公开(公告)号：US20230215006A1

公开(公告)日：2023-07-06

申请号：US18111876

申请日：2023-02-20

申请人： SHENZHEN INSTITUTES OF ADVANCED TECHNOLOGY

发明人： SHUQIANG WANG ,  CHANGWEI GONG

IPC分类号： G06T7/00 ,  G06V10/44 ,  G06V10/62 ,  G06N3/094 ,  G01R33/56

CPC分类号： G06T7/0014 ,  G06V10/454 ,  G06V10/62 ,  G06N3/094 ,  G01R33/5608 ,  G06T2207/10088 ,  G06T2207/20076

摘要： A method and a system for generating a dynamic addictive neural circuit based on weakly supervised contrastive learning are disclosed. The method includes: based on a convolutional neural network, reducing a dimensionality of voxels of multiple groups of fMRI to attributes of brain region nodes, and generating multiple groups of dynamic brain connection maps containing time series based on the attributes of the brain region nodes; extracting spatio-temporal features of brain connections in the dynamic brain connection maps; inputting the spatio-temporal features into an abnormal connection detection network, calculating an abnormal probability of brain connections based on contrastive learning, and obtaining the brain connection with a highest abnormal probability at each time point; and generating the dynamic addictive neural circuit based on neuroscientific prior knowledge and the brain connection with the greatest probability of abnormality.

公开(公告)号：US20230145472A1

公开(公告)日：2023-05-11

申请号：US17594748

申请日：2020-04-09

申请人： Volkswagen Aktiengesellschaft

发明人： Sebastian Ehmann

IPC分类号： G06V20/58 ,  G06T7/70 ,  G06V10/62 ,  G06V10/98

CPC分类号： G06V20/58 ,  G06T7/70 ,  G06V10/62 ,  G06V10/98 ,  G06T2207/30241

摘要： Technologies and techniques for capturing image material for monitoring image-analyzing systems, wherein an object is monitored to determine if it has been correctly recognized by the image-analyzing system in respect of time or location. The images captured are recorded in a memory. When a discrepancy is determined, in object recognition beyond a tolerance limit over a temporal or locational reference, select images or image sections are archived for more precise inspection.

公开(公告)号：US20240346824A1

公开(公告)日：2024-10-17

申请号：US18634794

申请日：2024-04-12

申请人： Google LLC

发明人： Alexey Alexeevich Gritsenko ,  Xuehan Xiong ,  Josip Djolonga ,  Mostafa Dehghani ,  Chen Sun ,  Mario Lucic ,  Cordelia Luise Schmid ,  Anurag Arnab

IPC分类号： G06V20/40 ,  G06T7/73 ,  G06V10/62 ,  G06V10/764 ,  G06V10/77 ,  G06V10/774 ,  G06V10/776 ,  G06V10/82

CPC分类号： G06V20/46 ,  G06T7/73 ,  G06V10/62 ,  G06V10/764 ,  G06V10/7715 ,  G06V10/774 ,  G06V10/776 ,  G06V10/82 ,  G06T2207/10016 ,  G06T2207/20081 ,  G06T2207/20084

摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing action localization on an input video. In particular, a system maintains a set of query vectors and uses the input video and the set of query vectors to generate an action localization output for the input video. The action localization output includes, for each of one or more agents depicted in the video, data specifying, for each of one or more video frames in the video, a respective bounding box in the video frame that depicts the agent and a respective action from a set of actions that is being performed by the agent in the video frame.

公开(公告)号：US20240331416A1

公开(公告)日：2024-10-03

申请号：US18550267

申请日：2022-11-11

申请人： BOE TECHNOLOGY GROUP CO., LTD.

发明人： Yulan Hu ,  Zhenzhong Zhang ,  Xiaotian Jiang

IPC分类号： G06V20/69 ,  A61B5/00 ,  G06T7/00 ,  G06V10/62 ,  G06V10/70 ,  G06V10/77 ,  G06V10/774 ,  G06V10/80 ,  G06V20/50 ,  G16B40/20

CPC分类号： G06V20/698 ,  A61B5/0042 ,  G06T7/0016 ,  G06V10/62 ,  G06V10/7715 ,  G06V10/774 ,  G06V10/806 ,  G06V10/87 ,  G06V20/50 ,  G16B40/20 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30016 ,  G06T2207/30096 ,  G06V2201/03

摘要： The present disclosure provides a method of processing medical data, which includes: acquiring first medical image data; inputting the first medical image data into a first feature extraction network to obtain a first image feature; and obtaining a first gene mutation information according to the first image feature. The first feature extraction network includes a first feature extraction module configured to: determine a first image query matrix and a first image key matrix according to the first medical image data; determine a first image weight matrix according to the first image query matrix and the first image key matrix, where the first image weight matrix represents a correlation information between each two first medical images in the first medical image data; and determine the first image feature according to the first image weight matrix and the first medical image data.

