Land Cover Classification from Hyperspectral Images via Local Nearest Neighbor Collaborative Representation with Tikhonov Regularization
The accurate and timely monitoring of land cover types is of great significance for the scientific planning, rational utilization, effective protection and management of land resources. In recent years, land cover classification based on hyperspectral images and the collaborative representation (CR)...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Land |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-445X/11/5/702 |
| _version_ | 1797498513223843840 |
|---|---|
| author | Rongchao Yang Qingbo Zhou Beilei Fan Yuting Wang |
| author_facet | Rongchao Yang Qingbo Zhou Beilei Fan Yuting Wang |
| author_sort | Rongchao Yang |
| collection | DOAJ |
| description | The accurate and timely monitoring of land cover types is of great significance for the scientific planning, rational utilization, effective protection and management of land resources. In recent years, land cover classification based on hyperspectral images and the collaborative representation (CR) model has become a hot topic in the field of remote sensing. However, most of the existing CR models do not consider the problem of sample imbalance, which affects the classification performance of CR models. In addition, the Tikhonov regularization term can improve the classification performance of CR models, but greatly increases the computational complexity of CR models. To address the above problems, a local nearest neighbor (LNN) method is proposed in this paper to select the same number of nearest neighbor samples from each nearest class of the test sample to construct a dictionary. This is then introduced into the original collaborative representation classification (CRC) method and CRC with Tikhonov regularization (CRT) for land cover classification, denoted as LNNCRC and LNNCRT, respectively. To verify the effectiveness of the proposed LNNCRC and LNNCRT methods, the classification performance and running time of the proposed methods are compared with those of six popular CR models on a hyperspectral scene with nine land cover types. The experimental results show that the proposed LNNCRT method achieves the best land cover classification performance, and the proposed LNNCRC and LNNCRT methods not only further exclude the interference of irrelevant training samples and classes, but also effectively eliminate the influence of imbalanced training samples, so as to improve the classification performance of CR models and effectively reduce the computational complexity of CR models. |
| first_indexed | 2024-03-10T03:34:23Z |
| format | Article |
| id | doaj.art-0daf4c70cdcd483d806c06db4e4ed5c7 |
| institution | Directory Open Access Journal |
| issn | 2073-445X |
| language | English |
| last_indexed | 2024-03-10T03:34:23Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Land |
| spelling | doaj.art-0daf4c70cdcd483d806c06db4e4ed5c72023-11-23T11:47:41ZengMDPI AGLand2073-445X2022-05-0111570210.3390/land11050702Land Cover Classification from Hyperspectral Images via Local Nearest Neighbor Collaborative Representation with Tikhonov RegularizationRongchao Yang0Qingbo Zhou1Beilei Fan2Yuting Wang3Agricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaAgricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaAgricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaAgricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaThe accurate and timely monitoring of land cover types is of great significance for the scientific planning, rational utilization, effective protection and management of land resources. In recent years, land cover classification based on hyperspectral images and the collaborative representation (CR) model has become a hot topic in the field of remote sensing. However, most of the existing CR models do not consider the problem of sample imbalance, which affects the classification performance of CR models. In addition, the Tikhonov regularization term can improve the classification performance of CR models, but greatly increases the computational complexity of CR models. To address the above problems, a local nearest neighbor (LNN) method is proposed in this paper to select the same number of nearest neighbor samples from each nearest class of the test sample to construct a dictionary. This is then introduced into the original collaborative representation classification (CRC) method and CRC with Tikhonov regularization (CRT) for land cover classification, denoted as LNNCRC and LNNCRT, respectively. To verify the effectiveness of the proposed LNNCRC and LNNCRT methods, the classification performance and running time of the proposed methods are compared with those of six popular CR models on a hyperspectral scene with nine land cover types. The experimental results show that the proposed LNNCRT method achieves the best land cover classification performance, and the proposed LNNCRC and LNNCRT methods not only further exclude the interference of irrelevant training samples and classes, but also effectively eliminate the influence of imbalanced training samples, so as to improve the classification performance of CR models and effectively reduce the computational complexity of CR models.https://www.mdpi.com/2073-445X/11/5/702land cover classificationhyperspectral imagescollaborative representationsample imbalancelocal nearest neighbors |
| spellingShingle | Rongchao Yang Qingbo Zhou Beilei Fan Yuting Wang Land Cover Classification from Hyperspectral Images via Local Nearest Neighbor Collaborative Representation with Tikhonov Regularization Land land cover classification hyperspectral images collaborative representation sample imbalance local nearest neighbors |
| title | Land Cover Classification from Hyperspectral Images via Local Nearest Neighbor Collaborative Representation with Tikhonov Regularization |
| title_full | Land Cover Classification from Hyperspectral Images via Local Nearest Neighbor Collaborative Representation with Tikhonov Regularization |
| title_fullStr | Land Cover Classification from Hyperspectral Images via Local Nearest Neighbor Collaborative Representation with Tikhonov Regularization |
| title_full_unstemmed | Land Cover Classification from Hyperspectral Images via Local Nearest Neighbor Collaborative Representation with Tikhonov Regularization |
| title_short | Land Cover Classification from Hyperspectral Images via Local Nearest Neighbor Collaborative Representation with Tikhonov Regularization |
| title_sort | land cover classification from hyperspectral images via local nearest neighbor collaborative representation with tikhonov regularization |
| topic | land cover classification hyperspectral images collaborative representation sample imbalance local nearest neighbors |
| url | https://www.mdpi.com/2073-445X/11/5/702 |
| work_keys_str_mv | AT rongchaoyang landcoverclassificationfromhyperspectralimagesvialocalnearestneighborcollaborativerepresentationwithtikhonovregularization AT qingbozhou landcoverclassificationfromhyperspectralimagesvialocalnearestneighborcollaborativerepresentationwithtikhonovregularization AT beileifan landcoverclassificationfromhyperspectralimagesvialocalnearestneighborcollaborativerepresentationwithtikhonovregularization AT yutingwang landcoverclassificationfromhyperspectralimagesvialocalnearestneighborcollaborativerepresentationwithtikhonovregularization |