У раду је представљена картографска обрада Landsat ТМ слике помоћу две ненадгледане методе класификације SAGA GIS: ISODATA и К-mean груписање. Приступи су тестирани и упоређени за мапирање типова земљишног покривача. Подручја вегетације откривена су и одвојена од осталих врста земљишног покривача у истраживаном подручју југозападног Исланда. Број кластера постављен је на десет класа. Обрада сателитске слике помоћу SAGA GIS постигнута је помоћу алата за класификацију слика у менију за геопроцесирање SAGA GIS. Ненадгледана класификација је била ефикасна у необележеним пикселима за типове покривача земљишта користећи машинско учење у GIS-у. Следећи итеративни приступ кластерисања, пиксели су груписани у сваком кораку алгоритма и кластери су поново додељени као центроиди. Рад доприноси техничком развоју примене машинског учења у картографији показујући ефикасност SAGA GIS у обради података даљинским испитивањем примењеним за мапирање вегетације и животне средине.
The paper presents the cartographic processing of the Landsat TM image by the two unsupervised classification methods of SAGA GIS: ISODATA and K-means clustering. The approaches were tested and compared for land cover type mapping. Vegetation areas were detected and separated from other land cover types in the study area of southwestern Iceland. The number of clusters was set to ten classes. The processing of the satellite image by SAGA GIS was achieved using Imagery Classification tools in the Geoprocessing menu of SAGA GIS. Unsupervised classification performed effectively in the unlabeled pixels for the land cover types using machine learning in GIS. Following an iterative approach of clustering, the pixels were grouped in each step of the algorithm and the clusters were reassigned as centroids. The paper contributes to the technical development of the application of machine learning in cartography by demonstrating the effectiveness of SAGA GIS in remote sensing data processing applied for vegetation and environmental mapping.
Lemenkova, P. (2021). Evaluating land cover types from Landsat TM using SAGA GIS for vegetation mapping based on ISODATA and K-means clustering. ACTA AGRICULTURAE SERBICA, 26(52), 159-165 [10.5937/aaser2152159l].
Evaluating land cover types from Landsat TM using SAGA GIS for vegetation mapping based on ISODATA and K-means clustering
Lemenkova, Polina
Primo
2021
Abstract
The paper presents the cartographic processing of the Landsat TM image by the two unsupervised classification methods of SAGA GIS: ISODATA and K-means clustering. The approaches were tested and compared for land cover type mapping. Vegetation areas were detected and separated from other land cover types in the study area of southwestern Iceland. The number of clusters was set to ten classes. The processing of the satellite image by SAGA GIS was achieved using Imagery Classification tools in the Geoprocessing menu of SAGA GIS. Unsupervised classification performed effectively in the unlabeled pixels for the land cover types using machine learning in GIS. Following an iterative approach of clustering, the pixels were grouped in each step of the algorithm and the clusters were reassigned as centroids. The paper contributes to the technical development of the application of machine learning in cartography by demonstrating the effectiveness of SAGA GIS in remote sensing data processing applied for vegetation and environmental mapping.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
