Supervised classification and NDVI calculation from remote piloted aircraft images for coffee plantations applications


  • Sthéfany Airane dos Santos Universidade Federal de Lavras/UFLA, Departamento de Engenharia Agrícola/DEA, Lavras, MG, Brasil.
  • Gabriel Araújo e Silva Ferraz Universidade Federal de Lavras/UFLA, Departamento de Engenharia Agrícola/DEA, Lavras, MG, Brasil.
  • Vanessa Castro Figueiredo Empresa de Pesquisa Agropecuária de Minas Gerais/EPAMIG, Três Pontas, MG, Brasil.
  • Lucas Santos Santana Universidade Federal de Lavras/UFLA, Departamento de Engenharia Agrícola/DEA, Lavras, MG, Brasil.
  • Beatriz Fonseca Dominik Campos Empresa de Pesquisa Agropecuária de Minas Gerais/EPAMIG, Lavras, MG, Brasil.



A tool that has been widely used in Precision Agriculture (PA) is the Remote Piloted Aircraft’s (RPA’s). These tools are used to monitor crops, in addition to checking and quantifying various attributes related to plants. However, there are few studies that evaluate the applicability of this technology in coffee plantations. The objective of this study is to present the applicability of two tools associated with PA and remote sensing to monitoring a coffee plantation. The study was conducted in the municipality of Três Pontas, Brazil, comprised a 1.2 ha coffee plantation. Data were collected during a flight with an eBee SQ RPA, and high spatial resolution images were captured by a Parrot Sequoia multispectral sensor coupled to the aircraft. The images were processed using the software Pix4D, thus creating an orthomosaic that was later uploaded to QGIS software. In this program, a supervised classification of land use and land cover was performed using the maximum likelihood method, and the following classes were obtained: coffee plant, exposed soil, and
undergrowth. From the mapping accuracy, an overall accuracy and kappa index of 91% and 85% were obtained, respectively. In addition to the supervised classification of the site, the normalized difference vegetation index (NDVI) was calculated for only the coffee plant class. The NDVI map showed the areas of the plantation coffee crop with higher and lower vegetative vigour.

Key words: Mapping; precision coffee farming; remotely piloted aircraft.

Author Biography

Sthéfany Airane dos Santos, Universidade Federal de Lavras/UFLA, Departamento de Engenharia Agrícola/DEA, Lavras, MG, Brasil.

Departamento de Engenharia

Setor de Máquinas e Mecanização

Agricultura de Precisão


ABREU JÚNIOR, C. A. M. et al. Mapping of nematodes in coffee culture from multispectral images obtained by aircraft remotely piloted. Paths of Geography, 21(76):72-84, 2020.

AHMAD, A. et al. Remotely piloted aircraft (RPA) in agriculture: A pursuit of sustainability. Agronomy, 11(1):7, 2021.

BARBOSA, B. D. S. et al. RGB vegetation indices applied to grass monitoring: A qualitative analysis. Agronomy Research, 17(2):349-357, 2019.

BATER, C. W. et al. Using digital time-lapse cameras to monitor species-specific understory and overstory phenology in support of wildlife habitat assessment. Environmental Monitoring and Assessment, 180(1-4):1-13, 2011.

BELGIU, M.; DRAˇGU¸T, L. Comparing supervised and unsupervised multiresolution segmentation approaches for extracting buildings from very high resolution imagery. ISPRS J. Photogramm. Remote Sensing, 96:67-75, 2014.

BERNARDES, T. et al. Monitoring Biennial Bearing Effect on Coffee Yield Using MODIS Remote Sensing Imagery. Remote Sensing, 4:2492-2509, 2012.

CHEMURA, A.; MUTANGA, O.; DUBE, T. Separability of coffee leaf rust infection levelswith machine learning methods at Sentinel-2 MSI spectral resolutions. Precision Agriculture, 18:859-881, 2016.

CHO, D. F. et al. Desempenho do algoritmo de classificação de imagens Random Forest para mapeamento do uso e cobertura do solo no cerrado brasileiro. Anuário do Instituto de Geociências, 44:37979, 2021.

CORDEIRO, A. P. et al. Regiões homogêneas de vegetação utilizando a variabilidade do NDVI. Ciência Florestal, 27:883-896, 2017.

CONGALTON, R. G. Accuracy and error analysis of global and local maps: Lessons learned and future considerations. Remote Sensing of Global Croplands for Food Security, 441:47-55, 2009.

COSTA, H.; FOODY, G. M.; BOYD, D. S. Supervised methods of image segmentation accuracy assessment in land cover mapping. Remote Sensing of Environment, 205:338-351, 2018.

DA CUNHA, J. P. A. R.; SIRQUEIRA, M. A.; HURTADO, S. Estimating vegetation volume of coffee crops using images from unmanned aerial vehicles. Engenharia Agrícola, 39:41-47, 2019.

EASTMAN, J. R. Idrisi for Windows. Version 2.0. Worceter, MA: Clark university, 1999.

FELIX, F. C. et al. Use of embarked sensors in vehicles aerial not created in monitoring vegetation, soil and interior waters. In: HAYASHI, C.; SARDINHA, D. S.; PAMPLIN, P. A. Z. (Org). Ciências ambientais: diagnósticos ambientais. Alfenas-MG, Hayashi, C. Editor 1ed, 41-63, 2020.

GOLDMAN, D. B. Vignette and exposure calibration and compensation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(12):2276-2288, 2010.

HERWITZ, S. R. et al. Imaging from an unmanned aerial vehicle: Agricultural surveillance and decision support. Computers and Electronics in Agriculture, 44(1):49-61, 2004.

