公开(公告)号：US12072442B2

公开(公告)日：2024-08-27

申请号：US17456045

申请日：2021-11-22

Applicant: NVIDIA Corporation

Inventor： Tommi Koivisto ,  Pekka Janis ,  Tero Kuosmanen ,  Timo Roman ,  Sriya Sarathy ,  William Zhang ,  Nizar Assaf ,  Colin Tracey

IPC: G06V10/46 ,  B60W50/00 ,  G01S7/41 ,  G05D1/00 ,  G06F16/35 ,  G06F18/21 ,  G06F18/214 ,  G06F18/23 ,  G06F18/2413 ,  G06N3/044 ,  G06N3/045 ,  G06N3/084 ,  G06N20/00 ,  G06V10/20 ,  G06V10/44 ,  G06V10/762 ,  G06V10/764 ,  G06V10/77 ,  G06V10/774 ,  G06V20/58 ,  G01S7/48 ,  G01S13/86 ,  G01S13/931 ,  G01S17/931 ,  G06N3/047 ,  G06N3/048

CPC classification number: G01S7/417 ,  B60W50/00 ,  G05D1/0246 ,  G06F16/35 ,  G06F18/214 ,  G06F18/217 ,  G06F18/23 ,  G06F18/2414 ,  G06N3/044 ,  G06N3/045 ,  G06N3/084 ,  G06N20/00 ,  G06V10/255 ,  G06V10/454 ,  G06V10/46 ,  G06V10/762 ,  G06V10/764 ,  G06V10/7715 ,  G06V10/774 ,  G06V20/58 ,  G06V20/584 ,  G01S7/412 ,  G01S7/4802 ,  G01S13/867 ,  G01S2013/9318 ,  G01S2013/9323 ,  G01S17/931 ,  G06N3/047 ,  G06N3/048

Abstract: In various examples, detected object data representative of locations of detected objects in a field of view may be determined. One or more clusters of the detected objects may be generated based at least in part on the locations and features of the cluster may be determined for use as inputs to a machine learning model(s). A confidence score, computed by the machine learning model(s) based at least in part on the inputs, may be received, where the confidence score may be representative of a probability that the cluster corresponds to an object depicted at least partially in the field of view. Further examples provide approaches for determining ground truth data for training object detectors, such as for determining coverage values for ground truth objects using associated shapes, and for determining soft coverage values for ground truth objects.

公开(公告)号：US12046026B2

公开(公告)日：2024-07-23

申请号：US17831818

申请日：2022-06-03

Applicant: PACKSIZE LLC

Inventor： Paolo Di Febbo ,  Carlo Dal Mutto ,  Kinh Tieu

IPC: G06V10/44 ,  G06F18/214 ,  G06F18/2413 ,  G06N3/045 ,  G06N3/084 ,  G06T7/00 ,  G06T7/246 ,  G06V10/46 ,  G06V10/75 ,  G06V10/764 ,  G06V10/82 ,  G06N3/063 ,  H04N5/33

CPC classification number: G06V10/82 ,  G06F18/214 ,  G06F18/2414 ,  G06N3/045 ,  G06N3/084 ,  G06T7/001 ,  G06T7/246 ,  G06V10/44 ,  G06V10/454 ,  G06V10/462 ,  G06V10/757 ,  G06V10/764 ,  G06N3/063 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/10048 ,  G06T2207/20081 ,  G06T2207/20084 ,  H04N5/33

Abstract: A keypoint detection system includes: a camera system including at least one camera; and a processor and memory, the processor and memory being configured to: receive an image captured by the camera system; compute a plurality of keypoints in the image using a convolutional neural network including: a first layer implementing a first convolutional kernel; a second layer implementing a second convolutional kernel; an output layer; and a plurality of connections between the first layer and the second layer and between the second layer and the output layer, each of the connections having a corresponding weight stored in the memory; and output the plurality of keypoints of the image computed by the convolutional neural network.

