公开(公告)号：US12112248B2

公开(公告)日：2024-10-08

申请号：US18488010

申请日：2023-10-16

Applicant: Torc CND Robotics, Inc.

Inventor： Felix Heide

IPC: G06N20/00 ,  G06F18/241 ,  G06F18/2413 ,  G06N3/045 ,  G06N3/084 ,  G06T5/00 ,  G06T5/50 ,  G06T5/73 ,  G06V10/44 ,  G06V10/764 ,  G06V10/82

CPC classification number: G06N20/00 ,  G06F18/241 ,  G06F18/24133 ,  G06N3/045 ,  G06N3/084 ,  G06T5/00 ,  G06T5/50 ,  G06T5/73 ,  G06V10/454 ,  G06V10/764 ,  G06V10/82 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20182

Abstract: System and method for end-to-end differentiable joint image refinement and perception are provided. A learning machine employs an image acquisition device for acquiring a set of training raw images. A processor determines a representation of a raw image, initializes a set of image representation parameters, defines a set of analysis parameters of an image analysis network configured to process the image's representation, and jointly trains the set of representation parameters and the set of analysis parameters to optimize a combined objective function. A module for transforming pixel-values of the raw image to produce a transformed image comprising pixels of variance-stabilized values, a module for successively performing processes of soft camera projection and image projection, and a module for inverse transforming the transformed pixels are disclosed. The image projection performs multi-level spatial convolution, pooling, subsampling, and interpolation.

公开(公告)号：US12087044B2

公开(公告)日：2024-09-10

申请号：US18202941

申请日：2023-05-28

Applicant: GOLDEN EDGE HOLDING CORPORATION

Inventor： Tarek El Dokor

IPC: G06F18/21 ,  G06F18/24 ,  G06F18/2413 ,  G06N3/02 ,  G06V10/764 ,  G06V10/776 ,  G06V20/10 ,  G06V20/52 ,  G06V40/16 ,  G06V40/20 ,  H04N5/33

CPC classification number: G06V10/776 ,  G06F18/217 ,  G06F18/24 ,  G06F18/24133 ,  G06N3/02 ,  G06V10/764 ,  G06V20/10 ,  G06V20/52 ,  G06V40/16 ,  G06V40/20 ,  H04N5/33

Abstract: A method and apparatus for processing image data is provided. The method includes the steps of employing a main processing network for classifying one or more features of the image data, employing a monitor processing network for determining one or more confusing classifications of the image data, and spawning a specialist processing network to process image data associated with the one or more confusing classifications.

公开(公告)号：US20240290201A1

公开(公告)日：2024-08-29

申请号：US18659547

申请日：2024-05-09

Applicant: NETRADYNE, INC.

Inventor： David Jonathan JULIAN ,  Avneesh AGRAWAL

IPC: G08G1/04 ,  B60W40/09 ,  G06F18/2413 ,  G06V10/40 ,  G06V10/764 ,  G06V10/82 ,  G06V20/40 ,  G06V20/56 ,  G06V20/58 ,  G06V20/59 ,  G07C5/08 ,  G08G1/01

CPC classification number: G08G1/04 ,  G06F18/24133 ,  G06V10/40 ,  G06V10/764 ,  G06V10/82 ,  G06V20/56 ,  G06V20/58 ,  G06V20/597 ,  G07C5/0808 ,  G07C5/0866 ,  G08G1/0112 ,  G08G1/0133 ,  B60W40/09 ,  B60W2420/403 ,  G06V20/44

Abstract: Systems and methods provide, implement, and use using a computer-vision based methods of context-sensitive monitoring and characterization of driver behavior. Additional systems and methods are provided for unsupervised learning of action values, monitoring of a driver's environment, and transmitting visual information from a client to a server.

公开(公告)号：US20240070546A1

公开(公告)日：2024-02-29

申请号：US18488010

申请日：2023-10-16

Applicant: Torc CND Robotics, Inc.

