-
61.
公开(公告)号:US20240193759A1
公开(公告)日:2024-06-13
申请号:US18533652
申请日:2023-12-08
Applicant: CREFLE Inc.
Inventor: Eunseok SEO
IPC: G06T7/00 , G06Q10/0633 , G06V10/25
CPC classification number: G06T7/0008 , G06Q10/0633 , G06V10/25 , G06T2207/30164 , G06V2201/07
Abstract: An artificial intelligence-based process defect detection system may include: a photographing module that collects image data by capturing a process that progresses on an object; a machine learning model that generates work data that is a result of recognizing and reading the object based on the image data; and a detection module that receives instruction data recorded regarding a process for an object optimized for product production, detects a defect or a non-defect by comparing the work data with the instruction data, and generates defect information when the process is defective.
-
公开(公告)号:US20240193727A1
公开(公告)日:2024-06-13
申请号:US18332939
申请日:2023-06-12
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Hyeonseung YU , Nahyup KANG , Hanjun KIM , Jaeyoung MOON , Juyoung LEE , Hwiryong JUNG , Inwoo HA , Seokpyo HONG
IPC: G06T3/40 , G06T3/00 , G06T7/50 , G06T7/90 , G06V10/764
CPC classification number: G06T3/4053 , G06T3/0093 , G06T7/50 , G06T7/90 , G06V10/764 , G06T2207/10024 , G06V2201/07
Abstract: A processor implemented method includes generating a semantic map indicating a visualization property assigned to an object of an obtained frame image having a first resolution and generating a reconstruction image using an image reconstruction machine learning model provided input based on the obtained frame image and the semantic map having a second resolution and including a second object having a visualization property indicated by the semantic map.
-
公开(公告)号:US12008820B2
公开(公告)日:2024-06-11
申请号:US17351832
申请日:2021-06-18
Inventor: Pengbin Yang , Yang Yang , Jianxu Zhang , Wenlong Chen
CPC classification number: G06V20/588 , G05D1/0088 , G05D1/0094 , G05D1/0246 , G06V2201/07
Abstract: The present disclosure provides a method of matching lane line data, which relates to a field of automatic driving, and in particular to a field of locating an autonomous vehicle. The method of matching lane line data includes: obtaining a first data indicating sensed lane lines and a second data indicating map lane lines respectively; constructing a correlation weight matrix for the first data and the second data, based on differences between the sensed lane lines and the map lane lines; and matching the first data with the second data according to the correlation weight matrix, so as to obtain a third data having an optimal match with the first data from the second data. The present disclosure further discloses an apparatus of matching lane line data, a device, a storage medium and a computer program product.
-
公开(公告)号:US20240185610A1
公开(公告)日:2024-06-06
申请号:US18441711
申请日:2024-02-14
Applicant: Arlo Technologies, Inc.
Inventor: Rajinder Singh , Mikio Yves Matsuo , Matthew McRae
CPC classification number: G06V20/52 , G06T5/50 , G06T5/70 , G06T7/20 , G06T11/60 , G06V20/44 , H04N23/695 , G06T2207/20221 , G06V2201/07
Abstract: An electronic monitoring system and a method of dynamically altering an activity zone within the electronic monitoring system are provided. The electronic monitoring system includes a camera having a first field-of-view and operating to generate a first image data. A user device is configured to receive the first image data; define an activity zone at a first area within the first image data; define a triggering event; and define an object in the first field-of-view. A computer-readable memory stores the data corresponding to the object. An electronic processor executes a stored program and receives the image data from the camera to generate an alert in response to the occurrence of a triggering event. If a camera in the electronic monitoring system has moved such that the field of view has changed since the activity zones were created by the user, then the electronic monitoring system may dynamically update the configured activity zones based, for example, on a computer vision analysis of the previously configured activity zones.
-
65.
公开(公告)号:US20240181884A1
公开(公告)日:2024-06-06
申请号:US18286420
申请日:2022-02-10
Applicant: Bayerische Motoren Werke Aktiengesellschaft
Inventor: Tomas HEJDA , Sadzida KRATZ , Christopher ROELLE
IPC: B60K35/234 , B60K35/90 , G02B27/01 , G06V10/60
CPC classification number: B60K35/234 , B60K35/90 , G02B27/0101 , G06V10/60 , B60K2360/349 , B60K2360/785 , G02B2027/0118 , G06V2201/07
Abstract: A reflection display system for displaying a display image for a vehicle occupant of a motor vehicle by reflecting the display image on a windshield is provided. The system includes a display unit which is designed to display the display image on a display surface, a detection sensor system for detecting the displayed display image on the display surface, and a control unit which is designed to actuate the display unit for displaying purposes, ascertain detection information on the basis of the detected displayed display image, ascertain the presence of a foreign object on the display surface of the display unit on the basis of the displayed display image and on the basis of the detection information, and signal a disruption of the display if the presence of a foreign object on the display surface of the display unit has been ascertained.
-
66.
