公开(公告)号：US12230044B2

公开(公告)日：2025-02-18

申请号：US17840895

申请日：2022-06-15

Applicant: VBC HOLDINGS LLC

Inventor： David Pilutti ,  Alison Willian Gomes Dos Santos ,  Francesco Armani ,  Giacomo Cattaruzzi

IPC: G06V20/69 ,  G06T5/30 ,  G06T5/40 ,  G06T5/70 ,  G06T5/94 ,  G06T7/155

Abstract: A method of determining a coverage of an image by an apparatus including processing circuitry includes executing, by the processing circuitry, instructions that cause the apparatus to generate a first segmentation mask by segmenting an image, generate a modified mask by applying a morphological operation to the first segmentation mask, generate a modified masked input based on the image and an inversion of the modified mask, generate a second segmentation mask by segmenting the modified masked input, and determine a coverage of the image based on the first segmentation mask and the second segmentation mask.

公开(公告)号：US20250029369A1

公开(公告)日：2025-01-23

申请号：US18281570

申请日：2022-09-30

Applicant: BOE Technology Group Co., Ltd.

Inventor： Mengdi SUN

IPC: G06V10/771 ,  G06T5/30 ,  G06T5/50 ,  G06V10/25 ,  G06V10/44 ,  G06V10/80

Abstract: Disclosed are an image restoration method and device, and a non-transitory computer storage medium. The image restoration method includes: an original mask in an original to-be-restored image is processed into a dilated mask with a regular shape, the dilated mask is overlaid at the location of the original mask in the original to-be-restored image to acquire a mask enhancement feature map, and then the dilated mask in the mask enhancement feature map is restored using an image restoration network to acquire a restored image corresponding to the original to-be-restored image.

公开(公告)号：US20240428417A1

公开(公告)日：2024-12-26

申请号：US18821441

申请日：2024-08-30

Applicant: Boston Scientific Scimed, Inc.

Inventor： Longquan CHEN ,  Niraj P. RAUNIYAR ,  Evan GYLLENHAAL

IPC: G06T7/00 ,  A61B18/26 ,  A61B90/00 ,  G06T5/00 ,  G06T5/30

Abstract: Systems and methods for processing electronic images from a medical device comprise receiving a first image frame and a second image frame from a medical device, and determining a region of interest by subtracting the first image frame from the second image frame, the region of interest corresponding to a visual obstruction in the first image frame and/or second image frame. Image processing may be applied to the first image frame and/or second image frame based on a comparison between a first area of the first image frame corresponding to the region of interest and a second area of the second image frame corresponding to the region of interest, and the first image frame and/or second image frame may be provided for display to a user.

公开(公告)号：US20240420489A1

公开(公告)日：2024-12-19

申请号：US18785781

申请日：2024-07-26

Applicant: Beckman Coulter, Inc.

Inventor： Bart J. WANDERS ,  Jiuliu LU ,  Bian QIAN ,  John S. RILEY

IPC: G06V20/69 ,  G06T5/30 ,  G06T7/00 ,  G06T7/194 ,  G06V10/60

Abstract: A visual analysis system may be automatically focused (or the focus of such a system may be automatically corrected) by subjecting one or more images captured by such a system to a multi-layer analysis. In such an analysis, a cell boundary may be identified in an input image based on the lightness value of the pixels of the input image. Based on the identified cell boundary, a predicted nominal focus value is determined which can provide a focusing distance (e.g., a distance between the focal plane of a camera used when an image was captured and the actual focal plane for an in-focus image). This focusing distance may then be used to (re) focus a camera or for other purposes (e.g., generating an alert).

公开(公告)号：US20240378854A1

公开(公告)日：2024-11-14

申请号：US18289426

申请日：2022-05-17

Applicant: ZTE CORPORATION

Inventor： Guotian FAN ,  Ruiqiang HONG ,  Ning LI ,  Hai ZHANG

IPC: G06V10/74 ,  G06T3/40 ,  G06T5/30 ,  G06T5/70 ,  G06T7/13 ,  G06T7/90

Abstract: Provided in the present disclosure are a detection method and system for a base station feeder line, and a related apparatus. The method includes: storing, by an image acquisition terminal, a collected feeder line image of a base station to be detected and an identifier of the corresponding base station to be detected in correspondence; and searching for and acquiring, by an image processing terminal, a target feeder line image according to a detection request, performing image preprocessing on the target feeder line image to convert the target feeder line image into a feature grayscale image, comparing the obtained feature grayscale image with a standard feeder line feature grayscale image, and determining, according to a comparison result, whether a feeder line of a target base station to be detected is correctly installed.

公开(公告)号：US20240378753A1

公开(公告)日：2024-11-14

申请号：US18688915

申请日：2022-07-26

Applicant: Continental Automotive Technologies GmbH

Inventor： Michael Goldhammer

IPC: G06T7/80 ,  G06T5/30 ,  G06T7/70 ,  G08G1/01

Abstract: A method for calibrating a road monitoring device in which, for a predefined calibration period, the positions of detected objects in relation to the road monitoring device are recorded and an accumulated object residence map is formed therefrom. A world coordinate map of the lanes or lane centers for the monitoring region with their position in a predefined world coordinate system. A position and orientation are determined automatically with a predefined degree of correspondence by computer-based movement and/or rotation of the accumulated object residence map or an object residence map derived from it, in particular a filtered object residence map, and computer-based determination of a respective degree of correspondence to the world coordinate map. The actual position and actual orientation of the sensor are derived from this position, and the position of the objects is calibrated accordingly.

