Published September 20, 2022 | Version 1.0
Dataset Open

A deep learning dataset for savanna tree species in Northern Australia

Creators

  • 1. Supervising Scientist
  • 2. Microsoft, Australia

Description

We present a baseline deep learning dataset of 2547 polygons for 36 tree species in Northern Australia. Polygons were drawn on imagery that was collected using Remotely Piloted Aircraft System (RPAS). The dataset consists of:

  • 7 orthomosaics 
  • 7 shape files with polygon annotations 
  • 1 training dataset in COCO format
  • 1 validation dataset in COCO format

Training and validation datasets were derived from the orthomosaics by tiling each image at 1024x1024 pixel size with 512 pixel step size (overlap). 

To perform deep learning model training with this dataset go to https://github.com/ajansenn/SavannaTreeAI for more information. 

Files

Training and validation dataset.zip

Files (19.3 GB)

Name Size Download all
md5:cc4cd46de190ecb160af0c8e8b9a4b5e
9.7 GB Download
md5:cb3b47ab05a58f86cd4f45f42b07e5e7
9.6 GB Preview Download