公开(公告)号：US11875557B2

公开(公告)日：2024-01-16

申请号：US16976409

申请日：2019-04-29

Applicant: CARNEGIE MELLON UNIVERSITY

Inventor： Felix Juefei Xu ,  Marios Savvides

IPC: G06V10/82 ,  G06N3/084 ,  G06N3/08 ,  G06V10/44 ,  G06F18/21 ,  G06F18/25 ,  G06F18/2135 ,  G06N3/048 ,  G06F18/2413 ,  G06N3/045

CPC classification number: G06V10/82 ,  G06F18/21 ,  G06F18/21355 ,  G06F18/2414 ,  G06F18/253 ,  G06N3/045 ,  G06N3/048 ,  G06N3/08 ,  G06N3/084 ,  G06V10/454

Abstract: The invention proposes a method of training a convolutional neural network in which, at each convolution layer, weights for one seed convolutional filter per layer are updated during each training iteration. All other convolutional filters are polynomial transformations of the seed filter, or, alternatively, all response maps are polynomial transformations of the response map generated by the seed filter.

公开(公告)号：US11687834B2

公开(公告)日：2023-06-27

申请号：US17131341

申请日：2020-12-22

Applicant: Gabriel Fine ,  Nathan Silberman

Inventor： Gabriel Fine ,  Nathan Silberman

IPC: G06T7/70 ,  G06N20/00 ,  G06T7/00 ,  A61B34/10 ,  A61B34/20 ,  G16H30/20 ,  G06T7/73 ,  G16H50/50 ,  G16H40/63 ,  G16H30/40 ,  G06N3/08 ,  G06F18/2413 ,  G06N3/044 ,  G06N3/045 ,  G06V30/19 ,  G06V10/82 ,  A61B90/00 ,  A61F2/01

CPC classification number: G06N20/00 ,  A61B34/10 ,  A61B34/20 ,  G06F18/2414 ,  G06N3/044 ,  G06N3/045 ,  G06N3/08 ,  G06T7/0016 ,  G06T7/70 ,  G06T7/75 ,  G06V10/82 ,  G06V30/19173 ,  G16H30/20 ,  G16H30/40 ,  G16H40/63 ,  G16H50/50 ,  A61B2034/102 ,  A61B2034/2051 ,  A61B2034/2065 ,  A61B2090/367 ,  A61B2090/376 ,  A61F2/01 ,  A61F2/0105 ,  G06T2207/10072 ,  G06T2207/10081 ,  G06T2207/10088 ,  G06T2207/10116 ,  G06T2207/10121 ,  G06T2207/10132 ,  G06T2207/20084 ,  G06T2207/30021

Abstract: A system and method is disclosed for displaying augmented image data for invasive medical devices. A current orientation and a current position of the invasive medical device within a patient can be determined by applying a trained model of the invasive medical device to unannotated images of the invasive medical device as captured by an imaging device. The images of the invasive medical device can be displayed and overlaid with the current orientation and current position of the invasive medical device. User input can be received to initialize tracking of an orientation and a position of the invasive medical device as the invasive medical device is moved within the patient.

公开(公告)号：US12062426B2

公开(公告)日：2024-08-13

申请号：US17200554

申请日：2021-03-12

Applicant: EchoNous, Inc.

Inventor： Nikolaos Pagoulatos ,  Ramachandra Pailoor ,  Kevin Goodwin

IPC: G16H30/20 ,  G16H50/20 ,  G16H30/40 ,  G06K9/62 ,  A61B8/00 ,  A61B8/08 ,  G06V10/44 ,  G06F18/2413 ,  G06V10/764 ,  G06V10/82 ,  G06F3/04842 ,  G06T7/00 ,  G06F3/04845

CPC classification number: G16H30/20 ,  A61B8/46 ,  A61B8/461 ,  A61B8/469 ,  A61B8/5215 ,  A61B8/5223 ,  A61B8/565 ,  G06F3/04842 ,  G06F18/2414 ,  G06T7/0012 ,  G06V10/454 ,  G06V10/764 ,  G06V10/82 ,  G16H30/40 ,  G16H50/20 ,  G06F3/04845 ,  G06T2200/24 ,  G06T2207/10132 ,  G06V2201/031

Abstract: Ultrasound image recognition systems and methods, and artificial intelligence training networks for such systems and methods, are provided. An ultrasound data information system includes an ultrasound image recognition training network that is configured to receive ultrasound training images and to develop ultrasound image knowledge based on the received ultrasound training images. An ultrasound imaging device acquires ultrasound images of a patient, and the device includes an ultrasound image recognition module. The ultrasound image recognition module is configured to receive the ultrasound image knowledge, receive the acquired ultrasound images from the ultrasound imaging device, and determine, based on the ultrasound image knowledge, whether the received ultrasound images represent a clinically desirable view of an organ or whether the clinically desirable views indicate normal function or a particular pathology. The received ultrasound images are transmitted to the ultrasound image recognition training network for further training and development of updated ultrasound image knowledge.

