公开(公告)号：WO2021263000A2

公开(公告)日：2021-12-30

申请号：PCT/US2021/038925

申请日：2021-06-24

Applicant: F. HOFFMANN-LA ROCHE AG ,  ROCHE DIAGNOSTICS GMBH ,  ROCHE MOLECULAR SYSTEMS, INC.

Inventor： TORBEN-NIELSEN, Benjamin ,  GARCIA-ALCALDE, Fernando ,  MAUDUIT, Vincent ,  GUERENDEL, Corentin Christophe Karim ,  ARNOLD, Phil Pascal

IPC: G16H30/40 ,  G06K9/00 ,  G06N3/04 ,  G06T7/00 ,  G16H50/20 ,  G16H10/60 ,  G06K9/6271 ,  G06K9/6293 ,  G06N20/20 ,  G06N3/0454 ,  G06N3/08 ,  G06N5/003 ,  G06T2207/10056 ,  G06T2207/20021 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30242 ,  G06T7/0012 ,  G06V10/50 ,  G06V2201/03

Abstract: A method of verifying multi-modal medical data is proposed. The method comprises: accessing multi-modal medical data of a subject, the multi-modal medical data comprising a medical image of a specimen slide, wherein a specimen in the specimen slide was collected from the subject; generating a prediction pertaining to a biological attribute of the medical image based on the medical image; determining a degree of consistency between the biological attribute of the medical image and other modalities of the multi-modal medical data; and outputting, based on the degree of consistency, an indication of whether the multi-modal medical data contain inconsistency.

公开(公告)号：WO2021250189A1

公开(公告)日：2021-12-16

申请号：PCT/EP2021/065674

申请日：2021-06-10

Applicant: SANGLE-FERRIERE, Bruno

Inventor： SANGLE-FERRIERE, Bruno

IPC: G06K9/00 ,  G02F2201/58 ,  G06F21/83 ,  G06F21/84 ,  G06T2207/30196 ,  G06T2207/30242 ,  G06T7/70 ,  G06V20/52 ,  G06V20/56

Abstract: Procédé de protection automatique d'un objet, d'une personne ou d'une information visuelle vis-à-vis d'un risque d'observation non désirée par une tierce personne, une personne non autorisée et/ou un appareil d'enregistrement d'images, ce procédé comportant les étapes consistant à : - Détecter automatiquement par analyse d'images provenant d'au moins un lidar ou d'une caméra (20) disposée de façon à couvrir une zone prédéfinie de surveillance (S), la présence d'une tierce personne ou d'une personne non autorisée et/ou dudit appareil dans cette zone ou à proximité, la zone prédéfinie de surveillance correspondant au moins à une zone depuis laquelle la personne ou ledit appareil est en mesure de voir l'objet, la personne ou ladite information, - en cas de détection positive, déclencher une action prédéfinie.

公开(公告)号：WO2021251998A1

公开(公告)日：2021-12-16

申请号：PCT/US2020/047138

申请日：2020-08-20

Applicant: SAUDI ARABIAN OIL COMPANY ,  ARAMCO SERVICES COMPANY

Inventor： ZHANG, Si-Hai

IPC: E21B25/00 ,  E21B41/00 ,  E21B43/26 ,  E21B2200/20 ,  E21B2200/22 ,  E21B49/02 ,  G01N33/24 ,  G01V99/005 ,  G06F30/20 ,  G06K9/6256 ,  G06K9/6263 ,  G06N7/08 ,  G06T11/206 ,  G06T2207/10012 ,  G06T2207/30181 ,  G06T2207/30242 ,  G06T7/70 ,  G06T7/97

Abstract: A method for generating a fracability model of a subterranean formation. The method includes coring and collecting rock cores from a plurality of geographical locations in the subterranean formation, capturing a plurality of core images of the rock cores, generating, by a computer processor and based on the plurality of core images, a plurality of artificial fracture counts of the rock cores, computing, by the computer processor and based on the plurality of artificial fracture counts, a first fracture density curve corresponding to a first geographical location of the plurality of geographical locations, generating, by the computer processor and based on the first fracture density curve, a first fracability measure curve of the rock cores, and generating, by the computer processor and based at least on the first fracability measure curve, a fracability model of the subterranean formation.

