Spectral Indexes Evaluation for Satellite Images Classification using CNN
Deep learning approaches are applied for a wide variety of problems, they are being used in the remote sensing field of study and showed high performance. Recent studies have demonstrated the efficiency of using spectral indexes in classification problems, because of accuracy and F1 score increasing...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
University of Zagreb, Faculty of organization and informatics
2021-01-01
|
| Series: | Journal of Information and Organizational Sciences |
| Subjects: | |
| Online Access: | https://hrcak.srce.hr/file/392385 |
| _version_ | 1827282102468476928 |
|---|---|
| author | Vladyslav Yaloveha Daria Hlavcheva Andrii Podorozhniak |
| author_facet | Vladyslav Yaloveha Daria Hlavcheva Andrii Podorozhniak |
| author_sort | Vladyslav Yaloveha |
| collection | DOAJ |
| description | Deep learning approaches are applied for a wide variety of problems, they are being used in the remote sensing field of study and showed high performance. Recent studies have demonstrated the efficiency of using spectral indexes in classification problems, because of accuracy and F1 score increasing in comparison with the usage of only RGB channels. The paper studies the problem of classification satellite images on the EuroSAT dataset using the proposed convolutional neural network. In the research set of the most used spectral indexes have been selected and calculated on the EuroSAT dataset. Then, a novel comparative analysis of spectral indexes was carried out. It has been established that the most significant set of indexes (NDVI, NDWI, GNDVI) increased classification accuracy from 64.72% to 84.19% and F1 score from 63.89% to 84.05%. The biggest improvement was obtained for River, Highway and PermanentCrop classes. |
| first_indexed | 2024-04-24T09:12:24Z |
| format | Article |
| id | doaj.art-359d9226ae70478fbc09073d13f7541f |
| institution | Directory Open Access Journal |
| issn | 1846-3312 1846-9418 |
| language | English |
| last_indexed | 2024-04-24T09:12:24Z |
| publishDate | 2021-01-01 |
| publisher | University of Zagreb, Faculty of organization and informatics |
| record_format | Article |
| series | Journal of Information and Organizational Sciences |
| spelling | doaj.art-359d9226ae70478fbc09073d13f7541f2024-04-15T17:29:58ZengUniversity of Zagreb, Faculty of organization and informaticsJournal of Information and Organizational Sciences1846-33121846-94182021-01-0145243544910.31341/jios.45.2.5Spectral Indexes Evaluation for Satellite Images Classification using CNNVladyslav Yaloveha0Daria Hlavcheva1Andrii Podorozhniak2Faculty of Computer and Information Technologies, National Technical University “KhPI”, Kharkiv, UkraineFaculty of Computer and Information Technologies, National Technical University “KhPI”, Kharkiv, UkraineFaculty of Computer and Information Technologies, National Technical University “KhPI”, Kharkiv, UkraineDeep learning approaches are applied for a wide variety of problems, they are being used in the remote sensing field of study and showed high performance. Recent studies have demonstrated the efficiency of using spectral indexes in classification problems, because of accuracy and F1 score increasing in comparison with the usage of only RGB channels. The paper studies the problem of classification satellite images on the EuroSAT dataset using the proposed convolutional neural network. In the research set of the most used spectral indexes have been selected and calculated on the EuroSAT dataset. Then, a novel comparative analysis of spectral indexes was carried out. It has been established that the most significant set of indexes (NDVI, NDWI, GNDVI) increased classification accuracy from 64.72% to 84.19% and F1 score from 63.89% to 84.05%. The biggest improvement was obtained for River, Highway and PermanentCrop classes.https://hrcak.srce.hr/file/392385Earth remote sensingdeep learningspectral indexesconvolutional neural networksEuroSAT |
| spellingShingle | Vladyslav Yaloveha Daria Hlavcheva Andrii Podorozhniak Spectral Indexes Evaluation for Satellite Images Classification using CNN Journal of Information and Organizational Sciences Earth remote sensing deep learning spectral indexes convolutional neural networks EuroSAT |
| title | Spectral Indexes Evaluation for Satellite Images Classification using CNN |
| title_full | Spectral Indexes Evaluation for Satellite Images Classification using CNN |
| title_fullStr | Spectral Indexes Evaluation for Satellite Images Classification using CNN |
| title_full_unstemmed | Spectral Indexes Evaluation for Satellite Images Classification using CNN |
| title_short | Spectral Indexes Evaluation for Satellite Images Classification using CNN |
| title_sort | spectral indexes evaluation for satellite images classification using cnn |
| topic | Earth remote sensing deep learning spectral indexes convolutional neural networks EuroSAT |
| url | https://hrcak.srce.hr/file/392385 |
| work_keys_str_mv | AT vladyslavyaloveha spectralindexesevaluationforsatelliteimagesclassificationusingcnn AT dariahlavcheva spectralindexesevaluationforsatelliteimagesclassificationusingcnn AT andriipodorozhniak spectralindexesevaluationforsatelliteimagesclassificationusingcnn |