Training Data for the NeonTreeEvaluation Benchmark

This dataset is the large training data files for the NeonTreeEvaluation Benchmark for individual tree detection from airborne imagery. For each geographic site, given by the NEON four letter code (e.g HARV -> Harvard Forest), there are up to 4 files: a RGB image, a LiDAR tile, and a 426 band hyperpspectral file, and a 1m canopy height file. For more information on the benchmark, and the corresponding R package, see https://github.com/weecology/NeonTreeEvaluation_package Annotations for the tiles, made by looking at the RGB are under version control here: https://github.com/weecology/NeonTreeEvaluation/tree/master/annotations.

Download the training.zip to get all files in the same folder organization as the evaluation data.