公开(公告)号：US20240192320A1

公开(公告)日：2024-06-13

申请号：US18582358

申请日：2024-02-20

Applicant: NVIDIA Corporation

Inventor： Tommi Koivisto ,  Pekka Janis ,  Tero Kuosmanen ,  Timo Roman ,  Sriya Sarathy ,  William Zhang ,  Nizar Assaf ,  Colin Tracey

IPC: G01S7/41 ,  B60W50/00 ,  G01S7/48 ,  G01S13/86 ,  G01S13/931 ,  G01S17/931 ,  G06F16/35 ,  G06F18/21 ,  G06F18/214 ,  G06F18/23 ,  G06F18/2413 ,  G06N3/044 ,  G06N3/045 ,  G06N3/047 ,  G06N3/048 ,  G06N3/084 ,  G06N20/00 ,  G06V10/20 ,  G06V10/44 ,  G06V10/46 ,  G06V10/762 ,  G06V10/764 ,  G06V10/77 ,  G06V10/774 ,  G06V20/58

CPC classification number: G01S7/417 ,  B60W50/00 ,  G06F16/35 ,  G06F18/214 ,  G06F18/217 ,  G06F18/23 ,  G06F18/2414 ,  G06N3/044 ,  G06N3/045 ,  G06N3/084 ,  G06N20/00 ,  G06V10/255 ,  G06V10/454 ,  G06V10/46 ,  G06V10/762 ,  G06V10/764 ,  G06V10/7715 ,  G06V10/774 ,  G06V20/58 ,  G06V20/584 ,  G01S7/412 ,  G01S7/4802 ,  G01S13/867 ,  G01S2013/9318 ,  G01S2013/9323 ,  G01S17/931 ,  G06N3/047 ,  G06N3/048

Abstract: In various examples, detected object data representative of locations of detected objects in a field of view may be determined. One or more clusters of the detected objects may be generated based at least in part on the locations and features of the cluster may be determined for use as inputs to a machine learning model(s). A confidence score, computed by the machine learning model(s) based at least in part on the inputs, may be received, where the confidence score may be representative of a probability that the cluster corresponds to an object depicted at least partially in the field of view. Further examples provide approaches for determining ground truth data for training object detectors, such as for determining coverage values for ground truth objects using associated shapes, and for determining soft coverage values for ground truth objects.

公开(公告)号：US12008758B2

公开(公告)日：2024-06-11

申请号：US17952234

申请日：2022-09-24

Applicant: PSIP LLC

Inventor： Salmaan Hameed ,  Giau Nguyen

IPC: G06T7/00 ,  A61B1/00 ,  G01B11/03 ,  G01B11/30 ,  G06F18/2413 ,  G06V10/44 ,  G06V10/50 ,  G06V10/764 ,  G06V10/82

CPC classification number: G06T7/0014 ,  A61B1/000094 ,  A61B1/000096 ,  A61B1/0014 ,  A61B1/00177 ,  A61B1/00181 ,  G01B11/03 ,  G01B11/30 ,  G06V10/454 ,  G06V10/50 ,  G06V10/764 ,  G06V10/82 ,  A61B1/00101 ,  G06F18/2414 ,  G06T2207/10068 ,  G06T2207/30032 ,  G06V2201/032 ,  G06V2201/034

Abstract: Identifying polyps or lesions in a colon. In some variations, computer-implemented methods for polyp detection may be used in conjunction with an endoscope system to analyze the images captured by the endoscopic system, identify any polyps and/or lesions in a visual scene captured by the endoscopic system, and provide an indication to the practitioner that a polyp and/or lesion has been detected.

公开(公告)号：US20240020951A1

公开(公告)日：2024-01-18

申请号：US18352168

申请日：2023-07-13

Applicant: Blue River Technology Inc.

