公开(公告)号：US20240087146A1

公开(公告)日：2024-03-14

申请号：US18273612

申请日：2021-04-08

申请人： NEC Corporation

发明人： Royston RODRIGUES ,  Masahiro TANl

IPC分类号： G06T7/35

CPC分类号： G06T7/35 ,  G06T2207/10032 ,  G06T2207/20081

摘要： A training apparatus (2000) acquires a ground-view image (20), an aerial-view image (30), and alignment information (50), and trains a discriminator (10) that extracts a plurality of partial aerial regions (40) from the aerial-view image (30) and determines that the ground-view image (20) matches the aerial-view image (30) when there is the partial aerial region (40) that matches the ground-view image (20). The training apparatus (2000) extracts a correctly-aligned partial aerial region (42) and a mis-aligned partial aerial region (44) from the aerial-view image (30). The correctly-aligned partial aerial region (42) is indicated by the alignment information (50) and corresponds to the ground-view image (20). The mis-aligned partial aerial region (44) partially overlaps the correctly-aligned partial aerial region (42). The training apparatus (2000) trains the discriminator (10) using both the correctly-aligned partial aerial region (42) and the mis-aligned partial aerial region (44) as positive examples.

公开(公告)号：US11830137B2

公开(公告)日：2023-11-28

申请号：US17187685

申请日：2021-02-26

申请人： Aurora Solar Inc.

发明人： Matthew John Stevens ,  Ganesh Nunnagoppula ,  Maxwell Siegelman ,  Adriel Anhao Luo

IPC分类号： G06T17/10 ,  G06T17/20 ,  G06T7/10 ,  G06N3/08 ,  G06T7/35 ,  G06V20/10 ,  G06T3/00

CPC分类号： G06T17/10 ,  G06N3/08 ,  G06T3/0081 ,  G06T7/10 ,  G06T7/35 ,  G06T17/20 ,  G06V20/176 ,  G06T2207/10032 ,  G06T2210/22

摘要： Automated three-dimensional (3D) building model estimation is disclosed. In an embodiment, a method comprises: obtaining, using one or more processors, an aerial image of a building based on an input address; obtaining, using the one or more processors, three-dimensional (3D) data containing the building based on the input address; pre-processing the aerial image and 3D data; reconstructing, using the one or more processors, a 3D building model from the pre-processed image and 3D data, the reconstructing including: predicting, using instance segmentation, a mask for each roof face; converting each roof face into a two-dimensional (2D) polygon; and projecting each 2D polygon into a 3D polygon representing the 3D building model.

公开(公告)号：US20230230281A1

公开(公告)日：2023-07-20

申请号：US18152219

申请日：2023-01-10

申请人： Robert Bosch GmbH

发明人： Christopher Herbon ,  Johannes Peter Berger

IPC分类号： G06T7/80 ,  G06T7/35 ,  G06T7/37

CPC分类号： G06T7/80 ,  G06T7/35 ,  G06T7/37 ,  G06T2207/30252 ,  G06T2207/30244

摘要： A method for calibrating a multiplicity of cameras on a vehicle in a common coordinate system. The method includes: a) acquiring camera images using each camera of the multiplicity of cameras, b) ascertaining overlap regions of camera images acquired in step a), c) setting up a common optimization function, which describes the alignments of each camera of the multiplicity of cameras as a target variable of the optimization, based on the overlap regions, d) solving the common optimization function set up in step c) to ascertain the alignments of each camera.

公开(公告)号：US20230186495A1

公开(公告)日：2023-06-15

申请号：US17923191

申请日：2021-04-07

申请人： Howmedica Osteonics Corp.

发明人： Sergii Poltaretskyi ,  Charlotte Le Saint ,  Jean Chaoui

IPC分类号： G06T7/35 ,  G06T19/20 ,  G06T7/55 ,  A61B34/10

CPC分类号： G06T7/35 ,  G06T19/20 ,  G06T7/55 ,  A61B34/10 ,  G06T2207/20124 ,  G06T2207/30052 ,  G06T2207/30008 ,  G06T2219/2021 ,  G06T2219/2004 ,  G06T2210/44 ,  G06T2210/41 ,  A61B2034/105 ,  A61B2090/365

摘要： Techniques are described for determining a pre-morbid shape of an anatomical object. A method includes receiving first image data of a first anatomical structure and second image data of a second anatomical structure. The first and second anatomical structures are anatomically related. The method includes determining a first shape model based on the first image data and a joint statistical shape model (SSM). The method includes determining a second shape model based on the first shape model, the first image data, and the second image data, the second shape model including a second estimated shape of the first anatomical structure and a second estimated shape for the second anatomical structure. The method includes generating anatomical information indicative of the pre-morbid shape of at least the second anatomical structure based on the second shape model.

公开(公告)号：US10019811B2

公开(公告)日：2018-07-10

申请号：US14972559

申请日：2015-12-17

申请人： CANON KABUSHIKI KAISHA

发明人： Takaaki Endo ,  Kiyohide Satoh ,  Ryo Ishikawa

IPC分类号： G06K9/46 ,  G06T7/60 ,  G06T3/00 ,  G06T7/35 ,  G06T7/33

CPC分类号： G06T7/60 ,  G06T3/0081 ,  G06T7/33 ,  G06T7/35 ,  G06T2207/10072

摘要： An image processing apparatus obtains a plurality of corresponding information items for registration of a first image and a second image of an object, calculates, in a case where the first image and the second image are registered using corresponding information items remaining after excluding at least one corresponding information item from the plurality of corresponding information items, a registration error that occurs at a position of the excluded corresponding information item, and estimates a registration error at an arbitrary position in a case where the first image and the second image are registered using the plurality of corresponding information items based on the calculated registration error.

公开(公告)号：US20180089843A1

公开(公告)日：2018-03-29

申请号：US15716425

申请日：2017-09-26

申请人： DigitalGlobe, Inc.

发明人： GRZEGORZ MIECZNIK

IPC分类号： G06T7/32 ,  G06T7/207

CPC分类号： G06T7/32 ,  G06T7/207 ,  G06T7/35 ,  G06T2207/10036

摘要： Techniques for improving image co-registration. One aspect relates to improving Mutual Information techniques by making the histogram bin widths used therein depend on the amount of signal noise. Another aspect relates to populating the bins by integrating the signal probability in each bin. A third aspect relates to converting top-of-the-atmosphere image data to surface reflectance data, and then using surface reflectance data in the Mutual Information technique for determining a correlation surface. The fourth aspect relates to registering higher-resolution images with lower-resolution images by down-sampling the higher-resolution image. The last aspect relates to a technique for determining the accuracy of the co-registration by synthesizing a perfectly-registered image in a second wavelength band from an image in a first wavelength band and then using Mutual Information between the two images to create a correlation surface.

公开(公告)号：US20180040152A1

公开(公告)日：2018-02-08

申请号：US15554649

申请日：2015-03-26

申请人： CENTRALESUPELEC

发明人： Nikos PARAGIOS ,  Singht BHARAT ,  Stavros ALCHATZIDIS

IPC分类号： G06T11/60 ,  G06T7/70

CPC分类号： G06T11/60 ,  G06T7/35 ,  G06T7/37 ,  G06T7/70 ,  G06T2207/10028 ,  G06T2207/10081 ,  G06T2207/10088 ,  G06T2207/10132 ,  G06T2207/20021 ,  G06T2207/20064 ,  G06T2207/20072 ,  G06T2207/30004

摘要： The invention concerns a method for deformable fusion of a source multi-dimensional image (s(x)) and a target multi-dimensional image (t(x)) of an object, each image being defined on a multi-dimensional domain by a plurality of image signal samples, each sample having an associate position in the multi-dimensional domain and an intensity value, the method comprising estimating a smooth deformation field (d(x)) that optimizes a similarity criterion between the source image and the target image using a Markov Random Field framework, in near real-time performance. The similarity criterion is computed on transform coefficients obtained by applying a sub-space hierarchical transform to the image samples of the target image and to image samples obtained from the source image, an optimal tradeoff between a smoothness condition and the similarity criterion being automatically determined.