公开(公告)号:US20240179418A1
公开(公告)日:2024-05-30
申请号:US18516790
申请日:2023-11-21
Applicant: CANON KABUSHIKI KAISHA
Inventor: YOMA KURIKI
CPC classification number: H04N23/73 , G06V10/60 , G09G5/377 , H04N23/61 , G06V2201/07
Abstract: An apparatus includes an acquisition unit configured to acquire an image, a detection unit configured to detect an object from the image, a photometry unit configured to perform photometry on the image in accordance with a set photometry mode, wherein the photometry mode includes a first photometry mode in which an exposure is determined by weighting a region having a relatively high luminance value in comparison with a region having a relatively low luminance value at least in a photometry region, and wherein, in a case where the detection unit detects the object in the image in a state where the first photometry mode is selected, the photometry unit performs photometry in the first photometry mode by using a region of the object as the photometry region.
-
公开(公告)号:US20240177323A1
公开(公告)日:2024-05-30
申请号:US18516413
申请日:2023-11-21
Applicant: CANON KABUSHIKI KAISHA
Inventor: HIROYO TANAKA
CPC classification number: G06T7/20 , G06T7/70 , G06V10/25 , G06V10/761 , H04N23/611 , H04N23/681 , G06T2207/30196 , G06V2201/07
Abstract: An apparatus comprises an acquisition unit that acquires information about a subject detected from a captured image, a calculation unit that calculates a tracking amount based on a position of the subject in the captured image and a target position, a control unit that controls subject tracking to bring the position of the subject in the captured image close to the target position, based on the tracking amount, and a setting unit that sets first and second regions based on at least any of a holding state of an imaging apparatus that captures the captured image, a detection result of an operation performed by a photographer on the imaging apparatus, a position in the captured image of the target position, and a type of the subject, wherein, in the first region, a degree to which the subject tracking is performed is lower than in the second region.
-
公开(公告)号:US11995877B2
公开(公告)日:2024-05-28
申请号:US17645830
申请日:2021-12-23
Applicant: Continental Autonomous Mobility US, LLC
Inventor: Eduardo Jose Ramirez Llanos , Xin Yu , Matthew Donald Berkemeier
CPC classification number: G06V10/245 , B60R1/28 , B62D13/005 , B62D15/0295 , G06V10/25 , G06V10/267 , G06V20/58 , G06V20/59 , G06V2201/07
Abstract: A vehicle driver assist system provides for the location of a target feature in an initial image and updates the location of that target feature based on information indicative of vehicle dynamic operation. The system predicts a relative position of the target feature within subsequent images such that only a portion of subsequent images need by analyzed and searched.
-
69.
公开(公告)号:US11995820B2
公开(公告)日:2024-05-28
申请号:US17295916
申请日:2020-05-26
Applicant: IMAGOWORKS INC.
Inventor: Youngjun Kim , Hannah Kim
CPC classification number: G06T7/0012 , G06T15/08 , G06T15/20 , G06V10/25 , G06V10/82 , G06T2207/30008 , G06T2207/30036 , G06V2201/07
Abstract: A method for automated detection of landmarks from 3D medical image data using deep learning according to the present inventive concept, the method includes receiving a 3D volume medical image, generating a 2D intensity value projection image based on the 3D volume medical image, automatically detecting an initial anatomical landmark using a first convolutional neural network based on the 2D intensity value projection image, generating a 3D volume area of interest based on the initial anatomical landmark and automatically detecting a detailed anatomical landmark using a second convolutional neural network different from the first convolutional neural network based on the 3D volume area of interest.
-
公开(公告)号:US11989945B2
公开(公告)日:2024-05-21
申请号:US17909218
申请日:2021-03-03
Applicant: THALES
Inventor: Dominique Delacourt , Olivier Cocle , Olivier Verdy , Dominique Bon , Ludovic Perruchot , Alain Le Meur , Frédéric Le Gusquet
IPC: G06V20/00 , G06V10/143 , G06V10/147 , G06V10/22 , G06V10/74 , G06V10/764 , G06V20/52 , G06V20/56 , G06V20/58 , H04N23/45 , H04N23/698 , H04N23/951 , G06V10/10
CPC classification number: G06V20/56 , G06V10/143 , G06V10/147 , G06V10/22 , G06V10/74 , G06V10/764 , G06V20/52 , G06V20/58 , H04N23/45 , H04N23/698 , H04N23/951 , G06V10/16 , G06V2201/07
Abstract: The present invention relates to a method for assisting in the detection of elements in an environment, comprising:
the acquisition of a first wide-field image of an environment by a first sensor (14A) having a first field of view and a first resolution,
the generation of a fused image from first narrow-field images of the environment acquired by a second sensor (14B) having a second field of view strictly less than the first field of view and a second resolution finer than the first resolution,
In response to the detection of a difference relating to an element on a second wide-field image acquired by the first sensor (14A), compared to the first wide-field image, the acquisition of a second narrow-field image imaging the difference, and
the update the fused image with the second narrow-field image.
-
-
-
-
-
-
-
-
-