公开(公告)号：US12102469B2

公开(公告)日：2024-10-01

申请号：US18514345

申请日：2023-11-20

申请人： Jianqiang Liu ,  Manat Maolinbay ,  Chwen-yuan Ku ,  Linbo Yang

发明人： Jianqiang Liu ,  Manat Maolinbay ,  Chwen-yuan Ku ,  Linbo Yang

IPC分类号： A61B6/00 ,  A61B6/02 ,  A61B6/03 ,  A61B6/04 ,  A61B6/06 ,  A61B6/08 ,  A61B6/40 ,  A61B6/42 ,  A61B6/46 ,  A61B6/58 ,  G01N23/044 ,  G01N23/083 ,  G01N23/18 ,  G06T7/00 ,  G06T7/11 ,  G06T11/00 ,  G06T17/00 ,  G06V10/25 ,  G06V10/62 ,  G16H10/60 ,  G16H30/20 ,  G16H50/20 ,  A61B6/50

CPC分类号： A61B6/541 ,  A61B6/025 ,  A61B6/032 ,  A61B6/035 ,  A61B6/0407 ,  A61B6/06 ,  A61B6/08 ,  A61B6/4007 ,  A61B6/4014 ,  A61B6/4021 ,  A61B6/405 ,  A61B6/4208 ,  A61B6/4283 ,  A61B6/4405 ,  A61B6/4441 ,  A61B6/4452 ,  A61B6/4476 ,  A61B6/4482 ,  A61B6/467 ,  A61B6/482 ,  A61B6/54 ,  A61B6/542 ,  A61B6/56 ,  A61B6/583 ,  G01N23/044 ,  G01N23/083 ,  G01N23/18 ,  G06T7/0012 ,  G06T7/0016 ,  G06T7/11 ,  G06T11/003 ,  G06T11/006 ,  G06T17/00 ,  G06V10/25 ,  G06V10/62 ,  G16H10/60 ,  G16H30/20 ,  G16H50/20 ,  A61B6/4275 ,  A61B6/502 ,  G01N2223/401 ,  G06T2200/24 ,  G06T2207/10076 ,  G06T2207/10081 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30064 ,  G06T2207/30096 ,  G06T2207/30168 ,  G06T2210/41 ,  G06V2201/032

摘要： An X-ray imaging system using multiple pulsed X-ray sources to perform highly efficient and ultrafast 3D radiography is presented. There are multiple pulsed X-ray sources mounted on a structure in motion to form an array of sources. The multiple X-ray sources move simultaneously relative to an object on a pre-defined arc track at a constant speed as a group. Electron beam inside each individual X-ray tube is deflected by magnetic or electrical field to move focal spot a small distance. When focal spot of an X-ray tube beam has a speed that is equal to group speed but with opposite moving direction, the X-ray source and X-ray flat panel detector are activated through an external exposure control unit so that source tube stay momentarily standstill equivalently. 3D scan can cover much wider sweep angle in much shorter time and image analysis can also be done in real-time.

公开(公告)号：US12092733B2

公开(公告)日：2024-09-17

申请号：US17551644

申请日：2021-12-15

申请人： GM Global Technology Operations LLC

发明人： Yuri Owechko ,  Qin Jiang

IPC分类号： G01S13/90 ,  G01S13/50 ,  G06V10/62 ,  G06V10/74 ,  G06V10/762 ,  G06V10/80

CPC分类号： G01S13/9027 ,  G01S13/505 ,  G01S13/9011 ,  G06V10/62 ,  G06V10/761 ,  G06V10/762 ,  G06V10/809

摘要： A radar anti-spoofing system for an autonomous vehicle includes a plurality of radar sensors that generate a plurality of input detection points representing radio frequency (RF) signals reflected from objects and a controller in electronic communication with the plurality of radar sensors. The controller executes instructions to determine time-matched clusters that represent objects located in an environment surrounding the autonomous vehicle based on the input detection points from the plurality of radar sensors. The controller determines an adjusted signal to noise (SNR) measure for a specific time-matched cluster by dividing an SNR of the specific time-matched cluster by a range measurement of the specific time-matched cluster. The controller determines a velocity-ratio measure of the time-matched cluster by dividing a motion-based velocity by a Doppler-frequency velocity, and identifies the time-matched cluster as either a ghost object or a real object.

