A HYBRID HIGH RESOLUTION IMAGE CLASSIFICATION METHOD FOR MAPPINGEELGRASS DISTRIBUTIONS IN YAQUINA BAY ESTUARY, OREGON

摘要

False-color infrared (CIR) aerial photography of the Yaquina Bay Estuary, Oregon was acquiredat extreme low tides and digitally orthorectified with a ground pixel resolution of 20 cm toprovide data for intertidal vegetation mapping. Submerged, semi-exposed and exposed eelgrassmeadows and macroalgae beds were clearly imaged. Normalized Difference Vegetation Index(NDVI) derived algorithms were developed to classify eelgrass, macroalgae, and non-vegetatedareas at the pixel level and assessed at an overall accuracy of ～70%. This method proved to beeffective in distinguishing intertidal vegetation from non-vegetated areas but less so in separatingvegetation by genera or species. The NDVI derived algorithm was adjusted by individual imageand applied to all three bands resulting in a three band intertidal vegetation mosaiced image.The resulting image was reclassified into five statistically distinct classes using unsupervisedisoclustering and gridded into a raster GIS. A speckle reduction filter was applied to the resultinggrid which was re-tiled and vectorized. A photo-interpreter with orthophotography as anoverlay differentiated the vector polygons as eelgrass or macroalgae using software selectiontools. This method combines vegetation classification in digital image processing, computeraideddrawing in raster-to-vector conversion and photo-interpreter guidance to produce mapsless spatially generalized than manual methods and more accurately classified than automateddigital processing methods. Remotely sensed data derived with this hybrid classification methodhave promising uses in areas where data precision and accuracy are required such as in estuarineecological analyses and coastal resource management.