公开(公告)号：US20240346675A1

公开(公告)日：2024-10-17

申请号：US18632171

申请日：2024-04-10

Applicant: Adeia Imaging LLC

Inventor： Ankit Jain ,  Priyam Chatterjee ,  Kartik Venkataraman

IPC: G06T7/593 ,  G06T5/30 ,  G06T5/50 ,  G06T7/11 ,  G06T7/13 ,  G06T7/136 ,  G06T7/194 ,  G06T7/44

CPC classification number: G06T7/593 ,  G06T5/30 ,  G06T5/50 ,  G06T7/11 ,  G06T7/13 ,  G06T7/136 ,  G06T7/194 ,  G06T7/44 ,  G06T2200/04 ,  G06T2207/10012 ,  G06T2207/10028 ,  G06T2207/20028 ,  G06T2207/20032 ,  G06T2207/20036 ,  G06T2207/20192

Abstract: Systems and methods for hybrid depth regularization in accordance with various embodiments of the invention are disclosed. In one embodiment of the invention, a depth sensing system comprises a plurality of cameras; a processor; and a memory containing an image processing application. The image processing application may direct the processor to obtain image data for a plurality of images from multiple viewpoints, the image data comprising a reference image and at least one alternate view image; generate a raw depth map using a first depth estimation process, and a confidence map; and generate a regularized depth map. The regularized depth map may be generated by computing a secondary depth map using a second different depth estimation process; and computing a composite depth map by selecting depth estimates from the raw depth map and the secondary depth map based on the confidence map.

公开(公告)号：US20240331139A1

公开(公告)日：2024-10-03

申请号：US18256312

申请日：2021-12-15

Applicant: MARS, INCORPORATED

Inventor： Mark Justin PARKINSON ,  Michael FITZKE ,  Vladimir FADEEV ,  Fernando RODRIGUES

IPC: G06T7/00 ,  G06T5/30 ,  G06T7/11 ,  G06V10/82 ,  G06V20/69

CPC classification number: G06T7/0012 ,  G06T5/30 ,  G06T7/11 ,  G06V10/82 ,  G06V20/695 ,  G06V20/698 ,  G06T2207/10056 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30024 ,  G06T2207/30096

Abstract: In one embodiment, the disclosure provides a method comprising: receiving an image of a biopsy slide; executing first programmed instructions to input the image to a first trained machine learning model programmed as a cancer classifier, thereby outputting a classification; determining, based on the classification, that the image should be further processed; executing a tissue detect ion algorithm on the image of the biopsy slide, thereby outputting a first set of coordinates; executing second programmed instructions to input the image of the biopsy slide and the first set of coordinates to a second trained machine learning model programmed for image segmentation, thereby outputting a binary pixel mask; executing third programmed instructions to generate an enhanced pixel mask using the binary pixel mask; and digitally storing, in computer memory, a second set of coordinates indicated by the enhanced pixel mask, in one embodiment, a 10-high-power field can be generated and digitally stored.

公开(公告)号：US20240273860A1

公开(公告)日：2024-08-15

申请号：US18567418

申请日：2021-06-10

Applicant: NEC Corporation

Inventor： Eiji Kaneko ,  Masato Toda

IPC: G06V10/75 ,  G06T5/30 ,  G06T5/50 ,  G06T5/77 ,  G06V10/74 ,  G06V20/13

CPC classification number: G06V10/751 ,  G06T5/30 ,  G06T5/50 ,  G06T5/77 ,  G06V10/754 ,  G06V10/761 ,  G06T2207/10044 ,  G06T2207/20212 ,  G06V20/13

Abstract: The image processing device includes a change area detection unit which detects a change area, where an object has changed compared to the first image, in the second image obtained by observing the same observed area as an observed area in the first image, an image correction unit which performs a correction process to make the change area in the second image smaller relative to a non-change area where the object has not changed, and an image pair output unit which outputs an image pair of the second image processed by the image correction unit and the first image.

公开(公告)号：US12020400B2

公开(公告)日：2024-06-25

申请号：US17585140

申请日：2022-01-26

Applicant: Adobe Inc.

Inventor： Chih-Yao Hsieh ,  Yilin Wang

IPC: G06K9/00 ,  G06T3/4046 ,  G06T3/4076 ,  G06T5/30 ,  G06T5/75 ,  G06T7/155 ,  G06V10/80

CPC classification number: G06T3/4076 ,  G06T3/4046 ,  G06T5/30 ,  G06T5/75 ,  G06T7/155 ,  G06V10/806

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that upsample and refine segmentation masks. Indeed, in one or more implementations, a segmentation mask refinement and upsampling system upsamples a preliminary segmentation mask utilizing a patch-based refinement process to generate a patch-based refined segmentation mask. The segmentation mask refinement and upsampling system then fuses the patch-based refined segmentation mask with an upsampled version of the preliminary segmentation mask. By fusing the patch-based refined segmentation mask with the upsampled preliminary segmentation mask, the segmentation mask refinement and upsampling system maintains a global perspective and helps avoid artifacts due to the local patch-based refinement process.