Study of the classification efficiency of difficult-to-distinguish vegetation types using hyperspectral data
The article is devoted to the effectiveness research of methods of controlled spectral and spectral-spatial classification of hyperspectral data. In particular, minimum distance, support vector machine, mahalanobis distance and maximum likelihood methods are considered on the example of vegetative c...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Samara National Research University
2019-06-01
|
| Series: | Компьютерная оптика |
| Subjects: | |
| Online Access: | http://computeroptics.smr.ru/KO/PDF/KO43-3/430315.pdf |
| _version_ | 1818027162487226368 |
|---|---|
| author | Sergey Borzov Mark Guryanov Oleg Potaturkin |
| author_facet | Sergey Borzov Mark Guryanov Oleg Potaturkin |
| author_sort | Sergey Borzov |
| collection | DOAJ |
| description | The article is devoted to the effectiveness research of methods of controlled spectral and spectral-spatial classification of hyperspectral data. In particular, minimum distance, support vector machine, mahalanobis distance and maximum likelihood methods are considered on the example of vegetative cover types differentiation. Significant attention is paid to studying the dependence of the accuracy of data classification with listed methods on the spectral features number and their selection method. The perspectivity of complex processing of spectral and spatial features, considering the correlation of close pixels, is demonstrated. The experimental results obtained with various methods of forming training sets are presented. |
| first_indexed | 2024-12-10T04:43:31Z |
| format | Article |
| id | doaj.art-deca4d354d284d959974f3f1456dde7c |
| institution | Directory Open Access Journal |
| issn | 0134-2452 2412-6179 |
| language | English |
| last_indexed | 2024-12-10T04:43:31Z |
| publishDate | 2019-06-01 |
| publisher | Samara National Research University |
| record_format | Article |
| series | Компьютерная оптика |
| spelling | doaj.art-deca4d354d284d959974f3f1456dde7c2022-12-22T02:01:48ZengSamara National Research UniversityКомпьютерная оптика0134-24522412-61792019-06-0143346447310.18287/2412-6179-2019-43-3-464-473Study of the classification efficiency of difficult-to-distinguish vegetation types using hyperspectral dataSergey Borzov0Mark Guryanov1Oleg Potaturkin2Institute of Automation and Electrometry of the Siberian Branch of the Russian Academy of Sciences, 630090, Novosibirsk Russia, Academician Koptyug ave. 1Institute of Automation and Electrometry of the Siberian Branch of the Russian Academy of Sciences, 630090, Novosibirsk Russia, Academician Koptyug ave. 1Institute of Automation and Electrometry of the Siberian Branch of the Russian Academy of Sciences, 630090, Novosibirsk Russia, Academician Koptyug ave. 1The article is devoted to the effectiveness research of methods of controlled spectral and spectral-spatial classification of hyperspectral data. In particular, minimum distance, support vector machine, mahalanobis distance and maximum likelihood methods are considered on the example of vegetative cover types differentiation. Significant attention is paid to studying the dependence of the accuracy of data classification with listed methods on the spectral features number and their selection method. The perspectivity of complex processing of spectral and spatial features, considering the correlation of close pixels, is demonstrated. The experimental results obtained with various methods of forming training sets are presented.http://computeroptics.smr.ru/KO/PDF/KO43-3/430315.pdfremote sensinghyperspectral imagescover types classificationspectral and spatial featuresimage processing |
| spellingShingle | Sergey Borzov Mark Guryanov Oleg Potaturkin Study of the classification efficiency of difficult-to-distinguish vegetation types using hyperspectral data Компьютерная оптика remote sensing hyperspectral images cover types classification spectral and spatial features image processing |
| title | Study of the classification efficiency of difficult-to-distinguish vegetation types using hyperspectral data |
| title_full | Study of the classification efficiency of difficult-to-distinguish vegetation types using hyperspectral data |
| title_fullStr | Study of the classification efficiency of difficult-to-distinguish vegetation types using hyperspectral data |
| title_full_unstemmed | Study of the classification efficiency of difficult-to-distinguish vegetation types using hyperspectral data |
| title_short | Study of the classification efficiency of difficult-to-distinguish vegetation types using hyperspectral data |
| title_sort | study of the classification efficiency of difficult to distinguish vegetation types using hyperspectral data |
| topic | remote sensing hyperspectral images cover types classification spectral and spatial features image processing |
| url | http://computeroptics.smr.ru/KO/PDF/KO43-3/430315.pdf |
| work_keys_str_mv | AT sergeyborzov studyoftheclassificationefficiencyofdifficulttodistinguishvegetationtypesusinghyperspectraldata AT markguryanov studyoftheclassificationefficiencyofdifficulttodistinguishvegetationtypesusinghyperspectraldata AT olegpotaturkin studyoftheclassificationefficiencyofdifficulttodistinguishvegetationtypesusinghyperspectraldata |