English   español  
Por favor, use este identificador para citar o enlazar a este item: http://hdl.handle.net/10261/111015
logo share SHARE   Add this article to your Mendeley library MendeleyBASE
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL
Exportar a otros formatos:

Application of the Dempster-Shafer theory to classify monocot and dicot weeds based on geometric shape descriptors

AutorHerrera Caro, Pedro Javier ; Dorado, José ; Ribeiro Seijas, Ángela
Palabras clavePrecision agriculture
DES theory
monocots/dicots discrimination
geometric shape descriptors
Weed types discrimination
Fecha de publicación21-may-2014
EditorProducción Gráfica Multimedia
CitaciónSecond International Conference on Robotics and Associated High-Technologies and Equipment for Agriculture and Forestry (RHEA-2014): 149- 156 (2014)
ResumenAn important objective in weed management is the discrimination between monocots and dicots, because these two types of weeds can be controlled more appropriately by specific herbicides. Monocot and dicot weeds differ in morphological characteristics such as the shape of leaves and stems. For this reason, the regions¿ structure belonging to weed classes plays a key role in the proposed discrimination process. Thus six geometric shaped descriptors were used as attributes to describe each isolated region in an image. Based on these attributes, this work established a strategy where the decision was taken by a classifier adapted from the Dempster-Shafer theory. Outdoor field images, taken under varying conditions of lighting, were used to test the proposal performance. This methodology based on distinguishing two types of weeds can be extrapolated to any situation where monocots and dicots are present, e.g. to discriminate between maize, a monocot crop, and dicot weeds.
Aparece en las colecciones: (CAR) Comunicaciones congresos
Ficheros en este ítem:
Fichero Descripción Tamaño Formato  
Herrera_Application of the Dempster_RHEA-2014_149_156_2014.pdf4,19 MBAdobe PDFVista previa
Mostrar el registro completo

NOTA: Los ítems de Digital.CSIC están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.