Multispectral Image Analysis of Remotely Sensed Crops

dc.contributor.advisorDeObeso-Orendain, Alberto
dc.contributor.authorVillanueva-Molina, José J.
dc.date.accessioned2022-09-27T20:18:50Z
dc.date.available2022-09-27T20:18:50Z
dc.date.issued2022-05
dc.descriptionThe range in topography, biodiversity, and agricultural technology has led to the emergence of precision agriculture. Precision agriculture is a farming management concept based on monitoring, measuring, and responding to crop variability. Computer vision, image analysis, and image processing are gaining considerable traction. For this paper, image analysis involves recognizing individual objects and providing insights from vegetation indices. The data acquired was remote-sensed multispectral images from blueberry, maguey, and pineapple. After computing vegetation indices, histograms were analyzed to choose thresholds. The masking of vegetation indices with threshold allowed the removal of areas with shadows and soil. The four leading vegetation indices used were the Normalized Difference Vegetation Index (NDVI), the Normalized Difference Red Edge (NDRE), the Simple Ratio, the Red Edge Chlorophyll Index, and the Visible Atmospherically Resistant Index (SAVI). This research reviews literature for acquiring, preprocessing, and analyzing remote-sensed multispectral images in precision agriculture. It compiles the theoretical framework for analyzing multispectral data. Also, it describes and implements radiometric calibration and image alignment using the custom code from the MicaSense repository. As a result, it was possible to segment the blueberry, tequila agave, and pineapple plants from the background regardless of the noisy images. Non-plant pixels were excluded and shown as transparent by masking areas with shadows and low NDVI pixels, which sometimes removed plant pixels. The NDVI and NDRE helped identify crop pixels. On the other hand, it was possible to identify the pineapple fruits from the agave plantation using the SAVI vegetation index and the thresholding method. Finally, the work identifies the problems associated with an incorrect data acquisition methodology and provides suggestions.es_MX
dc.description.sponsorshipITESO, A. C.es
dc.identifier.citationVillanueva-Molina, J. J. (2022). Multispectral Image Analysis of Remotely Sensed Crops. Trabajo de obtención de grado, Maestría en Sistemas Computacionales. Tlaquepaque, Jalisco: ITESO.es_MX
dc.identifier.urihttps://hdl.handle.net/11117/8203
dc.language.isoenges_MX
dc.publisherITESOes_MX
dc.rights.urihttp://quijote.biblio.iteso.mx/licencias/CC-BY-NC-2.5-MX.pdfes_MX
dc.subjectMultispectral Image Analysises_MX
dc.subjectRemotely Sensed Cropses_MX
dc.subjectPrecision Agriculturees_MX
dc.subjectspectral signaturees_MX
dc.subjectNDVIes_MX
dc.subjectNDREes_MX
dc.subjectimage processinges_MX
dc.titleMultispectral Image Analysis of Remotely Sensed Cropses_MX
dc.typeinfo:eu-repo/semantics/masterThesises_MX
dc.type.versioninfo:eu-repo/semantics/acceptedVersiones_MX

Archivos

Bloque original
Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
TOG_Multispectral Image Analysis of Remotely Sensed Crops_JoseVillanueva.pdf
Tamaño:
2.2 MB
Formato:
Adobe Portable Document Format
Descripción: