A Neural Network for Interpolating Light-Sources

Simon Colreavy-Donnelly, Stefan Kuhn, Fabio Caraffini, Stuart Oconnor, Zacharias Anastassi, Simon Coupland

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This study combines two novel deterministic methods with a Convolutional Neural Network to develop a machine learning method that is aware of directionality of light in images. The first method detects shadows in terrestrial images by using a sliding-window algorithm that extracts specific hue and value features in an image. The second method interpolates light-sources by utilising a line-algorithm, which detects the direction of light sources in the image. Both of these methods are single-image solutions and employ deterministic methods to calculate the values from the image alone, without the need for illumination-models. They extract real-time geometry from the light source in an image, rather than mapping an illuminationmodel onto the image, which are the only models used today. Finally, those outputs are used to train a Convolutional Neural Network. This displays greater accuracy than previous methods for shadow detection and can predict light source-direction and thus orientation accurately, which is a considerable innovation for an unsupervised CNN. It is significantly faster than the deterministic methods. We also present a reference dataset for the problem of shadow and light direction detection.

Original languageEnglish
Title of host publicationProceedings - 2020 IEEE 44th Annual Computers, Software, and Applications Conference, COMPSAC 2020
EditorsW. K. Chan, Bill Claycomb, Hiroki Takakura, Ji-Jiang Yang, Yuuichi Teranishi, Dave Towey, Sergio Segura, Hossain Shahriar, Sorel Reisman, Sheikh Iqbal Ahamed
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1634-1640
Number of pages7
ISBN (Electronic)9781728173030
DOIs
Publication statusPublished - Jul 2020
Externally publishedYes
Event44th IEEE Annual Computers, Software, and Applications Conference, COMPSAC 2020 - Virtual, Madrid, Spain
Duration: 13 Jul 202017 Jul 2020

Publication series

NameProceedings - 2020 IEEE 44th Annual Computers, Software, and Applications Conference, COMPSAC 2020

Conference

Conference44th IEEE Annual Computers, Software, and Applications Conference, COMPSAC 2020
Country/TerritorySpain
CityVirtual, Madrid
Period13/07/2017/07/20

Keywords

  • deep learning
  • light source detection
  • shadow detection
  • single-image solution
  • unsupervised learning

Fingerprint

Dive into the research topics of 'A Neural Network for Interpolating Light-Sources'. Together they form a unique fingerprint.

Cite this