Evaluating land cover types from Landsat TM using SAGA GIS for vegetation mapping based on ISODATA and K-means clustering

• Published in: Acta agriculturae Serbica
• Main Author: Lemenkova, Polina
• Other Authors: Ecole Polytechnique de Bruxelles, Université libre de Bruxelles (ULB)
• Format: Article in Journal/Newspaper
• Language: English
• Published: HAL CCSD 2021
• Subjects: SAGA GIS; mapping; vegetation; K-means; ISODATA; clustering; cartography; machine learning; ACM: I.: Computing Methodologies/I.4: IMAGE PROCESSING AND COMPUTER VISION; ACM: I.: Computing Methodologies/I.3: COMPUTER GRAPHICS; ACM: I.: Computing Methodologies/I.5: PATTERN RECOGNITION/I.5.3: Clustering/I.5.3.0: Algorithms; ACM: I.: Computing Methodologies/I.5: PATTERN RECOGNITION/I.5.3: Clustering/I.5.3.1: Similarity measures; ACM: I.: Computing Methodologies/I.4: IMAGE PROCESSING AND COMPUTER VISION/I.4.0: General; ACM: I.: Computing Methodologies/I.4: IMAGE PROCESSING AND COMPUTER VISION/I.4.10: Image Representation; ACM: I.: Computing Methodologies/I.4: IMAGE PROCESSING AND COMPUTER VISION/I.4.8: Scene Analysis; ACM: I.: Computing Methodologies/I.4: IMAGE PROCESSING AND COMPUTER VISION/I.4.8: Scene Analysis/I.4.8.0: Color; ACM: I.: Computing Methodologies/I.4: IMAGE PROCESSING AND COMPUTER VISION/I.4.8: Scene Analysis/I.4.8.3: Object recognition; ACM: I.: Computing Methodologies/I.5: PATTERN RECOGNITION; ACM: I.: Computing Methodologies/I.5: PATTERN RECOGNITION/I.5.3: Clustering; ACM: I.: Computing Methodologies/I.5: PATTERN RECOGNITION/I.5.2: Design Methodology; [INFO]Computer Science [cs]; [SDE]Environmental Sciences; [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR]; [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]; [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV]; [SDE.MCG]Environmental Sciences/Global Changes; [SDE.IE]Environmental Sciences/Environmental Engineering; [SDE.BE]Environmental Sciences/Biodiversity and Ecology; [SDU.STU]Sciences of the Universe [physics]/Earth Sciences; [SDV.BID]Life Sciences [q-bio]/Biodiversity; [SDV.EE]Life Sciences [q-bio]/Ecology; environment; [INFO.INFO-GR]Computer Science [cs]/Graphics [cs.GR]; [INFO.INFO-IA]Computer Science [cs]/Computer Aided Engineering; Iceland
• Online Access: https://hal.science/hal-03504862; https://hal.science/hal-03504862/document; https://hal.science/hal-03504862/file/9.%20AAS%20356-21%20Lemenkova.pdf; https://doi.org/10.5937/AASer2152159L

International audience 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.