公开(公告)号：US10325351B2

公开(公告)日：2019-06-18

申请号：US15207239

申请日：2016-07-11

Applicant: QUALCOMM Incorporated

Inventor： Mahdi Rad ,  Markus Oberweger ,  Vincent Lepetit

IPC: G06K9/46 ,  G06N3/04 ,  G06N3/08 ,  G06T3/40 ,  G06T5/00 ,  G06T5/20 ,  H04N1/60 ,  G06F17/18 ,  G06T15/50

Abstract: A method for normalizing an image by an electronic device is described. The method includes obtaining an image including a target object. The method also includes determining a set of windows of the image. The method further includes, for each window of the set of windows of the image, predicting parameters of an illumination normalization model adapted to the window using a first convolutional neural network (CNN), and applying the illumination normalization model to the window to produce a normalized window.

公开(公告)号：US10235771B2

公开(公告)日：2019-03-19

申请号：US15495665

申请日：2017-04-24

Applicant: QUALCOMM Incorporated

Inventor： Mahdi Rad ,  Markus Oberweger ,  Vincent Lepetit

IPC: G06K9/00 ,  G06T7/73 ,  G06K9/32 ,  G06K9/46

Abstract: Techniques are provided for estimating a three-dimensional pose of an object. An image including the object can be obtained, and a plurality of two-dimensional (2D) projections of a three-dimensional bounding (3D) box of the object in the image can be determined. The plurality of 2D projections of the 3D bounding box can be determined by applying a trained regressor to the image. The trained regressor is trained to predict two-dimensional projections of the 3D bounding box of the object in a plurality of poses, based on a plurality of training images. The three-dimensional pose of the object is estimated using the plurality of 2D projections of the 3D bounding box.

公开(公告)号：US10373369B2

公开(公告)日：2019-08-06

申请号：US15692401

申请日：2017-08-31

Applicant: QUALCOMM Incorporated

Inventor： Mahdi Rad ,  Markus Oberweger ,  Vincent Lepetit

IPC: G06K9/00 ,  G06T15/20 ,  G06T7/73 ,  G06K9/62

Abstract: The present disclosure describes methods, apparatuses, and non-transitory computer-readable mediums for estimating a three-dimensional (“3D”) pose of an object from a two-dimensional (“2D”) input image which contains the object. Particularly, certain aspects of the disclosure are concerned with 3D pose estimation of a symmetric or nearly-symmetric object. An image or a patch of an image includes the object. A classifier is used to determine whether a rotation angle of the object in the image or the patch of the image is within a first predetermined range. In response to a determination that the rotation angle is within the first predetermined range, a mirror image of the object is determined. Two-dimensional (2D) projections of a three-dimensional (3D) bounding box of the object are determined by applying a trained regressor to the mirror image of the object in the image or the patch of the image. The 3D pose of the object is estimated based on the 2D projections.

公开(公告)号：US20180137644A1

公开(公告)日：2018-05-17

申请号：US15495665

申请日：2017-04-24

Applicant: QUALCOMM Incorporated

Inventor： Mahdi Rad ,  Markus Oberweger ,  Vincent Lepetit

IPC: G06T7/73 ,  G06K9/00

CPC classification number: G06T7/73 ,  G06K9/00208 ,  G06K9/00671 ,  G06K9/3208 ,  G06K9/3241 ,  G06K9/4628 ,  G06T2207/20084

Abstract: Techniques are provided for estimating a three-dimensional pose of an object. An image including the object can be obtained, and a plurality of two-dimensional (2D) projections of a three-dimensional bounding (3D) box of the object in the image can be determined. The plurality of 2D projections of the 3D bounding box can be determined by applying a trained regressor to the image. The trained regressor is trained to predict two-dimensional projections of the 3D bounding box of the object in a plurality of poses, based on a plurality of training images. The three-dimensional pose of the object is estimated using the plurality of 2D projections of the 3D bounding box.

公开(公告)号：US20200184668A1

公开(公告)日：2020-06-11

申请号：US16210461

申请日：2018-12-05

Applicant: QUALCOMM Incorporated

Inventor： Mahdi Rad ,  Markus Oberweger ,  Vincent Lepetit

IPC: G06T7/70 ,  G06T7/50 ,  G06F17/50 ,  G06N3/08

Abstract: A method is described. The method includes mapping features extracted from an unannotated red-green-blue (RGB) image of the object to a depth domain. The method further includes determining a three-dimensional (3D) pose of the object by providing the features mapped from the unannotated RGB image of the object to the depth domain to a trained pose estimator network.

公开(公告)号：US20180268601A1

公开(公告)日：2018-09-20

申请号：US15692401

申请日：2017-08-31

Applicant: QUALCOMM Incorporated

Inventor： Mahdi Rad ,  Markus Oberweger ,  Vincent Lepetit

IPC: G06T15/20 ,  G06T7/73 ,  G06K9/62

CPC classification number: G06T15/205 ,  G06K9/00208 ,  G06K9/6256 ,  G06K9/627 ,  G06T7/70 ,  G06T7/75 ,  G06T2207/10028 ,  G06T2207/20068 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: The present disclosure describes methods, apparatuses, and non-transitory computer-readable mediums for estimating a three-dimensional (“3D”) pose of an object from a two-dimensional (“2D”) input image which contains the object. Particularly, certain aspects of the disclosure are concerned with 3D pose estimation of a symmetric or nearly-symmetric object. An image or a patch of an image includes the object. A classifier is used to determine whether a rotation angle of the object in the image or the patch of the image is within a first predetermined range. In response to a determination that the rotation angle is within the first predetermined range, a mirror image of the object is determined. Two-dimensional (2D) projections of a three-dimensional (3D) bounding box of the object are determined by applying a trained regressor to the mirror image of the object in the image or the patch of the image. The 3D pose of the object is estimated based on the 2D projections.

公开(公告)号：US20170262962A1

公开(公告)日：2017-09-14

申请号：US15207239

申请日：2016-07-11

Applicant: QUALCOMM Incorporated

Inventor： Mahdi Rad ,  Markus Oberweger ,  Vincent Lepetit

IPC: G06T3/40 ,  H04N1/60 ,  G06F17/18 ,  G06N3/04 ,  G06N3/08 ,  G06T15/50 ,  G06T5/20

CPC classification number: G06T3/4046 ,  G06F17/18 ,  G06K9/4628 ,  G06K9/4661 ,  G06N3/04 ,  G06N3/08 ,  G06T5/007 ,  G06T5/008 ,  G06T5/20 ,  G06T15/506 ,  G06T2207/10024 ,  G06T2207/20021 ,  G06T2207/20081 ,  G06T2207/20084 ,  H04N1/6005 ,  H04N1/6008

Abstract: A method for normalizing an image by an electronic device is described. The method includes obtaining an image including a target object. The method also includes determining a set of windows of the image. The method further includes, for each window of the set of windows of the image, predicting parameters of an illumination normalization model adapted to the window using a first convolutional neural network (CNN), and applying the illumination normalization model to the window to produce a normalized window.