Discrete Cosine Transform-Based Joint Spectral–Spatial Information Compression and Band-Correlation Calculation for Hyperspectral Feature Extraction
Prediction tasks over pixels in hyperspectral images (HSI) require careful effort to engineer the features used for learning a classifier. However, the generated classification map may suffer from an over-smoothing problem, which is manifested in significant differences from the original image in te...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/22/4270 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850267065974259712 |
|---|---|
| author | Ziqi Zhao Changbao Yang Zhongjun Qiu Qiong Wu |
| author_facet | Ziqi Zhao Changbao Yang Zhongjun Qiu Qiong Wu |
| author_sort | Ziqi Zhao |
| collection | DOAJ |
| description | Prediction tasks over pixels in hyperspectral images (HSI) require careful effort to engineer the features used for learning a classifier. However, the generated classification map may suffer from an over-smoothing problem, which is manifested in significant differences from the original image in terms of object boundaries and details. To address this over-smoothing problem, we designed a method for extracting spectral–spatial-band-correlation (SSBC) features. In SSBC features, joint spectral–spatial feature extraction is considered a discrete cosine transform-based information compression, where a flattening operation is used to avoid the high computational cost induced by the requirement of distillation from 3D images for joint spectral–spatial information. However, this process can yield extracted features with lost spectral information. We argue that increasing the spectral information in the extracted features is the key to addressing the over-smoothing problem in the classification map. Consequently, the normalized difference vegetation index and iron oxide are improved for HSI data in extracting band-correlation features as added spectral information because their calculations, involving two spectral bands, are not appropriate for the abundant spectral bands of HSI. Experimental results on four real HSI datasets show that the proposed features can significantly mitigate the over-smoothing problem, and the classification performance is comparable to that of state-of-the-art deep features. |
| format | Article |
| id | doaj-art-8bc8fbb59f314b818823a51a82a6ce2f |
| institution | OA Journals |
| issn | 2072-4292 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-8bc8fbb59f314b818823a51a82a6ce2f2025-08-20T01:53:57ZengMDPI AGRemote Sensing2072-42922024-11-011622427010.3390/rs16224270Discrete Cosine Transform-Based Joint Spectral–Spatial Information Compression and Band-Correlation Calculation for Hyperspectral Feature ExtractionZiqi Zhao0Changbao Yang1Zhongjun Qiu2Qiong Wu3College of Geo-Exploration Science and Technology, Jilin University, Changchun 130026, ChinaCollege of Geo-Exploration Science and Technology, Jilin University, Changchun 130026, ChinaJilin Institute of Water Resources and Hydropower Survey and Design, Changchun 130012, ChinaCollege of Geo-Exploration Science and Technology, Jilin University, Changchun 130026, ChinaPrediction tasks over pixels in hyperspectral images (HSI) require careful effort to engineer the features used for learning a classifier. However, the generated classification map may suffer from an over-smoothing problem, which is manifested in significant differences from the original image in terms of object boundaries and details. To address this over-smoothing problem, we designed a method for extracting spectral–spatial-band-correlation (SSBC) features. In SSBC features, joint spectral–spatial feature extraction is considered a discrete cosine transform-based information compression, where a flattening operation is used to avoid the high computational cost induced by the requirement of distillation from 3D images for joint spectral–spatial information. However, this process can yield extracted features with lost spectral information. We argue that increasing the spectral information in the extracted features is the key to addressing the over-smoothing problem in the classification map. Consequently, the normalized difference vegetation index and iron oxide are improved for HSI data in extracting band-correlation features as added spectral information because their calculations, involving two spectral bands, are not appropriate for the abundant spectral bands of HSI. Experimental results on four real HSI datasets show that the proposed features can significantly mitigate the over-smoothing problem, and the classification performance is comparable to that of state-of-the-art deep features.https://www.mdpi.com/2072-4292/16/22/4270hyperspectral imagefeature extractionjoint spectral–spatial informationband correlationover-smoothing |
| spellingShingle | Ziqi Zhao Changbao Yang Zhongjun Qiu Qiong Wu Discrete Cosine Transform-Based Joint Spectral–Spatial Information Compression and Band-Correlation Calculation for Hyperspectral Feature Extraction Remote Sensing hyperspectral image feature extraction joint spectral–spatial information band correlation over-smoothing |
| title | Discrete Cosine Transform-Based Joint Spectral–Spatial Information Compression and Band-Correlation Calculation for Hyperspectral Feature Extraction |
| title_full | Discrete Cosine Transform-Based Joint Spectral–Spatial Information Compression and Band-Correlation Calculation for Hyperspectral Feature Extraction |
| title_fullStr | Discrete Cosine Transform-Based Joint Spectral–Spatial Information Compression and Band-Correlation Calculation for Hyperspectral Feature Extraction |
| title_full_unstemmed | Discrete Cosine Transform-Based Joint Spectral–Spatial Information Compression and Band-Correlation Calculation for Hyperspectral Feature Extraction |
| title_short | Discrete Cosine Transform-Based Joint Spectral–Spatial Information Compression and Band-Correlation Calculation for Hyperspectral Feature Extraction |
| title_sort | discrete cosine transform based joint spectral spatial information compression and band correlation calculation for hyperspectral feature extraction |
| topic | hyperspectral image feature extraction joint spectral–spatial information band correlation over-smoothing |
| url | https://www.mdpi.com/2072-4292/16/22/4270 |
| work_keys_str_mv | AT ziqizhao discretecosinetransformbasedjointspectralspatialinformationcompressionandbandcorrelationcalculationforhyperspectralfeatureextraction AT changbaoyang discretecosinetransformbasedjointspectralspatialinformationcompressionandbandcorrelationcalculationforhyperspectralfeatureextraction AT zhongjunqiu discretecosinetransformbasedjointspectralspatialinformationcompressionandbandcorrelationcalculationforhyperspectralfeatureextraction AT qiongwu discretecosinetransformbasedjointspectralspatialinformationcompressionandbandcorrelationcalculationforhyperspectralfeatureextraction |