English   español  
Please use this identifier to cite or link to this item: http://hdl.handle.net/10261/164956
Share/Impact:
Statistics
logo share SHARE   Add this article to your Mendeley library MendeleyBASE
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE
Exportar a otros formatos:

Title

The full protocol for early-season weed mapping with UAV technology

AuthorsPeña Barragán, José Manuel ; Torres-Sánchez, Jorge ; Castro, Ana Isabel de ; López Granados, Francisca
KeywordsSite-specific weed management (SSWM)
Unmanned aerial vehicle
Object-based image analysis
Herbaceous row crops
Woody crops
Issue DateJun-2016
Citation7th International Weed Science Congress (2016)
AbstractThe application of site-specifi c weed management (SSWM) practices requires that the weeds be previously located in the crop fi eld, e.g., by generating a weed map. Until now, obtaining these weed maps early in the growing season, which is the moment recommended in many crops for an optimal weed management treatment, has been a great challenge because of the reduced size of the weed and crop plants and their spectral similarity at an early phenological stage. This challenge has been overcome by the combined use of aerial images collected with an Unmanned Aerial Vehicles (UAV) and application of object-based image analysis (OBIA) techniques. This abstract describes the full protocol developed in the last four years by our research group with that objective. The investigation was conducted over several parcels of three herbaceous (wheat, corn and sunfl ower) and three woody (olive, poplar and grape) crops. The main phases of this protocol involved: 1) confi guration and use of the UAV and sensors for image acquisition, 2) determining the fi nest fl ight confi guration (UAV altitude, image spatial and spectral resolutions, fl ight length, etc.) for each type of crop, with particular attention to crop evolution (multi-temporal study), 3) optimizing the process of image mosaicing and geo-referencing in order to generate a unique ortho-mosaiced image that completely covers the fi elds of study, and 4) development of customised and robust OBIA procedures for weed mapping and crop assessment in order to optimize cropweed management operations adapted to diff erent scenarios. Our results demonstrated that weed emergences could be discriminated with accuracy higher than 90% if image resolutions are correctly selected for each type of crop and scenario, although an agreement with fl ight length and UAV battery duration is needed in order to optimize the full procedure.
DescriptionTrabajo presentado en el 7th International Weed Science Congress (Weed Science and Management to Feed the Planet), celebrado en Praga del 19 al 25 de junio de 2016.
URIhttp://hdl.handle.net/10261/164956
Appears in Collections:(IAS) Comunicaciones congresos
Files in This Item:
File Description SizeFormat 
accesoRestringido.pdf15,38 kBAdobe PDFThumbnail
View/Open
Show full item record
Review this work
 


WARNING: Items in Digital.CSIC are protected by copyright, with all rights reserved, unless otherwise indicated.