International Journal of Remote Sensing · 1998 · 356 citations · 7 references
Natural SciencesGeographyPhysical GeographyCoastal GeographyForest EcologyRemote SensingLand Cover ClassificationLand Cover MappingMangrove EcologyRemote Sensing Image AnalysisRemote Sensing ImageryVegetation MonitoringClassification AccuracyClassification Accuracy AnalysisClassification Accuracy AssessmentMangrove MappingMangrove Remote SensingRemote Sensing Image ClassificationSatellite Image ClassificationVisual Interpretation
Abstract. Di erent approaches to the classi ® cation of remotely sensed data of mangroves are reviewed, and ® ve di erent methodologies identi ® ed. Landsat TM, SPOT XS and CASI data of mangroves from the Turks and Caicos Islands, were classi ® ed using each method. All classi ® cations of SPOT XS data failed to discriminate satisfactorily between mangrove and non-mangrove vegetation. Classi ® cation accuracy of CASI data was higher than Landsat TM for all methods, and more mangrove classes could be discriminated. Merging Landsat TM and SPOT XP data improved visual interpretation of images, but did not enhance discrimination of di erent mangrove categories. The most accurate combination of sensor and image processing method for mapping the mangroves of the eastern Caribbean islands is identi ® ed. 1.
7