Inventor： Felix Heide

IPC: G06N20/00 ,  G06F18/241 ,  G06F18/2413 ,  G06N3/045 ,  G06N3/084 ,  G06T5/00 ,  G06T5/50 ,  G06V10/44 ,  G06V10/764 ,  G06V10/82

CPC classification number: G06N20/00 ,  G06F18/241 ,  G06F18/24133 ,  G06N3/045 ,  G06N3/084 ,  G06T5/001 ,  G06T5/003 ,  G06T5/50 ,  G06V10/454 ,  G06V10/764 ,  G06V10/82 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20182

Abstract: System and method for end-to-end differentiable joint image refinement and perception are provided. A learning machine employs an image acquisition device for acquiring a set of training raw images. A processor determines a representation of a raw image, initializes a set of image representation parameters, defines a set of analysis parameters of an image analysis network configured to process the image's representation, and jointly trains the set of representation parameters and the set of analysis parameters to optimize a combined objective function. A module for transforming pixel-values of the raw image to produce a transformed image comprising pixels of variance-stabilized values, a module for successively performing processes of soft camera projection and image projection, and a module for inverse transforming the transformed pixels are disclosed. The image projection performs multi-level spatial convolution, pooling, subsampling, and interpolation.

公开(公告)号：US11900660B2

公开(公告)日：2024-02-13

申请号：US16175362

申请日：2018-10-30

Applicant: TERUMO KABUSHIKI KAISHA

Inventor： Yoshiyuki Saito ,  Shota Ishii ,  Yoshitaka Itou ,  Tetsuya Fukuoka

IPC: G06V10/82 ,  A61B5/02 ,  A61B8/08 ,  A61B5/00 ,  A61B6/00 ,  A61B17/00 ,  G16H30/40 ,  G16H20/40 ,  G16H50/20 ,  G06F18/21 ,  A61B5/05 ,  G06V10/44 ,  G06F18/2413 ,  G06V10/764 ,  G06V40/14

CPC classification number: G06V10/82 ,  A61B5/0075 ,  A61B5/02007 ,  A61B5/7267 ,  A61B6/504 ,  A61B6/5217 ,  A61B8/0891 ,  A61B8/5223 ,  A61B17/00234 ,  G06F18/217 ,  G06F18/24133 ,  G06V10/454 ,  G06V10/764 ,  G16H20/40 ,  G16H30/40 ,  G16H50/20 ,  A61B5/05 ,  A61B2017/00292 ,  G06V40/14 ,  G06V2201/03

Abstract: A method for diagnosing, validation of diagnosis and treating a patient having lesions in both arteries of left and right lower limbs. By determining that a larger vessel diameter lesion to be treated first, catheters and an operation time can be reduced is to be treated first on a priority basis based on diagnostic data, deciding that a smaller vessel diameter lesion is to be treated next, then treating the lesions substantially continuously.

公开(公告)号：US11887360B2

公开(公告)日：2024-01-30

申请号：US17497287

申请日：2021-10-08

Applicant: Intel Corporation

Inventor： Shao-Wen Yang ,  Eve M. Schooler ,  Maruti Gupta Hyde ,  Hassnaa Moustafa ,  Katalin Klara Bartfai-Walcott ,  Yen-Kuang Chen ,  Jessica McCarthy ,  Christina R. Strong ,  Arun Raghunath ,  Deepak S. Vembar

IPC: G06V10/82 ,  G06F9/50 ,  G06F21/60 ,  G06V10/44 ,  G06V20/52 ,  G06V40/10 ,  G06F18/241 ,  G06V10/764 ,  G06Q50/26 ,  G08G1/09 ,  G11B27/031 ,  H04N7/18 ,  G08G1/087 ,  G06F9/48 ,  G06F21/62 ,  G06F18/2413 ,  G08G1/01

