公开(公告)号：US20240362802A1

公开(公告)日：2024-10-31

申请号：US18306682

申请日：2023-04-25

申请人： Microsoft Technology Licensing, LLC

发明人： Michael BLEYER ,  Pascal PARÉ ,  Paul LEE ,  Aleksander Bogdan BAPST

IPC分类号： G06T7/33 ,  G06T7/246 ,  G06T19/20

CPC分类号： G06T7/344 ,  G06T7/251 ,  G06T19/20 ,  G06T2219/2004 ,  G06T2219/2016 ,  H04N23/54

摘要： A system determining motion models for aligning scene content captured by different image sensors is configurable to access a first motion model generated based upon a set of feature correspondences that includes (i) an inlier set used to determine model parameters for the first motion model and (ii) an outlier set. The system is also configurable to define a modified set of feature correspondences that includes the outlier set from the set of feature correspondences. The system is also configurable to generate a second motion model by using the modified set of feature correspondences to determine model parameters for the second motion model.

公开(公告)号：US20240358437A1

公开(公告)日：2024-10-31

申请号：US18647311

申请日：2024-04-26

申请人： The Johns Hopkins University

发明人： Robert S. Armiger ,  Catherine M. Carneal ,  Nathan G. Drenkow ,  Nathanael P. Kuo ,  Connor O. Pyles ,  Anna E. Knight

IPC分类号： A61B34/10 ,  A61B34/00 ,  A61B90/00 ,  A61B90/50 ,  G06T7/33 ,  G06T7/60 ,  G06T7/73 ,  G06T19/00 ,  G06T19/20 ,  G16H40/63

CPC分类号： A61B34/10 ,  A61B90/361 ,  G06T7/344 ,  G06T7/60 ,  G06T7/73 ,  G06T19/006 ,  G06T19/20 ,  G16H40/63 ,  A61B2034/105 ,  A61B2034/252 ,  A61B2090/061 ,  A61B2090/365 ,  A61B2090/372 ,  A61B2090/373 ,  A61B2090/502 ,  G06T2207/10132 ,  G06T2207/30004 ,  G06T2207/30196 ,  G06T2210/41 ,  G06T2219/2004

摘要： An anatomy visualization device may include a display, an optical sensor, and processing circuitry. The processing circuitry may be configured to capture, via the optical sensor, body registration points on a body of an individual, receive external anatomical measurements of the body, apply the external anatomical measurements to a body shape model, and determine an organ placement prediction for the body based on the application of external anatomical measurements to the body shape model. The organ placement prediction may include organ position information, organ size information, and organ shape information for a plurality of organs. The processing circuitry may also align the organ placement prediction with the body registration points and render, on the display, the organ placement prediction in alignment with the body registration points as an augmented reality object on the body.

公开(公告)号：US20240346670A1

公开(公告)日：2024-10-17

申请号：US18292188

申请日：2022-07-06

申请人： LightLab Imaging, Inc.

发明人： Shimin Li ,  Ajay Gopinath

IPC分类号： G06T7/33 ,  G06T7/00

CPC分类号： G06T7/33 ,  G06T7/0012 ,  G06T2207/30101

摘要： The present disclosure provides systems and methods for automatically aligning intravascular data taken during a plurality of pullbacks in a target blood vessel. Extraluminal images may be taken to determine the location of the guide catheter in the target vessel. Two or more pullbacks may then be performed in the target vessel. The start and end point of each pullback may be determined. A distance between the end point of each pullback and the proximal tip, or junction point, of the guide catheter may be determined. A difference between the end point of each pullback and the junction point may be determined. The difference between the distances from the end of the pullback and the junction point may correspond to the distance to offset one of the representations of the pullbacks in order to automatically align the representation of the pullbacks.

公开(公告)号：US12112490B2

公开(公告)日：2024-10-08

申请号：US17277657

申请日：2020-05-11

申请人： STATE GRID ZHEJIANG ELECTRIC POWER CO., LTD. TAIZHOU POWER SUPPLY COMPANY ,  TAIZHOU ECONOMIC DEVELOPMENT ZONE TRANSPORTATION INSPECTION BRANCH OF TAIZHOU HONGDA ELECTRIC POWER CONSTRUCTION CO., LTD.

发明人： Jiandong Si ,  Jian Yang ,  Chen Zhou ,  Jianhua Lv ,  Guode Ying ,  Qian Yu ,  Qian Zhang ,  Huang Zhang ,  Huanghao Ying ,  Xiaofei Wang ,  Xi Yang ,  Weizhong Chen ,  Dongqi Lu ,  Ge Zhou ,  Jieli Bao ,  Huiyong Qiu

IPC分类号： G06T7/33 ,  G06T3/60 ,  H04N23/698 ,  H04N23/80

CPC分类号： G06T7/33 ,  G06T3/60 ,  H04N23/80 ,  G06T2207/20221 ,  H04N23/698

摘要： Disclosed are apparatus, electronic device, and method for stitching dual-camera images. The method includes collecting two images having overlapping photographic content. The method includes extracting and matching feature points of the two images. The method includes roughly aligning the two images by using a homography matrix. The method includes accurately aligning the two images by using a least squares method to complete stitching the two images.

公开(公告)号：US12106512B2

公开(公告)日：2024-10-01

申请号：US17816218

申请日：2022-07-29

申请人： INUITIVE LTD.

发明人： Eliyahu Hayat Levi

IPC分类号： G06T7/73 ,  G06T7/33 ,  G06T7/521 ,  G06T7/55 ,  G06V10/24

CPC分类号： G06T7/74 ,  G06T7/33 ,  G06T7/521 ,  G06T7/55 ,  G06V10/24 ,  G06T2207/20228 ,  G06T2207/30244

摘要： A method is provided for calibrating a structured light system. The structured light system comprises, a camera, a processor and a projector that emits light at an unknown pattern. According to this method, the projector emits an unknown pattern at two different distances relative to the camera's location, and the camera captures the pattern that was projected at the different distances
The processor then determines the vertical disparity between the two captured images and estimates a relative orientation between the camera and the projector. This estimation in turn is applied in the calibration of the structured light system.

公开(公告)号：US12106503B2

公开(公告)日：2024-10-01

申请号：US18187754

申请日：2023-03-22

申请人： Xesto Inc.

发明人： Mehmet Afiny Affan Akdemir ,  Christian Garcia Salguero ,  Victoria Sophie Howe

IPC分类号： G06T7/593 ,  G06T7/33 ,  G06T19/00

CPC分类号： G06T7/593 ,  G06T7/33 ,  G06T19/00 ,  G06T2207/20036 ,  G06T2207/20084

摘要： Systems and methods are provided for three-dimensional scanning and measurement by a device having a processor. The processor is configured to receive images of an object from at least two angles; preprocess the images using morphological refinement; create a source point cloud based on the images; remove outliers from the source point cloud; globally register the source point cloud to generate a transformed source point cloud; compare the transformed source point cloud with a target point cloud to generate a stitched point cloud that thereby creates a stitched 3D model; measure the resulting stitched 3D model; and provide the resulting stitched 3D model for comparison to a digitized item to assess sizing of the 3D model to the item.

公开(公告)号：US12106495B2

公开(公告)日：2024-10-01

申请号：US18126972

申请日：2023-03-27

申请人： Carvana, LLC

发明人： Bruno Francois ,  Grant Schindler

IPC分类号： G06T7/33 ,  G06F3/0484 ,  G06T3/4007 ,  G06T7/246 ,  G06V10/40 ,  G06V10/48 ,  G06V20/56 ,  H04N23/62 ,  H04N23/68 ,  H04N23/698 ,  H04N25/40

CPC分类号： G06T7/33 ,  G06F3/0484 ,  G06T3/4007 ,  G06T7/246 ,  G06V10/40 ,  G06V10/48 ,  G06V20/56 ,  H04N23/62 ,  H04N23/68 ,  H04N23/698 ,  H04N25/41 ,  G06T2200/32 ,  G06T2207/30244

摘要： Many embodiments can comprise a system. The system can comprise a processor and a memory coupled to the processor. The memory can include instructions that, when executed by the processor, cause the processor to: determine a direction of gravity in each image of a sequence of images around an object; estimate a center of mass of the object in each image of the sequence of images using the direction of gravity and dimensions of the object; stabilize each image in the sequence of images using the center of mass; and generate a 360 degree display of the object using each image in the stabilized sequence of images. Other embodiments are disclosed herein.

公开(公告)号：US12104902B2

公开(公告)日：2024-10-01

申请号：US17234982

申请日：2021-04-20

申请人： Max-Planck-Gesellschaft zur Foerderung der Wissenschaften e.V.

发明人： Johann Engelhardt

IPC分类号： G01B9/02 ,  G01B9/02098 ,  G01B11/26 ,  G02B5/04 ,  G02B21/00 ,  G06T7/33 ,  G06T7/73

CPC分类号： G01B9/02098 ,  G01B9/02041 ,  G01B11/26 ,  G02B5/04 ,  G02B21/0036 ,  G02B21/008 ,  G06T7/33 ,  G06T7/74

摘要： In a method of detecting changes in direction of a collimated coherent light beam, the light beam is split into partial light beams which are superimposed on a camera to form an interference pattern displaying light intensity minima and maxima alternatingly following to one another in a transverse direction oriented transversely to an average propagation direction of the partial beams. The light beam is focused into at least one focus located in front of the camera. Pictures of the interference pattern including a plurality of the light intensity maxima are registered with the camera. An average shift of the plurality of light intensity maxima with regard to the camera in the at least one transverse direction is determined from the pictures. A change in angular orientation of the collimated coherent light beam in the at least one transvers direction is deduced from the average shift.

公开(公告)号：US12103178B2

公开(公告)日：2024-10-01

申请号：US18340000

申请日：2023-06-22

申请人： Google LLC

发明人： Kurt Konolige ,  Nareshkumar Rajkumar ,  Stefan Hinterstoisser

IPC分类号： B25J9/16 ,  G06T7/33 ,  G06T7/70 ,  G06T7/73 ,  G06T17/00 ,  G06V20/10

CPC分类号： B25J9/161 ,  B25J9/1692 ,  G06T7/344 ,  G06T7/70 ,  G06T7/75 ,  G06T17/00 ,  G06V20/10 ,  G05B2219/33038 ,  G05B2219/39046 ,  G05B2219/39543 ,  G05B2219/40564 ,  G06T2207/10012 ,  G06T2207/10028 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30244

摘要： Methods and apparatus related to generating a model for an object encountered by a robot in its environment, where the object is one that the robot is unable to recognize utilizing existing models associated with the robot. The model is generated based on vision sensor data that captures the object from multiple vantages and that is captured by a vision sensor associated with the robot, such as a vision sensor coupled to the robot. The model may be provided for use by the robot in detecting the object and/or for use in estimating the pose of the object.

公开(公告)号：US20240320842A1

公开(公告)日：2024-09-26

申请号：US18610895

申请日：2024-03-20

申请人： Siemens Healthineers AG

发明人： Michael Manhart ,  Stanislav Tashenov

IPC分类号： G06T7/33 ,  G06T11/60 ,  G06V10/74

CPC分类号： G06T7/337 ,  G06T11/60 ,  G06V10/761 ,  G06T2207/30101 ,  G06T2210/41 ,  G06V2201/031

摘要： A method for providing a result dataset includes capturing a vessel dataset. The vessel dataset has time-resolved images of at least one vessel section of an examination object in a number of physiological phases. The method includes capturing an object dataset. The object dataset has an image of a medical object in the examination object in at least one physiological phase of the number of physiological phases. The method includes identifying a corresponding image in the vessel dataset in each case for the images of the object dataset with matching physiological phase, and providing the result dataset by at least partial overlaying and/or mixing of the images of the object dataset with the corresponding images of the vessel dataset.