公开(公告)号：WO2021191012A1

公开(公告)日：2021-09-30

申请号：PCT/EP2021/056775

申请日：2021-03-17

Applicant: UNIVERSITAT POLITECNICA DE CATALUNYA ,  COMERCIAL QUÍMICA MASSÓ, SA

Inventor： VILASECA RICART, Meritxell ,  DÍAZ DOUTÓN, Fernando ,  BURGOS FERNÁNDEZ, Francisco Javier ,  GARCÍA GUERRA, Carlos Enrique ,  VIRGILI OLIVE, Albert ,  ZARAGOZA BALLESTÉ, Abel Antonio

IPC: G06K9/00 ,  G06K9/20 ,  G06K9/40 ,  G06K9/38 ,  G06T7/60 ,  G06T7/136 ,  G06T7/155 ,  G06K9/00369 ,  G06K9/00771 ,  G06K9/2018 ,  G06T2207/30242 ,  G06T7/11 ,  G06T7/174

Abstract: A method and system are proposed for the automatic counting of the number of insects in a trap. The method comprises acquiring, by means of an acquisition system, a plurality of spectral images of a trap or of a portion of the trap, wherein the spectral images are acquired for at least two different quasi-monochromatic spectral ranges after having sequentially illuminated the trap, or portion of the trap, with light at said two quasi-monochromatic spectral ranges. The trap, or portion of the trap, contains a series of objects adhered thereto, including insects, and optionally other particles. In addition, the method comprises counting, by means of a processor, the number of insects of a first type of said insects through the detection and differentiation of the insects of said first type taking the spectral and morphological parameters thereof into account.

公开(公告)号：WO2021142009A1

公开(公告)日：2021-07-15

申请号：PCT/US2021/012338

申请日：2021-01-06

Applicant: HYLA, INC.

Inventor： JOHNSON, Brandon, P. ,  HERALD, Roscoe, R. ,  HANKS, Harrison, A. ,  FARLEY, Carson

IPC: G06Q30/02 ,  G06F7/00 ,  G06F7/04 ,  G06Q10/00 ,  G06Q30/00 ,  G06Q50/00 ,  G06K9/00664 ,  G06T2207/10152 ,  G06T2207/30121 ,  G06T2207/30242 ,  G06T7/0004

Abstract: Systems and methods for automatically grading a user device are provided. Such systems and methods can include (1) a lighting element positioned at an angle relative to a platform, (2) an imaging device positioned at the angle relative to the platform such that light emitted from the lighting element and a field of view of the imaging device form a right angle where the light emitted from the lighting element and the field of view meet at a user device when the user device is positioned at a predetermined location on the platform, and (3) control circuitry that can activate the lighting element, instruct the imaging device to capture an image of a screen of the user device while the user device is at the predetermined location and is being illuminated by the first lighting element, and parse the image to determine whether the screen is damaged.

公开(公告)号：WO2022197001A8

公开(公告)日：2022-09-22

申请号：PCT/KR2022/003239

申请日：2022-03-08

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： BINDIGAN HARIPRASANNA, Pawan Prasad ,  DAS, Saikat Kumar ,  K S, Green Rosh ,  BOREGOWDA, Lokesh Rayasandra ,  SINGH, Balvinder ,  PEDDIGARI, Venkat Ramana ,  SHUKLA, Alok Shankarlal

IPC: G06T5/00 ,  G06T3/40 ,  G06N3/08 ,  G06T2207/10016 ,  G06T2207/20016 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30242 ,  G06T3/4046 ,  G06T5/006 ,  G06T5/20 ,  G06V10/20 ,  G06V10/764 ,  G06V10/776 ,  G06V10/82

Abstract: A method for removing an artifact in a high resolution image by an electronic device is provided. The method includes receiving the high resolution image comprising the artifact. Further, the method includes downscaling the high resolution image into a plurality of lower resolution images. Further, the method includes removing the artifact from the plurality of lower resolution images by applying at least one first machine learning model from a plurality of machine learning models on the plurality of lower resolution images. Further, the method includes generating a high resolution image free from the artifact by applying at least one second machine learning model from the plurality of machine learning models on an output from the at least one first machine learning model. The output from each of the machine learning model comprises a low resolution image free from the artifact.

公开(公告)号：WO2022010681A1

公开(公告)日：2022-01-13

申请号：PCT/US2021/039357

申请日：2021-06-28

Applicant: BROOKHURST GARAGE, INC.