CPC classification number: G06V10/82 ,  G06F9/4881 ,  G06F9/505 ,  G06F18/241 ,  G06F18/24133 ,  G06F21/604 ,  G06F21/6245 ,  G06Q50/26 ,  G06V10/44 ,  G06V10/764 ,  G06V20/52 ,  G06V40/103 ,  G08G1/091 ,  G11B27/031 ,  H04N7/181 ,  G06F2209/506 ,  G08G1/0116 ,  G08G1/087

Abstract: In one embodiment, an apparatus comprises a memory and a processor. The memory is to store sensor data captured by one or more sensors associated with a first device. Further, the processor comprises circuitry to: access the sensor data captured by the one or more sensors associated with the first device; determine that an incident occurred within a vicinity of the first device; identify a first collection of sensor data associated with the incident, wherein the first collection of sensor data is identified from the sensor data captured by the one or more sensors; preserve, on the memory, the first collection of sensor data associated with the incident; and notify one or more second devices of the incident, wherein the one or more second devices are located within the vicinity of the first device.

公开(公告)号：US11734390B2

公开(公告)日：2023-08-22

申请号：US17408441

申请日：2021-08-22

Applicant: Zhejiang University

Inventor： Jianwei Yin ,  Ge Su ,  Yongheng Shang ,  Yingchun Yang ,  Shuiguang Deng

IPC: G06N3/02 ,  G06F18/21 ,  G06N3/088 ,  G06F18/232 ,  G06F18/2132 ,  G06F18/214 ,  G06F18/2413

CPC classification number: G06F18/2193 ,  G06F18/2132 ,  G06F18/2155 ,  G06F18/232 ,  G06F18/24133 ,  G06N3/088

Abstract: The present disclosure discloses an unsupervised domain adaptation method, a device, a system and a storage medium of semantic segmentation based on uniform clustering; first, a prototype-based source domain uniform clustering loss and an empirical prototype-based target domain uniform clustering loss are established, to reduce intra-class differences of pixels responding to the same category; meanwhile, the pixels with similar structures but different classes are driven away from each other, wherein they tend to be evenly distributed, increasing the inter-class distance and overcoming the problem that the category boundaries are unclear during the domain adaptation process; next, the prototype-based source domain uniform clustering loss and the empirical prototype-based target domain uniform clustering loss are integrated into an adversarial training framework, which reduces the domain difference between the source domain and the target domain, thus improving the accuracy of semantic segmentation.

公开(公告)号：US20230186621A1

公开(公告)日：2023-06-15

申请号：US18107876

申请日：2023-02-09

Applicant: X Development LLC

Inventor： Ananya Gupta ,  Phillip Ellsworth Stahlfeld ,  Bangyan Chu

IPC: G06V20/10 ,  G06T7/50 ,  G06T7/73 ,  G06F30/18 ,  G06F16/587 ,  G06F16/29 ,  G06T5/30 ,  G06T7/60 ,  G06T11/20 ,  G06T17/05 ,  H02J3/00 ,  G06F18/2413

CPC classification number: G06V20/182 ,  G06F16/29 ,  G06F16/587 ,  G06F18/24133 ,  G06F30/18 ,  G06T5/30 ,  G06T7/50 ,  G06T7/60 ,  G06T7/73 ,  G06T7/75 ,  G06T11/206 ,  G06T17/05 ,  G06V20/176 ,  H02J3/00 ,  G06T2207/10032 ,  G06T2207/30184 ,  G06V20/194 ,  H02J2203/20

Abstract: Methods, systems, and apparatus, including computer programs encoded on a storage device, for electric grid asset detection are enclosed. An electric grid asset detection method includes: obtaining overhead imagery of a geographic region that includes electric grid wires; identifying the electric grid wires within the overhead imagery; and generating a polyline graph of the identified electric grid wires. The method includes replacing curves in polylines within the polyline graph with a series of fixed lines and endpoints; identifying, based on characteristics of the fixed lines and endpoints, a location of a utility pole that supports the electric grid wires; detecting an electric grid asset from street level imagery at the location of the utility pole; and generating a representation of the electric grid asset for use in a model of the electric grid.

