This database was used in the work Potential of machine learning and WorldView-2 images to recognize endangered and invasive species in the Atlantic Rainforest. In this work, we compared the use of spectral and textural descriptors (Pyramid Histogram of Oriented Gradients - PHOG and Filter Edge), optimized by data mining (Genetic Algorithm - GA) submitted to two classifiers Random Forest - RF and Artificial Neural Network - ANN. Thus, we sought to explore the spectral and textural response of these species in WorldView-2 multispectral images.

We selected two compositions (RBG: R=660 nm, G=545 nm, B=480 nm, and NIR: NIR-2=950 nm, G=545 nm, B=480 nm)