A Neural Network for Interpolating Light-Sources

dc.cclicenceCC-BY-NCen
dc.contributor.authorColreavy-Donnelly, S.
dc.contributor.authorKuhn, Stefan
dc.contributor.authorCaraffini, Fabio
dc.contributor.authorO'Connor, S.
dc.contributor.authorAnastassi, Zacharias
dc.contributor.authorCoupland, Simon
dc.date.acceptance2020-05-15
dc.date.accessioned2020-06-02T10:28:50Z
dc.date.available2020-06-02T10:28:50Z
dc.date.issued2020-07-13
dc.description.abstractThis 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 illumination-model 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. © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.en
dc.funderNo external funderen
dc.identifier.citationColreavy-Donnelly, S., Kuhn, S., Caraffini, F., O'Connor, S., Anastassi, Z., Coupland, S. (2020) A Neural Network for Interpolating Light-Sources. 4th IEEE International Workshop on Software Engineering for Smart Systems - IEEE Computer Society Signature Conference on Computers, Software and Applications (COMPSAC), Madrid, Spain, July 2020.en
dc.identifier.urihttps://dora.dmu.ac.uk/handle/2086/19689
dc.language.isoenen
dc.publisherIEEEen
dc.researchinstituteInstitute of Artificial Intelligence (IAI)en
dc.subjectshadow detectionen
dc.subjectlight source detectionen
dc.subjectsingleimage solutionen
dc.subjectdeep learningen
dc.subjectunsupervised learningen
dc.titleA Neural Network for Interpolating Light-Sourcesen
dc.typeConferenceen
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
LightNN.pdf
Size:
1.36 MB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
4.2 KB
Format:
Item-specific license agreed upon to submission
Description: