-
公开(公告)号：US20240412396A1
公开(公告)日：2024-12-12
申请号：US18657848
申请日：2024-05-08
Applicant: Fujitsu Limited
Inventor： Noriyasu ASO
Abstract: A computer-readable recording medium stores a specifying program for causing a computer to execute a process. The process includes: calculating a first distance between a center point of each shape data and a straight line on a same plane as the center point, for a specific portion of which the center point is defined, from among a plurality of portions included in a shape indicated by each shape data classified into the same group; adding the calculated first distance to dimensional information of the specific portion in each shape data; and specifying a dimensional relationship between different portions of the shape data in the group, based on the dimensional information for each portion of each shape data in the group.
-
公开(公告)号：US20240394914A1
公开(公告)日：2024-11-28
申请号：US18321616
申请日：2023-05-22
Applicant: QUALCOMM Incorporated
Inventor： Jeong-Kyun Lee , Young-Ki Baik , Yongho Shin , Sueyeon Kim , Duck Hoon Kim
Abstract: This disclosure provides systems, methods, and devices for vehicle driving assistance systems that support image processing. In a first aspect, a method includes receiving images of a vehicle and determining locations of key points of the vehicle within the keyframes. Pose estimations may then be determined based on the key point locations, and a three-dimensional contour of the vehicle may be determined based on the pose estimations. A model may then be trained based on the three-dimensional contour of the vehicle. Other aspects and features are also claimed and described.
-
公开(公告)号：US12141988B2
公开(公告)日：2024-11-12
申请号：US17508882
申请日：2021-10-22
Inventor： So-Hee Park
Abstract: Disclosed herein are a contour-based privacy region masking apparatus and method. The contour-based privacy region masking apparatus includes a memory for storing at least one program, and a processor for executing the program, wherein the program may perform detecting a contour of an object that is a privacy protection target in an original image, setting a masking region based on the detected contour, and de-identifying the masking region in the original image.
-
公开(公告)号：US12100098B2
公开(公告)日：2024-09-24
申请号：US17970490
申请日：2022-10-20
Applicant: Magic Leap, Inc.
Inventor： Benjamin Joseph Uscinski
CPC classification number: G06T17/00 , G06T7/564 , G06T7/593 , G06T19/006 , G06V10/44 , G06V20/20 , G06V40/193
Abstract: A method to reconstruct an environment is provided. The method makes available to a wide variety of XR applications fresh and accurate 3D reconstruction data of environments with low processing time and low usage of computational resources and storage spaces. The 3D reconstruction data are structured in a way to be efficiently shared between users for multi-user experiences. The method includes obtaining plane segments of an environment, identifying surface planes of the environment by, for example, filtering and grouping the plane segments or ad hoc selection of the plane segments by a user, and inferring corner points of the environment based on the surface planes. The corner points are used to build a 3D representation of the environment when an XR application requires.
-
公开(公告)号：US12080037B2
公开(公告)日：2024-09-03
申请号：US17749771
申请日：2022-05-20
Inventor： Chiayu Lin , Tsubasa Kusaka
Abstract: According to one embodiment, a reading system includes an extractor, a generator, a corrector, and a reader. The extractor extracts a first candidate region from an input image. The first candidate region is of a candidate of a region in which a meter is imaged. The generator generates a rectangle around the first candidate region when an exterior form of the first candidate region is circular. The rectangle corresponds to the exterior form of the first candidate region. The corrector generates a second candidate region by using the generated rectangle to correct the exterior form of the first candidate region to approach a perfect circle. The reader reads, from the second candidate region, a numerical value indicated by the meter.
-
Patent Agency Ranking
公开(公告)号：US20240249424A1
公开(公告)日：2024-07-25
申请号：US18550210
申请日：2022-03-04
Applicant: Central Institute for Experimental Animals
Inventor： Terumi Yurimoto , Erika Sasaki , Takashi Inoue
CPC classification number: G06T7/564 , A01K29/005 , G06T7/90 , G06T2207/10024 , G06T2207/10048 , G06T2207/20081 , G06T2207/20084
Abstract: An excrement property estimation model learning device includes a training data acquisition unit configured to acquire training data including input-side training data including an excrement space which is a predetermined space where there is excrement from an animal being reared, and learning image data that is image data of a captured image obtained by capturing the excrement space, and a correct label indicating whether any abnormal excrement that is abnormal excrement is reflected in an image shown in the learning image data, an excrement property estimation learning model execution unit configured to use an excrement property estimation learning model, which is a machine learning model for estimating a probability that abnormal excrement is reflected in the learning image data, to estimate the probability that abnormal excrement is reflected in the image shown in the learning image data, and an update unit configured to update, on the basis of a difference between an estimation result from the excrement property estimation learning model execution unit and the correct label, the excrement property estimation learning model such that the difference is reduced.
-
公开(公告)号：US20240193796A1
公开(公告)日：2024-06-13
申请号：US18528447
申请日：2023-12-04
Applicant: NEC Corporation
Inventor： Katsuhiro YUTANI
CPC classification number: G06T7/251 , G06T7/521 , G06T7/564 , G06T2207/10028
Abstract: An acquisition means repeatedly acquires three-dimensional data of a monitoring target surface on a time axis. A deformation detection means detects, based on a plurality of pieces of the three-dimensional data, a first deformation occurring at a first time, and a second deformation occurring at a position different from an occurrence position of the first deformation at a second time being after the first time. A deformation prediction means predicts, based on a detection result by the deformation detection means, that a third deformation may occur in a future at a position different from occurrence positions of the first deformation and the second deformation.
-
公开(公告)号：US11819359B2
公开(公告)日：2023-11-21
申请号：US17409411
申请日：2021-08-23
Applicant: JointVue, LLC
Inventor： Mohamed R. Mahfouz , Ray C. Wasielewski
CPC classification number: A61B8/0875 , A61B8/14 , A61B8/5207 , A61B8/5223 , G06T7/564 , G06T17/00 , A61B8/4245 , G06T2207/10028 , G06T2207/10136 , G06T2207/30008 , G06T2210/41
Abstract: Methods and apparatus for treating a patient. The method includes acquiring a plurality of radio frequency (RF) signals with an ultrasound transducer, each RF signal representing one or more return echoes from a scan line of a pulse-mode echo ultrasound scan. A position of the ultrasound transducer corresponding to each of the acquired RF signals is determined, and a plurality of contour lines generated from the plurality of RF signals. The method estimates a 3-D shape and position of an anatomical feature, such as a joint of patient based on the generated contour lines and corresponding ultrasound transducer positions. An apparatus, or computer includes a processor and a memory with instructions that, when executed by the processor, perform the aforementioned method.
-
公开(公告)号：US11748891B2
公开(公告)日：2023-09-05
申请号：US17799010
申请日：2021-02-26
Inventor： Junming Hong , Huan Chen
IPC: G06T7/12 , G06T7/521 , B65G69/24 , B65G69/26 , B66C13/18 , G06T7/10 , G06V30/19 , G06T7/543 , G06T7/564 , B65G67/04
CPC classification number: G06T7/12 , B65G69/24 , B65G69/26 , B66C13/18 , G06T7/10 , G06T7/521 , G06T7/543 , G06T7/564 , G06V30/19127 , B65G67/04
Abstract: The present invention provides an automatic container loading and unloading apparatus and method. The apparatus comprises: a data acquisition module, used for scanning a container truck panel to obtain laser point cloud data; a data preprocessing module, used for segmenting a laser point cloud on a surface of the container truck panel from the laser point cloud data; a key point extraction module, used for performing edge extraction on the laser point cloud on the surface of the container truck panel to obtain discrete points on edges of the keel of the container truck panel; and a straight line fitting module, used for performing random sample consensus straight line fitting on the discrete points on the edges of the keel of the container truck panel to obtain spatial straight lines of the edges of the keel of the truck panel. The automatic container loading and unloading apparatus and method provided by the present invention using spatial straight lines on the edges of the keel of the container truck panel for computing processing, thereby achieving stronger robustness and higher accuracy, so that a container is loaded onto the container truck panel with higher precision and lower calculation amount.
-
公开(公告)号：US11712306B2
公开(公告)日：2023-08-01
申请号：US16922823
申请日：2020-07-07
Applicant: Neuralink Corp.
Inventor： Gilbert I. Montague
IPC: A61B34/30 , A61B5/00 , A61B90/00 , A61B90/11 , A61B90/30 , A61N1/05 , A61N1/36 , G06T5/00 , G06T7/11 , G06T7/12 , G06T7/187 , G06T7/564 , A61B34/20
CPC classification number: A61B34/20 , A61B34/30 , G06T7/12 , A61B2090/309 , A61B2090/3735 , G06T2207/10101 , G06T2207/30016
Abstract: Disclosed are methods related to guiding robotic surgery using optical coherence tomography (OCT) and computer-readable media and computer systems executing the methods. They may include receiving a series of cross-sectional slices of 3D space obtained from an OCT probe over biological tissue and processing and filtering the series of slices. The processing and filtering may include spatially smoothing the intensity values of each slice, thresholding each slice after it has been blurred, performing a connected-component analysis to identify blobs on the thresholded slice, filtering the blobs, performing edge detection, and invoking a selective median filter. The processing and filtering can be used to construct a depth map from the received series of cross-sectional slices in order to guide a robotic end effector, based on the depth map.
-
-
-
-
-
-
-
-
-
Search Results
253
records
(took 0.021 seconds)
