Published February 12, 2019 | Version v1
Dataset Open

Dataset for: Sky pixel detection in outdoor imagery using an adaptive algorithm and machine learning.

  • 1. University of Melbourne

Description

The data presented in this article is related to the research article entitled ``Sky pixel detection in outdoor imagery using an adaptive algorithm and machine learning." \citep{Nice2019UC}.

The dataset consists of a trained Inception V3 neural network model as well as the configuration files to train the neural network and run the inferences. The dataset also contains two sets of outdoor imagery (from Skyfinder and Google Street View) used to train the neural network and validate the sky pixel detection system in the linked article. The original images are included as well as rescaled imagery used to train the neural network, and sky masks used for validation.

Files

CNTK-InceptionV3.zip

Files (10.5 GB)

Name Size Download all
md5:f56021c2bbfd60e8213305c72a4e9539
91.1 MB Preview Download
md5:c206069fa64e9c898623ac41826318cd
6.2 GB Preview Download
md5:59048fafd0663eef645be2b109ffecbf
4.0 GB Preview Download
md5:fb65c7979a64a9262b931c62c41a9d5b
262.4 MB Preview Download