyperspectral Image Classification |
| title_full_unstemmed | Band Selection via Band Density Prominence Clustering for Hyperspectral Image Classification |
| title_short | Band Selection via Band Density Prominence Clustering for Hyperspectral Image Classification |
| title_sort | band selection via band density prominence clustering for hyperspectral image classification |
| topic | band density prominent peak clustering (BDPC) band distance (BD) band local density (BLD) band prominence value (BPV) band selection (BS) hyperspectral image classification (HSIC) |
| url | https://www.mdpi.com/2072-4292/16/6/942 |
| work_keys_str_mv | AT cheinichang bandselectionviabanddensityprominenceclusteringforhyperspectralimageclassification AT yimeikuo bandselectionviabanddensityprominenceclusteringforhyperspectralimageclassification AT kennethyeonkongma bandselectionviabanddensityprominenceclusteringforhyperspectralimageclassification |