DOE Patents title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: System and method for extracting dominant orientations from a scene

Abstract

In one embodiment, a method of identifying the dominant orientations of a scene comprises representing a scene as a plurality of directional vectors. The scene may comprise a three-dimensional representation of a scene, and the plurality of directional vectors may comprise a plurality of surface normals. The method further comprises determining, based on the plurality of directional vectors, a plurality of orientations describing the scene. The determined plurality of orientations explains the directionality of the plurality of directional vectors. In certain embodiments, the plurality of orientations may have independent axes of rotation. The plurality of orientations may be determined by representing the plurality of directional vectors as lying on a mathematical representation of a sphere, and inferring the parameters of a statistical model to adapt the plurality of orientations to explain the positioning of the plurality of directional vectors lying on the mathematical representation of the sphere.

Inventors:
; ; ; ;
Issue Date:
Research Org.:
Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1360774
Patent Number(s):
9665791
Application Number:
14/678,585
Assignee:
Massachusetts Institute of Technology
Patent Classifications (CPCs):
G - PHYSICS G06 - COMPUTING G06K - RECOGNITION OF DATA
G - PHYSICS G06 - COMPUTING G06T - IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
DOE Contract Number:  
FC02-99ER54512; FA8650-11-1-7154
Resource Type:
Patent
Resource Relation:
Patent File Date: 2015 Apr 03
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING

Citation Formats

Straub, Julian, Rosman, Guy, Freifeld, Oren, Leonard, John J., and Fisher, III;, John W. System and method for extracting dominant orientations from a scene. United States: N. p., 2017. Web.
Straub, Julian, Rosman, Guy, Freifeld, Oren, Leonard, John J., & Fisher, III;, John W. System and method for extracting dominant orientations from a scene. United States.
Straub, Julian, Rosman, Guy, Freifeld, Oren, Leonard, John J., and Fisher, III;, John W. Tue . "System and method for extracting dominant orientations from a scene". United States. https://www.osti.gov/servlets/purl/1360774.
@article{osti_1360774,
title = {System and method for extracting dominant orientations from a scene},
author = {Straub, Julian and Rosman, Guy and Freifeld, Oren and Leonard, John J. and Fisher, III;, John W.},
abstractNote = {In one embodiment, a method of identifying the dominant orientations of a scene comprises representing a scene as a plurality of directional vectors. The scene may comprise a three-dimensional representation of a scene, and the plurality of directional vectors may comprise a plurality of surface normals. The method further comprises determining, based on the plurality of directional vectors, a plurality of orientations describing the scene. The determined plurality of orientations explains the directionality of the plurality of directional vectors. In certain embodiments, the plurality of orientations may have independent axes of rotation. The plurality of orientations may be determined by representing the plurality of directional vectors as lying on a mathematical representation of a sphere, and inferring the parameters of a statistical model to adapt the plurality of orientations to explain the positioning of the plurality of directional vectors lying on the mathematical representation of the sphere.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2017},
month = {5}
}

Works referenced in this record:

Joint component framework for modeling complex joint behavior
patent, February 2008


Method and apparatus for determining item orientation
patent, July 2012


Methods and systems for 3D shape retrieval
patent, December 2013


Video Surveillance Systems, Devices And Methods With Improved 3d Human Pose And Shape Modeling
patent-application, September 2013


Discriminative histograms of local dominant orientation (D-HLDO) for biometric image feature extraction
journal, October 2013


Vanishing points and three-dimensional lines from omni-directional video
journal, October 2003


Manhattan World: compass direction from a single image by Bayesian inference
conference, January 1999


Reconstructing building interiors from images
conference, September 2009


21/2 D Scene Reconstruction of Indoor Scenes from Single RGB-D Images
book, January 2013


Real-time manhattan world rotation estimation in 3D
conference, September 2015