skip to main content
DOE Patents title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Systems and methods that generate height map models for efficient three dimensional reconstruction from depth information

Abstract

Methods of generating a three dimensional representation of an object in a reference plane from a depth map including distances from a reference point to pixels in an image of the object taken from a reference point. Weights are assigned to respective voxels in a three dimensional grid along rays extending from the reference point through the pixels in the image based on the distances in the depth map from the reference point to the respective pixels, and a height map including an array of height values in the reference plane is formed based on the assigned weights. An n-layer height map may be constructed by generating a probabilistic occupancy grid for the voxels and forming an n-dimensional height map comprising an array of layer height values in the reference plane based on the probabilistic occupancy grid.

Inventors:
; ;
Issue Date:
Research Org.:
The University of North Carolina at Chapel Hill, Chapel Hill, NC (United States); Eidgenossische Technische Hochschule Zurich, Zurich, CH (Switzerland)
Sponsoring Org.:
USDOE
OSTI Identifier:
1230019
Patent Number(s):
9,208,612
Application Number:
13/578,758
Assignee:
The University of North Carolina at Chapel Hill
DOE Contract Number:  
FG52-08NA28778
Resource Type:
Patent
Resource Relation:
Patent File Date: 2011 Dec 08
Country of Publication:
United States
Language:
English
Subject:
42 ENGINEERING

Citation Formats

Frahm, Jan-Michael, Pollefeys, Marc Andre Leon, and Gallup, David Robert. Systems and methods that generate height map models for efficient three dimensional reconstruction from depth information. United States: N. p., 2015. Web.
Frahm, Jan-Michael, Pollefeys, Marc Andre Leon, & Gallup, David Robert. Systems and methods that generate height map models for efficient three dimensional reconstruction from depth information. United States.
Frahm, Jan-Michael, Pollefeys, Marc Andre Leon, and Gallup, David Robert. Tue . "Systems and methods that generate height map models for efficient three dimensional reconstruction from depth information". United States. https://www.osti.gov/servlets/purl/1230019.
@article{osti_1230019,
title = {Systems and methods that generate height map models for efficient three dimensional reconstruction from depth information},
author = {Frahm, Jan-Michael and Pollefeys, Marc Andre Leon and Gallup, David Robert},
abstractNote = {Methods of generating a three dimensional representation of an object in a reference plane from a depth map including distances from a reference point to pixels in an image of the object taken from a reference point. Weights are assigned to respective voxels in a three dimensional grid along rays extending from the reference point through the pixels in the image based on the distances in the depth map from the reference point to the respective pixels, and a height map including an array of height values in the reference plane is formed based on the assigned weights. An n-layer height map may be constructed by generating a probabilistic occupancy grid for the voxels and forming an n-dimensional height map comprising an array of layer height values in the reference plane based on the probabilistic occupancy grid.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2015},
month = {12}
}

Patent:

Save / Share:

Works referenced in this record:

A Fusion Scheme for Joint Retrieval of Urban Height Map and Classification From High-Resolution Interferometric SAR Images
journal, February 2007

  • Tison, Cline; Tupin, Florence; Maitre, Henri
  • IEEE Transactions on Geoscience and Remote Sensing, Vol. 45, Issue 2
  • DOI: 10.1109/TGRS.2006.887006

A volumetric method for building complex models from range images
conference, January 1996

  • Curless, Brian; Levoy, Marc
  • Proceedings of the 23rd annual conference on Computer graphics and interactive techniques - SIGGRAPH '96
  • DOI: 10.1145/237170.237269

Image-based street-side city modeling
conference, January 2009

  • Xiao, Jianxiong; Fang, Tian; Zhao, Peng
  • ACM SIGGRAPH Asia 2009 papers on - SIGGRAPH Asia '09
  • DOI: 10.1145/1661412.1618460

Layered depth images
conference, January 1998

  • Shade, Jonathan; Gortler, Steven; He, Li-wei
  • Proceedings of the 25th annual conference on Computer graphics and interactive techniques - SIGGRAPH '98
  • DOI: 10.1145/280814.280882

3D Urban Scene Modeling Integrating Recognition and Reconstruction
journal, October 2007

  • Cornelis, Nico; Leibe, Bastian; Cornelis, Kurt
  • International Journal of Computer Vision, Vol. 78, Issue 2-3
  • DOI: 10.1007/s11263-007-0081-9

Data Processing Algorithms for Generating Textured 3D Building Facade Meshes from Laser Scans and Camera Images
journal, February 2005


Detailed Real-Time Urban 3D Reconstruction from Video
journal, October 2007

  • Pollefeys, M.; Nistér, D.; Frahm, J. -M.
  • International Journal of Computer Vision, Vol. 78, Issue 2-3
  • DOI: 10.1007/s11263-007-0086-4

An Automated Method for Large-Scale, Ground-Based City Model Acquisition
journal, October 2004


Towards Wiki-based Dense City Modeling
conference, October 2007

  • Irschara, Arnold; Zach, Christopher; Bischof, Horst
  • 2007 IEEE 11th International Conference on Computer Vision
  • DOI: 10.1109/ICCV.2007.4409216

Real-Time Visibility-Based Fusion of Depth Maps
conference, October 2007

  • Merrell, Paul; Akbarzadeh, Amir; Wang, Liang
  • 2007 IEEE 11th International Conference on Computer Vision
  • DOI: 10.1109/ICCV.2007.4408984

A taxonomy and evaluation of dense two-frame stereo correspondence algorithms
conference, January 2001

  • Scharstein, D.; Szeliski, R.; Zabih, R.
  • Proceedings IEEE Workshop on Stereo and Multi-Baseline Vision (SMBV 2001)
  • DOI: 10.1109/SMBV.2001.988771

A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms
conference, January 2006


Fast Compact City Modeling for Navigation Pre-Visualization
conference, January 2006

  • Cornelis, N.; Cornelis, K.; Van Gool, L.
  • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06)
  • DOI: 10.1109/CVPR.2006.118

Manhattan-world stereo
conference, June 2009

  • Furukawa, Yasutaka; Curless, Brian; Seitz, Steven M.
  • 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPR Workshops), 2009 IEEE Conference on Computer Vision and Pattern Recognition
  • DOI: 10.1109/CVPR.2009.5206867

Piecewise planar stereo for image-based rendering
conference, September 2009

  • Sinha, Sudipta N.; Steedly, Drew; Szeliski, Richard
  • 2009 IEEE 12th International Conference on Computer Vision (ICCV)
  • DOI: 10.1109/ICCV.2009.5459417

A Globally Optimal Algorithm for Robust TV-L1 Range Image Integration
conference, October 2007

  • Zach, Christopher; Pock, Thomas; Bischof, Horst
  • 2007 IEEE 11th International Conference on Computer Vision
  • DOI: 10.1109/ICCV.2007.4408983

Visual Modeling with a Hand-Held Camera
journal, September 2004