DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Prioritized multi-view stereo depth map generation using confidence prediction

Mostegel, Christian and Fraundorfer, Friedrich and Bischof, Horst (2018) Prioritized multi-view stereo depth map generation using confidence prediction. ISPRS Journal of Photogrammetry and Remote Sensing, 167, pp. 167-180. Elsevier. DOI: 10.1016/j.isprsjprs.2018.03.022 ISSN 0924-2716

[img] PDF

Official URL: https://www.sciencedirect.com/science/article/pii/S092427161830087X


In this work, we propose a novel approach to prioritize the depth map computation of multi-view stereo (MVS) to obtain compact 3D point clouds of high quality and completeness at low computational cost. Our prioritization approach operates before the MVS algorithm is executed and consists of two steps. In the first step, we aim to find a good set of matching partners for each view. In the second step, we rank the resulting view clusters (i.e. key views with matching partners) according to their impact on the fulfillment of desired quality parameters such as completeness, ground resolution and accuracy. Additional to geometric analysis, we use a novel machine learning technique for training a confidence predictor. The purpose of this confidence predictor is to estimate the chances of a successful depth reconstruction for each pixel in each image for one specific MVS algorithm based on the RGB images and the image constellation. The underlying machine learning technique does not require any ground truth or manually labeled data for training, but instead adapts ideas from depth map fusion for providing a supervision signal. The trained confidence predictor allows us to evaluate the quality of image constellations and their potential impact to the resulting 3D reconstruction and thus builds a solid foundation for our prioritization approach. In our experiments, we are thus able to reach more than 70% of the maximal reachable quality fulfillment using only 5% of the available images as key views. For evaluating our approach within and across different domains, we use two completely different scenarios, i.e. cultural heritage preservation and reconstruction of single family houses.

Item URL in elib:https://elib.dlr.de/120524/
Document Type:Article
Title:Prioritized multi-view stereo depth map generation using confidence prediction
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Mostegel, Christianmostegel (at) icg.tugraz.atUNSPECIFIED
Fraundorfer, Friedrichfriedrich.fraundorfer (at) dlr.deUNSPECIFIED
Bischof, Horstbischof (at) icg.tu-graz.ac.atUNSPECIFIED
Date:August 2018
Journal or Publication Title:ISPRS Journal of Photogrammetry and Remote Sensing
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In ISI Web of Science:Yes
DOI :10.1016/j.isprsjprs.2018.03.022
Page Range:pp. 167-180
Keywords:Multi-view stereo; Machine learning; Confidence measures; View prioritization; Image clustering; View cluster ranking
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Transport
HGF - Program Themes:Traffic Management (old)
DLR - Research area:Transport
DLR - Program:V VM - Verkehrsmanagement
DLR - Research theme (Project):V - Vabene++ (old)
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > Photogrammetry and Image Analysis
Deposited By: Zielske, Mandy
Deposited On:03 Jul 2018 18:38
Last Modified:06 Sep 2019 15:28

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.