Brazilian Coffee Crop and Orange Orchard Datasets

  • by

Brazilian Coffee Crops Dataset

This dataset is a composition of scenes taken by SPOT sensor in 2005 over four counties in the State of Minas Gerais, Brazil: Arceburgo, Guaranesia, Guaxupé and Monte Santo. It has many intraclass variance caused by different crop management techniques. Also, coffee is an evergreen culture and the South of Minas Gerais is a mountainous region, which means that this dataset includes scenes with different plant ages and/or with spectral distortions caused by shadows. There is a total of four orthoimages, one for each county, and also four mask images with pixel level annotation of coffee/non-coffee class.

Orange Orchard Dataset

This dataset is comprised of satellite images obtained from Planet of an Orange Orchard located at the municipality of Ubirajara, São Paulo, Brazil. The satellite images are divided in four bands: Red, Green, Blue, and Near InfraRed. In addition to the images a shapefile mask is provided denoting areas of Orange plantations.

Please, cite this dataset as:

Gama, Pedro Henrique Targino, Hugo Neves Oliveira, Jose Marcato, and Jefersson Dos Santos. "Weakly Supervised Few-Shot Segmentation Via Meta-Learning." IEEE Transactions on Multimedia (2022).

  title={Weakly Supervised Few-Shot Segmentation Via Meta-Learning},
  author={Gama, Pedro Henrique Targino and Oliveira, Hugo Neves and Marcato, Jose and Dos Santos, Jefersson},
  journal={IEEE Transactions on Multimedia},


We thank Rubens Lamparelli, Cooxupé, and José Marcato Junior for the image sets.

Download Datasets