INSTITUTO NACIONAL DE METEOROLOGIA DO BRASIL – INMET. Normais Climatológicas (1961/2020). Brasília - DF, 2020.

JENSEN, J. R. Introductory digital image processing. Englewood Cliffs: Prentice-Hall, 1996. 51p.

JOHNSON, L. F. et al. Feasibility of monitoring coffee field ripeness with airborne multispectral imagery. Applied Engineering in Agriculture, 20(6):845, 2004.

KŘÍŽOVÁ, K.; KUMHÁLOVÁ, J. Comparison of selected remote sensing sensors for crop yield variability estimation. Agronomy Research, 15(4):1636-1645, 2017.

LANDIS, J. R.; KOCH, G. G. The measurement of observer agreement for categorical data. Biometrics, 33(1):159-174, 1977.

LAMPARELLI, R. A. C.; NERY, L.; ROCHA, J. V. Use of the technique by main components (acp) and lighting factor, in the mapping of coffee culture in mountainous relief. Engenharia Agrícola, 31(3):584-597, 2011.

LILLESAND, T. M.; KIEFER, R. W.; CHIPAN, J. W. Remote sensing and interpretation, 5ed. Madison: Wiley, 2004. 763p.

LUNETTA, R. S. et al. Land-cover change detection using multi-time MODIS NDVI data. Remote Sensing of Environment, 105(2):142-154, 2006.

MA, L. et al. A review of supervised object-based land-cover image classification. ISPRS Journal of Photogrammetry and Remote Sensing, 130:277-293, 2017.

MOREIRA, M. A. Fundamentals of remote sensing and application methodologies, 3.ed., 2007. 320p.

MOREIRA, M. A.; BARROS, M. A.; RUDORFF, B. F. T. Geotechnologies in the mapping of coffee culture in municipal scale. Society & Nature, 20(1):101-110, 2008.

OLIVEIRA, H. C. et al. Failure detection in row crops from UAV images using morphological operators. IEEE Geoscience and Remote Sensing Letters, 15(7):991-995, 2018.

OLSSON, P. O. et al. Radiometric Correction of Multispectral UAS Images: Evaluating the Accuracy of the Parrot Sequoia Camera and Sunshine Sensor. Remote Sensing, 13:577, 2021.

PELLEGRINO, G. Q. et al. Estimation of the leaf area index and of dry mass of sugarcane stalks from spectral field data. Revista Brasileira de Agrometeorologia, 15(1):49-58, 2007.

SANTOS, L. M. et al. Use of remotely piloted aircraft to map land use in an area of coffee trees. In: AGUILERA, J. G.; ZUFFO, A. M. (Org.). The productive dynamics of sustainable agriculture. Ponta Grossa- PR, Atena Editora, p.140-144, 2019a.

SANTOS, L. M. et al. Analysis of flight parameters and georeferencing of images with different control points obtained by RPA. Agronomy Research, 17(5):2054-2063, 2019b.

SANTOS, L. M. et al. Analysis of flight parameters of remotely piloted aircraft in the generation of orthoosaic for coffee growing. In: AGUILERA, J. G.; ZUFFO, A. M. (Org.). The productive dynamics of agriculture sustainable. Ponta Grossa-PR, Atena Editora, p.22-29, 2019c.

SANTOS, L. M. et al. Biophysical parameters of coffee crop estimated by UAV RGB images. Precision Agriculture, 21:1227-1241, 2020.

SANTOS, L. M. et al. Coffee crop coefficient prediction as a function of biophysical variables identified from RGB UAS images. Agronomy Research, 18(2):1463-1471, 2020.

SARMIENTO, C. M. et al. Comparison of supervised classifiers in the discrimination of coffee areas in general fields - Minas Gerais General. Coffee Science, 9(4):546-557, 2014.

SIMÕES, M. S.; ROCHA, J. V.; LAMPARELLI, R. A. C. Orbital spectral variables, growth analysis and sugarcane yield, Scientia Agricola, 66(4):451-461, 2009.

STARÝ, K. et al. Comparing RGB - based vegetation indices from UAV imageries to estimate hops canopy area. Agronomy Research, 18(4):2592-2601, 2020.

STOW, D. et al. Illumination Geometry and Flying Height Influence Surface Reflectance and NDVI Derived from Multispectral UAS Imagery. Drones 3, 55, 2019.

TORRES-SÁNCHEZ, J. et al. Multi-temporal mapping of the vegetation fraction in early-season wheat fields using images from UAV. Computers and Electronics in Agriculture, 103:104-113, 2014.

VELÁSQUEZ, D. et al. A Method for Detecting Coffee Leaf Rust through Wireless Sensor Networks, Remote Sensing, and Deep Learning: Case Study of the Caturra Variety in Colombia. Applied Sciences, 10(2):697, 2020.

URBAHS, A.; JONAITE, I. Features of the use of unmanned aerial vehicles for agriculture applications. Aviation, 17:170-175, 2013.

ZHANG, X. et al. A global classification of vegetation based on NDVI, rainfall and temperature. International Journal of Climatology, 37(5):2318-2324, 2016.




How to Cite

SANTOS, S. A. dos; FERRAZ, G. A. e S. .; FIGUEIREDO, V. C.; SANTANA, L. S.; CAMPOS, B. F. D. Supervised classification and NDVI calculation from remote piloted aircraft images for coffee plantations applications. Coffee Science - ISSN 1984-3909, [S. l.], v. 16, p. e161978, 2022. DOI: 10.25186/.v16i.1978. Disponível em: Acesso em: 30 sep. 2022.