3-dimensional model generation using edges

US9846963B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-9846963-B2
Application numberUS-201514725938-A
CountryUS
Kind codeB2
Filing dateMay 29, 2015
Priority dateOct 3, 2014
Publication dateDec 19, 2017
Grant dateDec 19, 2017

How to read this patent

A practical reading order for non-experts. Skip the full description unless you need deep technical detail.

  1. Title

    What the patent document calls the invention.

  2. Abstract

    A short plain-language summary of the technical disclosure.

  3. Assignees and inventors

    Who owns or filed the patent and who is credited as inventor.

  4. Key dates

    Filing, priority, publication, and grant dates set the timeline.

  5. First independent claim

    The legal scope of protection — read this for what is actually claimed.

  6. CPC / IPC classifications

    Technology tags used to group this patent with similar filings.

  7. Citations and related patents

    Prior art links and similar publications in this corpus.

Abstract

Official abstract text for this publication.

3-dimensional model generation using edges may include detecting, using a processor, a plurality of edges in a plurality of images and determining, using the processor, a set edges from the plurality of edges that are matched across the plurality of images. Camera poses of the plurality of images may be estimated using the processor and using a cost function that depends upon the set of edges.

First claim

Opening claim text (preview).

What is claimed is: 1. A method, comprising: detecting, using a processor, a plurality of edges in a plurality of images; determining, using the processor, a set of edges from the plurality of edges that are matched across the plurality of images; determining, using the processor, three orthogonal axes according to the set of edges by grouping edges of the set of edges into a plurality of buckets according to orientation, wherein each of a first axis and a second axis of the three orthogonal axes is determined according to one of the plurality of buckets based upon a number of edges in the plurality of buckets; estimating camera poses of the plurality of images using a cost function that depends upon the set of edges; generating planes for a 3-dimensional model according to the camera poses and the set of edges, wherein the 3-dimensional model is generated from the plurality of images; identifying false planes from among the planes; and removing the false planes. 2. The method of claim 1 , wherein a third axis of the three orthogonal axes is determined according to a function of the first axis and the second axis. 3. The method of claim 1 , wherein determining three orthogonal axes further comprises: determining the first axis according to the bucket including a largest number of edges; determining the second axis according to the bucket including a second largest number of edges; and determining a third axis according to a cross-product of the first axis and the second axis. 4. The method of claim 3 , further comprising: adjusting the second axis to be orthogonal to the first axis. 5. The method of claim 1 , further comprising: rendering the planes. 6. A system, comprising: a memory configured to store program code; and a processor coupled to the memory, wherein the processor is programmed using the program code to initiate executable operations comprising: detecting a plurality of edges in a plurality of images; determining a set of edges from the plurality of edges that are matched across the plurality of images; determining, using the processor, three orthogonal axes according to the set of edges by grouping edges of the set of edges into a plurality of buckets according to orientation, wherein each of a first axis and a second axis of the three orthogonal axes is determined according to one of the plurality of buckets based upon a number of edges in the plurality of buckets; estimating camera poses of the plurality of images using a cost function that depends upon the set of edges; generating planes for a 3-dimensional model according to the camera poses and the set of edges, wherein the 3-dimensional model is generated from the plurality of images; identifying false planes from among the planes; and removing the false planes. 7. The system of claim 6 , wherein a third axis of the three orthogonal axes is determined according to a function of the first axis and the second axis. 8. The system of claim 6 , wherein determining three orthogonal axes comprises: determining the first axis according to the bucket including a largest number of edges; determining the second axis according to the bucket including a second largest number of edges; and determining a third axis according to a cross-product of the first axis and the second axis. 9. The system of claim 8 , wherein the processor is further programmed to initiate executable operations comprising: adjusting the second axis to be orthogonal to the first axis. 10. The system of claim 6 , wherein the processor is further programmed to initiate executable operations comprising: rendering the planes. 11. A computer program product comprising a computer readable storage medium having program code stored thereon, the program code executable by a processor to perform a method comprising: detecting, using the processor, a plurality of edges in a plurality of images; determining, using the processor, a set of edges from the plurality of edges that are matched across the plurality of images; determining, using the processor, three orthogonal axes according to the set of edges by grouping edges of the set of edges into a plurality of buckets according to orientation, wherein each of a first axis and a second axis of the three orthogonal axes is determined according to one of the plurality of buckets based upon a number of edges in the plurality of buckets; estimating, using the processor, camera poses of the plurality of images using a cost function that depends upon the set of edges; generating planes for a 3-dimensional model according to the camera poses and the set of edges, wherein the 3-dimensional model is generated from the plurality of images; identifying false planes from among the planes; and removing the false planes. 12. The computer program product of claim 11 , wherein a third axis of the three orthogonal axes is determined according to a function of the first axis and the second axis. 13. The computer program product of claim 11 , wherein determining three orthogonal axes further comprises: determining the first axis according to the bucket including a largest number of edges; determining the second axis according to the bucket including a second largest number of edges; and determining a third axis according to a cross-product of the first axis and the second axis. 14. The computer program product of claim 13 , wherein the method further comprises: adjusting the second axis to be orthogonal to the first axis. 15. The computer program product of claim 11 , wherein the method further comprises: rendering the planes.

Assignees

Inventors

Classifications

Patent family

Related publications grouped by family.

External sources

Frequently asked questions

Answers are generated from the same data shown on this page.

What does patent US9846963B2 cover?
3-dimensional model generation using edges may include detecting, using a processor, a plurality of edges in a plurality of images and determining, using the processor, a set edges from the plurality of edges that are matched across the plurality of images. Camera poses of the plurality of images may be estimated using the processor and using a cost function that depends upon the set of edges.
Who is the assignee on this patent?
Samsung Electronics Co Ltd
What technology area does this patent fall under?
Primary CPC classification G06T7/73. Mapped technology areas include Physics.
When was this patent published?
Publication date Tue Dec 19 2017 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 8 related publications on this page (citations in our corpus or others sharing the same primary CPC).