Detecting crops and weeds using agricultural-based vision systems

NOVEMBER 10, 2008--In recent decades, precision agriculture, a practice geared to delivering "the right dose at the right place at the right moment," has become possible with the development of remote sensors. In particular, vegetative matter within fields can be digitally recorded using vision systems embedded either in agricultural engines or in small remotely piloted aircraft. These images can then be used to identify regions of high weed content to focus, and reduce, herbicide applications. That is why Frédéric Truchetet at the University of Bourgogne (Le Creusot, France) has developed two programs based on such systems for weed detection in crop fields. Amultispectral camera embedded in an aircraft enabled Truchetet to obtain images within which the spatial distribution of weeds can be estimated. Various classification methods were used to categorize pixels as either crop or weeds. For more information, go to: http://spie.org/x27354.xml