Inventor： KIM, Young, Joon ,  LEE, Kyuman ,  HWANG, Sunyou

IPC: G05D1/02 ,  G05D1/00 ,  G06T7/11 ,  G06T7/246 ,  G06T7/50 ,  G06T7/70 ,  B25J19/02 ,  B25J13/08 ,  B64C2201/063 ,  B64C2201/066 ,  B64C2201/127 ,  B64C2201/141 ,  B64C2211/00 ,  B64C39/024 ,  G05D1/0253 ,  G06N3/08 ,  G06T2207/10028 ,  G06T2207/30242 ,  G06T7/12 ,  G06T7/74

Abstract: A robot includes an image sensor that captures the environment of a storage site. The robot visually recognizes regularly shaped structures to navigate through the storage site using various object detection and image segmentation techniques. In response to receiving a target location in the storage site, the robot moves to the target location along a path. The robot receives the images as the robot moves along the path. The robot analyzes the images captured by the image sensor to determine the current location of the robot in the path by tracking a number of regularly shaped structures in the storage site passed by the robot. The regularly shaped structures may be racks, horizontal bars of the racks, and vertical bars of the racks. The robot can identify the target location by counting the number of rows and columns that the robot has passed.

公开(公告)号：WO2021147826A1

公开(公告)日：2021-07-29

申请号：PCT/CN2021/072538

申请日：2021-01-18

Applicant: 北京工业大学

Inventor： 黄樟钦 ,  盛梦雪 ,  张硕 ,  李洪亮

IPC: G06T7/277 ,  G06K9/6201 ,  G06T2207/10016 ,  G06T2207/30196 ,  G06T2207/30242 ,  G06T7/246 ,  G06T7/62

Abstract: 一种面向边缘端行人跟踪和人数精确统计的方法，涉及边缘计算场景下基于人工智能部件的行人跟踪和人数统计领域。该方法初始时建立并实时维护行人动态跟踪列表。从边缘端的人工智能部件获取行人结果信息，并在其基础上建立行人静态检测列表。将行人静态检测列表和行人动态跟踪列表进行精确匹配。边缘端的成本及性能限制使得边缘端计算能力有限会导致行人精确匹配失败。此时，该方法将根据行人动态跟踪信息对行人进行智能模糊匹配。根据匹配后的结果实时更新行人动态跟踪列表，并对统计区域内的行人进行人数精确统计，若精确统计失败，所述方法对该行人使用延迟计数策略。

公开(公告)号：WO2021139258A1

公开(公告)日：2021-07-15

申请号：PCT/CN2020/118534

申请日：2020-09-28

Applicant: 平安科技（深圳）有限公司

Inventor： 郭冰雪 ,  吕传峰

IPC: G06T7/00 ,  G06T7/11 ,  G06T7/136 ,  G06T5/00 ,  G06N3/0454 ,  G06N3/084 ,  G06T2207/10056 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30024 ,  G06T2207/30242 ,  G06T5/007 ,  G06T5/30 ,  G06T7/0012

Abstract: 一种基于图像识别的细胞识别计数方法、装置、计算机设备和存储介质，涉及人工智能技术领域。所述方法包括：获取全局数字化细胞图像（202），选取全局数字化细胞图像中的区域图像，区域图像为待识别计数的局部图像（204），对区域图像进行非线性颜色变换处理，得到目标图像（206），将目标图像输入基于包含非常规细胞的历史全局数字化细胞图像训练的细胞识别计数神经网络，识别目标图像中的非常规细胞、并对识别出的非常规细胞进行计数，得到细胞识别计数结果（208）。通过非线性颜色变换处理使得图像的颜色更接近真实图像，使用已训练的细胞识别计数网络，能够快速准确地对目标图像中的非常规细胞进行识别计数，提高细胞识别计数的效率。

公开(公告)号：WO2022267447A1

公开(公告)日：2022-12-29

申请号：PCT/CN2022/070657

申请日：2022-01-07

Applicant: 上海杏脉信息科技有限公司

Inventor： 王本刚 ,  吴惠民

IPC: G06T7/00 ,  G06T7/10 ,  G06K9/00 ,  G06N3/08 ,  G06T2207/10056 ,  G06T2207/20021 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30096 ,  G06T2207/30242 ,  G06T7/0012 ,  G06V20/69

Abstract: 一种病理图像处理系统、方法及介质。该系统包括：病理图像获取模块，用于获取病理图像，病理图像为经PD-L1免疫组化检测试剂染色的组织样本的病理学显微图像；病理图像识别模块，与病理图像获取模块相连，用于识别病理图像中的特定部位，特定部位包括病理图像中的肿瘤细胞所在部位和/或经PD-L1免疫组化检测试剂染色后呈现特定颜色的部位；表达水平获取模块，与病理图像识别模块相连，用于根据病理图像识别模块对特定部位的识别结果获取病理图像的PD-L1表达水平，病理图像处理系统能够自动识别病理图像中的特定部位，并根据特定部位的识别结果获取病理图像的PD-L1表达水平。