IIIE   20352
INSTITUTO DE INVESTIGACIONES EN INGENIERIA ELECTRICA "ALFREDO DESAGES"
Unidad Ejecutora - UE
artículos
Título:
Methodology for classification of geographical features with remote sensing images: Application to tidal flats.
Autor/es:
PERILLO, M.M.; CIPOLLETTI, M.P.; PERILLO, G.M.E.; REVOLLO SARMIENTO, G.N.; DELRIEUX, C.A.
Revista:
GEOMORPHOLOGY
Editorial:
ELSEVIER SCIENCE BV
Referencias:
Lugar: Amsterdam; Año: 2016 vol. 257 p. 10 - 22
ISSN:
0169-555X
Resumen:
Tidal flats generally exhibit ponds of diverse size, shape, orientation and origin. Studying the genesis, evolution,stability and erosive mechanisms of these geographic features is critical to understand the dynamics of coastalwetlands. However, monitoring these locations through direct access is hard and expensive, not always feasible,and environmentally damaging. Processing remote sensing images is a natural alternative for the extraction ofqualitative and quantitative data due to their non-invasive nature. In this work, a robust methodology for automaticclassification of ponds and tidal creeks in tidal flats using Google Earth images is proposed. The applicabilityof our method is tested in nine zoneswith different morphological settings. Each zone is processed by a segmentationstage,where ponds and tidal creeks are identified. Next, each geographical feature is measured and a set ofshape descriptors is calculated. This dataset, together with a-priori classification of each geographical feature, isused to define a regression model, which allows an extensive automatic classification of large volumes of datadiscriminating ponds and tidal creeks against other various geographical features. In all cases, we identifiedand automatically classified different geographic features with an average accuracy over 90% (89.7% in theworst case, and 99.4% in the best case). These results show the feasibility of using freely available Google Earthimagery for the automatic identification and classification of complex geographical features. Also, the presentedmethodology may be easily applied in otherwetlands of the world and perhaps employing other remote sensingimagery.