公开(公告)号：US12032972B2

公开(公告)日：2024-07-09

申请号：US17829315

申请日：2022-05-31

申请人： Intel Corporation

发明人： Anatoly Litvinov ,  Ilya Sister ,  Andrey Semenjatshenco ,  Nir Gerber

IPC分类号： G06F1/24 ,  G06F1/3296 ,  G06F9/00 ,  G06F9/445 ,  G06F11/34 ,  G06V10/62 ,  G06V10/74 ,  G06V10/75

CPC分类号： G06F9/44505 ,  G06F1/3296 ,  G06F11/3409 ,  G06V10/62 ,  G06V10/761 ,  G06V10/758

摘要： Methods, apparatus, systems, and articles of manufacture are disclosed to improve performance of a compute device by detecting a scene change. An example apparatus includes scene change detection circuitry and interrupt circuitry. The example scene change detection circuitry is to determine a first score value for a first metric of similarity between a first image of a field of view (FOV) of an image sensor and a second image of the FOV, determine a second score value for a second metric of similarity between the first image and the second image, and compute a composite score value based on the first score value and the second score value. The example interrupt circuitry is to generate an interrupt to processor circuitry of the compute device to cause the processor circuitry to adjust a computation condition of the compute device based on the composite score.

公开(公告)号：US12008768B2

公开(公告)日：2024-06-11

申请号：US17055108

申请日：2019-09-24

申请人： Visual Robotics Systems Inc.

发明人： Bryan Lee Olmstead

IPC分类号： G06T7/20 ,  B25J9/16 ,  G06T7/55 ,  G06V10/62 ,  G06V10/75

CPC分类号： G06T7/20 ,  B25J9/1697 ,  G06T7/55 ,  G06V10/751 ,  G06V10/62

摘要： Mobile apparatus (e.g., robotic systems and mobile vehicles) use one or more cameras fixed to the apparatus so that the cameras move when the mobile apparatus moves. The cameras acquire images of the world space in which the apparatus operates, and the images are processed to develop information about objects sharing the world space with the mobile apparatus. This information permits a control system to direct the apparatus to interact with (or avoid) the objects.

公开(公告)号：US20240177486A1

公开(公告)日：2024-05-30

申请号：US18057691

申请日：2022-11-21

申请人： Lemon Inc. ,  Beijing Zitiao Network Technology Co., Ltd.

发明人： Xiaojie JIN ,  Sen PEI

IPC分类号： G06V20/40 ,  G06V10/62 ,  G06V10/774 ,  G06V10/776 ,  G06V10/80 ,  G06V10/82

CPC分类号： G06V20/46 ,  G06V10/62 ,  G06V10/774 ,  G06V10/776 ,  G06V10/806 ,  G06V10/82 ,  G06V20/41

摘要： Systems and methods are provided that include a processor executing a video classifying program to receive an input video, sample video frames from the input video, extract frame-wise spatial features from the video frames using a convolutional neural network, extract a frame-wise temporal feature for each video frame, aggregate the frame-wise spatial features and the frame-wise temporal feature for each video frame to provide a temporal context to the frame-wise spatial features, input the aggregated frame-wise spatial features and the frame-wise temporal feature for each frame into a transformer encoder to obtain temporal-aware feature representations of the video frames, input the feature representations into a feedforward network model to obtain feedforward-transformed features, obtain a parameter by inputting each feedforward-transformed feature and a set of highlight prototypes into a function comparing the feedforward-transformed features to the set of highlight prototypes, classify the video frames as highlights based on the calculated parameter.

公开(公告)号：US11987272B2

公开(公告)日：2024-05-21

申请号：US17190619

申请日：2021-03-03

申请人： Perceptive Automata, Inc.

发明人： Samuel English Anthony ,  Kshitij Misra ,  Avery Wagner Faller

IPC分类号： G06N3/08 ,  B60W30/00 ,  B60W60/00 ,  G05D1/00 ,  G06F18/214 ,  G06F18/40 ,  G06N3/04 ,  G06N3/084 ,  G06V10/778 ,  G06V20/40 ,  G06V20/58 ,  G06V40/20 ,  G08G1/04 ,  G08G1/16 ,  G06N5/01 ,  G06N20/10 ,  G06V10/62

CPC分类号： B60W60/00274 ,  B60W30/00 ,  G05D1/0088 ,  G06F18/214 ,  G06F18/41 ,  G06N3/04 ,  G06N3/08 ,  G06N3/084 ,  G06V10/7784 ,  G06V20/41 ,  G06V20/58 ,  G06V40/20 ,  G08G1/04 ,  G08G1/166 ,  G05D2201/0213 ,  G06N5/01 ,  G06N20/10 ,  G06V10/62

摘要： Systems and methods for predicting user interaction with vehicles. A computing device receives an image and a video segment of a road scene, the first at least one of an image and a video segment being taken from a perspective of a participant in the road scene and then generates stimulus data based on the image and the video segment. Stimulus data is transmitted to a user interface and response data is received, which includes at least one of an action and a likelihood of the action corresponding to another participant in the road scene. The computing device aggregates a subset of the plurality of response data to form statistical data and a model is created based on the statistical data. The model is applied to another image or video segment and a prediction of user behavior in the another image or video segment is generated.