Abstract
The purpose of the study was to compare performance of the classification methods, that are Rule Based (RB) classifier and Support Vector Machine (SVM), of Planetscope and Worldview-3 satellite images in order to produce land use / cover thematic maps. Six classes, which are deep water, shallow water, vegetation, agricultural area, soil and saline soil, were considered. After performing the classification process, accuracy assessment was employed based on the error matrices. The results showed that, both of the classification methods and satellite data were adequate to classify the area. Besides, classification accuracy was improved when Worldview-3 satellite and SVM method were used. The classification accuracies of RB classification of Planetscope and Worldview-3 were %87 and %94 respectively and the classification accuracies of SVM classification of Planetscope and Worldview-3 were %93 and %96 respectively.
| Original language | English |
|---|---|
| Pages (from-to) | 1887-1892 |
| Number of pages | 6 |
| Journal | International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives |
| Volume | 42 |
| Issue number | 2/W13 |
| DOIs | |
| Publication status | Published - 4 Jun 2019 |
| Event | 4th ISPRS Geospatial Week 2019 - Enschede, Netherlands Duration: 10 Jun 2019 → 14 Jun 2019 |
Bibliographical note
Publisher Copyright:© Authors 2019.
Funding
I would like to acknowledge the financial support of the Scientific and Technological Research Council of Turkey under project number TUBITAK-116Y142, and also Istanbul Technical University Scientific Projects Office (BAP) under project number MYL-2018-41650.
| Funders | Funder number |
|---|---|
| Istanbul Technical University Scientific Projects Office | |
| British Association for Psychopharmacology | MYL-2018-41650 |
| Türkiye Bilimsel ve Teknolojik Araştirma Kurumu | TUBITAK-116Y142 |
Keywords
- Land Use / Cover
- Machine Learning
- Object Based Classification
- Remote sensing
- Support Vector Machine