2024-03-29T15:17:51Zhttp://digital.csic.es/dspace-oai/requestoai:digital.csic.es:10261/1110152021-07-12T06:50:01Zcom_10261_31565com_10261_4col_10261_31569
http://hdl.handle.net/10261/111015
258241
Application of the Dempster-Shafer theory to classify monocot and dicot weeds based on geometric shape descriptors
Producción Gráfica Multimedia
2014
comunicación de congreso
Herrera Caro, Pedro Javier
Dorado, José
rp14264
Ribeiro Seijas, Ángela
Precision agriculture
DES theory
monocots/dicots discrimination
geometric shape descriptors
Weed types discrimination
2014-05-21
An 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.
European Commission
Ministerio de Economía y Competitividad (España)
Second International Conference on Robotics and Associated High-Technologies and Equipment for Agriculture and Forestry (RHEA-2014)
2014
149
156