公开(公告)号：US09842264B2

公开(公告)日：2017-12-12

申请号：US15226406

申请日：2016-08-02

申请人： Chiman Kwan ,  Bulent Ayhan

发明人： Chiman Kwan ,  Bulent Ayhan

IPC分类号： G06K9/00 ,  G06T3/00 ,  G06K9/62 ,  G06T7/33 ,  G06T7/35 ,  G06K9/20 ,  G06K9/46

CPC分类号： G06K9/00791 ,  G06K9/2018 ,  G06K9/4671 ,  G06K9/6211 ,  G06K9/6269 ,  G06T3/0068 ,  G06T7/33 ,  G06T7/35 ,  G06T2207/10021 ,  G06T2207/20076

摘要： This invention fuses spectral information from multiple imagers of an unmanned ground vehicle (UGV). Since the imagers contain different spectral information for each pixel location, the invention provides highly accurate targeting and guidance information to the UGV. The invention applies a robust 2-step image registration process for alignment of images captured by each of the multiple imagers to automatically identify targets of interest, so that the UGV can move toward the targets. This two-step image registration process can achieve sub-pixel accuracy. After registration, a new multispectral image is formed with pixels containing spectral information from all imagers. The invention further incorporates an accurate anomaly detection algorithm to help detect new targets in the scene, and incorporates advanced composition estimation algorithms to determine the composition of targets. Finally, the invention allows users to interact with the target detection results through a user friendly graphical user interface.

公开(公告)号：US20170337672A1

公开(公告)日：2017-11-23

申请号：US15600227

申请日：2017-05-19

申请人： Shenyang Neusoft Medical Systems Co., Ltd.

发明人： Yuyue ZOU ,  Shuang HONG ,  Fengqiu CAO ,  Yan KANG

IPC分类号： G06T5/50 ,  G06T7/30 ,  G06T3/40

CPC分类号： G06T5/50 ,  G06T3/4038 ,  G06T7/30 ,  G06T7/35 ,  G06T2207/10072 ,  G06T2207/30004 ,  G06T2207/30012

摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium for image splicing are provided. In one aspect, a method includes obtaining at least two groups of to-be-spliced images and scanning information corresponding to the at least two groups of to-be-spliced images, determining an overlap area of the at least two groups of to-be-spliced images and a physical sequence of splicing according to the scanning information, registering the at least two groups of to-be-spliced images based on the overlap area to obtain a registration result, and splicing the at least two groups of registered to-be-spliced images according to the physical sequence of splicing and the registration result.

公开(公告)号：US09785234B2

公开(公告)日：2017-10-10

申请号：US14757834

申请日：2015-12-26

申请人： Intel Corporation

发明人： Nizan Horesh

IPC分类号： H04N9/47 ,  G06F3/01 ,  G06F1/16 ,  H04N5/247 ,  H04N5/225 ,  G06T7/00 ,  G06K9/00

CPC分类号： G06F3/013 ,  G06K9/00604 ,  G06K9/0061 ,  G06T7/33 ,  G06T7/337 ,  G06T7/35 ,  H04N5/23219 ,  H04N5/247

摘要： Technologies for gaze tracking by ambient light include a mobile compute device to capture a first image of a user of the mobile compute device by a first camera and a second image of a real-world environment of the mobile compute device by a second camera. The mobile compute device determines a physical location of a light source relative to the mobile compute device based on the second image and identifies a first and second corneal reflection in an eye of the user captured in the first image. The mobile compute device determines, based on the physical location, a first correspondence between the first corneal reflection and the light source and a second correspondence between the second corneal reflection and an image displayed on a display of the mobile compute device. Further, the mobile compute device performs gaze tracking based on the first correspondence and the second correspondence.