Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Obtaining depth map from 2D non stereo images using deep neural networks

Obtaining depth map from 2D non stereo images using deep neural networks PurposeSingle image depth prediction allows to extract depth information from a usual 2D image without usage of special sensors such as laser sensors, stereo cameras, etc. The purpose of this paper is to solve the problem of obtaining depth information from 2D image by applying deep neural networks (DNNs).Design/methodology/approachSeveral experiments and topologies are presented: DNN that uses three inputs—sequence of 2D images from videostream and DNN that uses only one input. However, there is no data set, that contains videostream and corresponding depth maps for every frame. So technique of creating data sets using the Blender software is presented in this work.FindingsDespite the problem of an insufficient amount of available data sets, the problem of overfitting was encountered. Although created models work on the data sets, they are still overfitted and cannot predict correct depth map for the random images, that were included into the data sets.Originality/valueExisting techniques of depth images creation are tested, using DNN. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png International Journal of Intelligent Unmanned Systems Emerald Publishing

Obtaining depth map from 2D non stereo images using deep neural networks

Download PDF
13 pages

Loading next page...
 
/lp/emerald-publishing/obtaining-depth-map-from-2d-non-stereo-images-using-deep-neural-9diXO63LQb

References (35)

Publisher
Emerald Publishing
Copyright
Copyright © Emerald Group Publishing Limited
ISSN
2049-6427
DOI
10.1108/IJIUS-03-2018-0007
Publisher site
See Article on Publisher Site

Abstract

PurposeSingle image depth prediction allows to extract depth information from a usual 2D image without usage of special sensors such as laser sensors, stereo cameras, etc. The purpose of this paper is to solve the problem of obtaining depth information from 2D image by applying deep neural networks (DNNs).Design/methodology/approachSeveral experiments and topologies are presented: DNN that uses three inputs—sequence of 2D images from videostream and DNN that uses only one input. However, there is no data set, that contains videostream and corresponding depth maps for every frame. So technique of creating data sets using the Blender software is presented in this work.FindingsDespite the problem of an insufficient amount of available data sets, the problem of overfitting was encountered. Although created models work on the data sets, they are still overfitted and cannot predict correct depth map for the random images, that were included into the data sets.Originality/valueExisting techniques of depth images creation are tested, using DNN.

Journal

International Journal of Intelligent Unmanned Systems – Emerald Publishing

Published: Jul 2, 2018

There are no references for this article.