Random Sample Consensus for Groups of Data

Patent metadata

Field	Value
Publication number	US-2017228613-A1
Application number	US-201715494106-A
Country	US
Kind code	A1
Filing date	Apr 21, 2017
Priority date	Aug 15, 2008
Publication date	Aug 10, 2017
Grant date	—

Abstract

In one embodiment, a computer accessible storage medium stores a plurality of instructions which, when executed: group a set of reconstructed three dimensional (3D) points derived from image data into a plurality of groups based on one or more attributes of the 3D points; select one or more groups from the plurality of groups; and sample data from the selected groups, wherein the sampled data is input to a consensus estimator to generate a model that describes a 3D model of a scene captured by the image data. Other embodiments may bias sampling into a consensus estimator for any data set, based on relative quality of the data set.

First claim

1 - 22 . (canceled)

23 . A method for reconstructing a three-dimensional (3D) model of a scene based on a consensus estimate of a model parameter from captured images of the scene by at least one computing device, the method comprising:
detecting, by the at least one computing device, a first set of features in a first image of the scene and a second set of features in a second image of the scene; determining, by the at least one computing device, potential correspondences between the first set of features and the second set of features; generating, by the at least one computing device, the consensus estimate of the model parameter by:
forming groups of the potential correspondences based on at least one image attribute;
generating a plurality of scores in which each said score is based on respective said potential correspondences in a respective said group;
sampling the potential correspondences of at least one said group based on the plurality of scores; and
determining the consensus estimate of the model parameter based on the sampled potential correspondences; and
reconstructing, by the at least one computing device, the 3D model of the scene based at least in part on the consensus estimate of the model parameter.

24 . A method as described in claim 23 , wherein the scores are based on a number of the respective said potential correspondences in the respective said group.

25 . A method as described in claim 24 , wherein said groups having larger numbers of the respective said potential correspondences are scored more favorably.

26 . A method as described in claim 23 , wherein the scores are based on a ratio of inlier correspondences to outlier correspondences of the respective said potential correspondences in the respective said group.

27 . A method as described in claim 26 , wherein said groups having higher ratios of the inlier correspondences to the outlier correspondences are scored more favorably.

28 . A method as described in claim 23 , wherein the at least one image attribute is color.

29 . A method as described in claim 23 , wherein the features include at least one of points, lines, curves, or surfaces.

30 . A method as described in claim 23 , wherein the consensus estimate of the model parameter is determined with RANSAC from the sampled potential correspondences.

31 . A method as described in claim 23 , further comprising generating a fit score for the consensus estimate of the model parameter that indicates a fit of the consensus estimate of the model parameter to all the potential correspondences.

32 . A method as described in claim 31 , further comprising, responsive to a determination that the fit score does not indicate a suitable fit of the consensus estimate of the model parameter to all the potential correspondences:
sampling the potential correspondences of at least one additional said group; and updating the consensus estimate of the model parameter based on the sampled potential correspondences of the at least one said group and the at least one additional said group.

33 . A method as described in claim 23 , further comprising:
detecting at least a third set of features in at least a third image of the scene; determining the potential correspondences between the first set of features and the at least third set of features; and determining the potential correspondences between the second set of features and the at least third set of features.

34 . A system comprising:
at least one processor; and memory having stored thereon computer-readable instructions that are executable by the at least one processor to perform operations for reconstructing a three-dimensional (3D) model of a scene based on a consensus estimate of a model parameter from captured sensor data of the scene, the operations comprising: detecting a first set of features in a first set of sensor data of the scene and a second set of features in a second set of sensor data of the scene; determining potential correspondences between the first set of features and the second set of features; generating the consensus estimate of the model parameter by:
forming groups of the potential correspondences based on at least one attribute described by the captured sensor data;
generating a plurality of scores in which each said score is based on respective said potential correspondences in a respective said group;
sampling the potential correspondences of at least one said group based on the plurality of scores; and
determining the consensus estimate of the model parameter based on the sampled potential correspondences; and
reconstructing the 3D model of the scene based at least in part on the consensus estimate of the model parameter.

35 . A system as described in claim 34 , wherein the scores are based on a number of the respective said potential correspondences in the respective said group.

36 . A system as described in claim 35 , wherein said groups having larger numbers of the respective said potential correspondences are scored more favorably.

37 . A system as described in claim 34 , wherein the scores are based on a ratio of inlier correspondences to outlier correspondences of the respective said potential correspondences in the respective said group.

38 . A system as described in claim 37 , wherein said groups having higher ratios of the inlier correspondences to the outlier correspondences are scored more favorably.

39 . A system as described in claim 34 , wherein:
the captured sensor data of the scene comprises images of the scene; the first set of sensor data comprises a first image of the scene; the second set of sensor data comprises a second image of the scene; and the at least one attribute described by the captured sensor data comprises at least one image attribute.

40 . A system as described in claim 34 , wherein the operations further comprise, responsive to a determination that the fit score does not indicate a suitable fit of the consensus estimate of the model parameter to all the potential correspondences:
generating a fit score for the consensus estimate of the model parameter that indicates a fit of the consensus estimate of the model parameter to all the potential correspondences; sampling the potential correspondences of at least one additional said group; and updating the consensus estimate of the model parameter based on the sampled potential correspondences of the at least one said group and the at least one additional said group

41 . A method for reconstructing a three-dimensional (3D) model of an object in a scene based on a consensus estimate of a model parameter from captured video of the scene by at least one computing device, the method comprising:
identifying, by the at least one computing device, a first and second image of the scene in a sequence of images forming the captured video; detecting, by the at least one computing device, a first set of features in the first image and a second set of features in the second image; determining, by the at least one computing device, potential correspondences between the first set of features and the second set of features; generating, by the at least one computing device, the consensus estimate of the model parameter by:
forming groups of the potential correspondences based on at least one image attribute;
generating a plurality of scores in which each said score is based on respective said potential correspondences in a respective said group;
sampling the potential correspondences of at lea

Assignees

• Adobe Systems Inc

Inventors

• Jin Hailin
• Ni Kai

Classifications

• G06V20/647 Primary

  by matching two-dimensional images to three-dimensional objects · CPC title

• G06V10/757

  Matching configurations of points or features · CPC title

• G06F18/2413

  based on distances to training or reference patterns · CPC title

• G06K9/4604

  Physics · mapped topic

• G06K9/4652

  Physics · mapped topic