公开(公告)号：US11670077B2

公开(公告)日：2023-06-06

申请号：US17093616

申请日：2020-11-09

Applicant: Butterfly Network, Inc.

Inventor： Tomer Gafner ,  Matthew de Jonge ,  Robert Schneider ,  David Elgena ,  Alex Rothberg ,  Jonathan M. Rothberg ,  Michal Sofka ,  Karl Thiele ,  Abraham Neben

IPC: G06V10/82 ,  A61B8/06 ,  A61B8/02 ,  G06T7/70 ,  G06T11/60 ,  A61B8/08 ,  G06V10/44 ,  G06V40/60 ,  G06F18/2413 ,  G06V30/19 ,  G06V30/194 ,  A61B8/00 ,  G06T19/00 ,  G06T7/00 ,  A61B90/00 ,  A61B34/20

CPC classification number: G06V10/82 ,  A61B8/02 ,  A61B8/06 ,  A61B8/065 ,  A61B8/085 ,  A61B8/4427 ,  A61B8/46 ,  A61B8/52 ,  A61B8/5207 ,  A61B8/5223 ,  G06F18/24133 ,  G06T7/0012 ,  G06T7/0014 ,  G06T7/70 ,  G06T11/60 ,  G06T19/006 ,  G06V10/454 ,  G06V30/194 ,  G06V30/19173 ,  G06V40/67 ,  A61B8/0833 ,  A61B8/0883 ,  A61B8/4263 ,  A61B8/463 ,  A61B8/5215 ,  A61B2034/2065 ,  A61B2090/365 ,  A61B2090/378 ,  A61B2090/3937 ,  G06T2207/10132 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20221 ,  G06T2207/30048 ,  G06T2207/30061 ,  G06T2210/41 ,  G06V2201/03

Abstract: Aspects of the technology described herein relate to techniques for guiding an operator to use an ultrasound device. Thereby, operators with little or no experience operating ultrasound devices may capture medically relevant ultrasound images and/or interpret the contents of the obtained ultrasound images. For example, some of the techniques disclosed herein may be used to identify a particular anatomical view of a subject to image with an ultrasound device, guide an operator of the ultrasound device to capture an ultrasound image of the subject that contains the particular anatomical view, and/or analyze the captured ultrasound image to identify medical information about the subject.

公开(公告)号：US11645365B2

公开(公告)日：2023-05-09

申请号：US16731695

申请日：2019-12-31

Applicant: INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTE

Inventor： Shien-Chun Luo ,  Po-Wei Chen

IPC: G06F9/38 ,  G06N3/08 ,  G06F18/2413 ,  G06F9/30 ,  G06F1/3203 ,  G06T3/40

CPC classification number: G06F18/24133 ,  G06F1/3203 ,  G06F9/3005 ,  G06F9/3877 ,  G06N3/08 ,  G06T3/4046 ,  G06F2209/5011

Abstract: A convolutional neural network (CNN) operation accelerator comprising a first sub-accelerator and a second sub-accelerator is provided. The first sub-accelerator comprises I units of CNN processor cores, J units of element-wise & quantize processors, and K units of pool and nonlinear function processor. The second sub-accelerator comprises X units of CNN processor cores, Y units of first element-wise & quantize processors, and Z units of pool and nonlinear function processor. The above variables I˜K, X˜Z are all greater than 0, and at least one of the three relations, namely, “I is different from X”, “J is different from Y”, and “K is different from Z”, is satisfied. A to-be-performed CNN operation comprises a first partial CNN operation and a second partial CNN operation. The first sub-accelerator and the second sub-accelerator perform the first partial CNN operation and the second partial CNN operation, respectively.