Inventor： Lee Kamp Redden ,  Christopher Grant Padwick ,  Rajesh Radhakrishnan ,  James Patrick Ostrowski

IPC: G06V10/764 ,  G06T7/00 ,  A01M7/00 ,  G06T7/73 ,  G06V20/10 ,  G06V10/20 ,  G06V10/44 ,  G06V20/20 ,  G06F18/2413

CPC classification number: G06V10/764 ,  G06T7/0002 ,  A01M7/0089 ,  G06T7/75 ,  G06V20/188 ,  G06V10/255 ,  G06V10/451 ,  G06V20/20 ,  G06F18/2414 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30188 ,  G06T2210/12 ,  G06T2207/20132 ,  G06T2207/10024

Abstract: A plant treatment platform uses a plant detection model to detect plants as the plant treatment platform travels through a field. The plant treatment platform receives image data from a camera that captures images of plants (e.g., crops or weeds) growing in the field. The plant treatment platform applies pre-processing functions to the image data to prepare the image data for processing by the plant detection model. For example, the plant treatment platform may reformat the image data, adjust the resolution or aspect ratio, or crop the image data. The plant treatment platform applies the plant detection model to the pre-processed image data to generate bounding boxes for the plants. The plant treatment platform then can apply treatment to the plants based on the output of the machine-learned model.

公开(公告)号：US11748981B2

公开(公告)日：2023-09-05

申请号：US17731228

申请日：2022-04-27

Applicant: AstraZeneca Computational Pathology GmbH

Inventor： Guenter Schmidt ,  Nicolas Brieu ,  Ansh Kapil ,  Jan Martin Lesniak

IPC: G06V10/82 ,  G06T7/00 ,  G06V20/69 ,  G06V10/764 ,  G06T7/136 ,  G06T7/33 ,  G06T7/35 ,  G01N1/30 ,  G06F18/2413

CPC classification number: G06V10/82 ,  G01N1/30 ,  G06F18/2414 ,  G06T7/0012 ,  G06T7/136 ,  G06T7/337 ,  G06T7/35 ,  G06V10/764 ,  G06V20/695 ,  G06V20/698 ,  G01N2800/52 ,  G01N2800/7028 ,  G06T2207/20084 ,  G06T2207/30024 ,  G06T2207/30242

Abstract: A method for indicating how a cancer patient will respond to a predetermined therapy relies on spatial statistical analysis of classes of cell centers in a digital image of tissue of the cancer patient. The cell centers are detected in the image of stained tissue of the cancer patient. For each cell center, an image patch that includes the cell center is extracted from the image. A feature vector is generated based on each image patch using a convolutional neural network. A class is assigned to each cell center based on the feature vector associated with each cell center. A score is computed for the image of tissue by performing spatial statistical analysis based on classes of the cell centers. The score indicates how the cancer patient will respond to the predetermined therapy. The predetermined therapy is recommended to the patient if the score is larger than a predetermined threshold.

公开(公告)号：US11704576B1

公开(公告)日：2023-07-18

申请号：US17180695

申请日：2021-02-19

Applicant: ARVA INTELLIGENCE CORP.

Inventor： John A. McEntire ,  Thomas A. Dye

IPC: G06F11/30 ,  G06N5/01 ,  G06N20/00 ,  G06Q50/02 ,  G06F16/29 ,  G06F18/214 ,  G06F18/21 ,  G06F18/2413 ,  G06F18/243

CPC classification number: G06N5/01 ,  G06F16/29 ,  G06F18/214 ,  G06F18/217 ,  G06F18/2414 ,  G06F18/24323 ,  G06N20/00 ,  G06Q50/02

Abstract: A system and method for identifying ground types from one or more interpolated covariates. The method proceeds by accessing soil composition information for plots of land, in which the soil composition information includes measured soil sample results, environmental results, soil conductivity results or any combination thereof. The method continues by identifying covariates from the soil composition information. Subsequently, the method interpolates covariates associated with different locations with an interpolation training model. Voxels are generated that are each associated with interpolated covariates having a corresponding geographical location. The method trains a random forest training model with the interpolated covariates. The voxels traverse the trained random forest model to identify clusters of voxels that are co-associated. The method identifies a ground type by combining the co-associated clusters. Each ground type is associated with a crop zone, a soil fertility, or a farm management recommendation.