Combining Landsat and ALOS Data for Land Cover Mapping
Saygin Abdikan, Mustafa Ustuner, Fusun Balik Sanli, Gokhan Bilgin, None None
proceeding (Uluslararası, Hakemli) | Yazar(lar): Saygin Abdikan, Mustafa Ustuner, Fusun Balik Sanli, Gokhan Bilgin, None None | Yıl: 2017 | Dergi/Kurum: 2017 25TH SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE (SIU) | İndeks: WOS.ISTP | Anahtar Kelimeler: Landsat, ALOS, land cover, image classification —
In this study, L-band ALOS PALSAR radar satellite image and Landsat TM optical satellite image were used to investigate the contribution of radar satellite image to optical satellite image for land cover mapping. Dual-polarimetric data of ALOS satellite and also normalized difference vegetation index (NDVI) generated from Landsat image were used for the analysis. In addition, different classification techniques were taken into consideration and forest dominated land cover maps were produced and the results were compared. Random Forest (RF), k-Nearest Neighbors (k-NN) and Support Vector Machines (SVM) approaches were applied as image classification techniques. While the best result among the methods is DVM, the data set in which combined data arc used gives the best general accuracy result.