-
1.发明公开公开(公告)号：US20240249387A1
公开(公告)日：2024-07-25
申请号：US18005056
申请日：2021-11-05
Applicant: RAKUTEN GROUP, INC.
Inventor： Mitsuru NAKAZAWA , Bjorn STENGER
IPC: G06T5/50
CPC classification number: G06T5/50 , G06T2207/20221
Abstract: Provided is an information-processing device including: a CPU; and a memory storing instructions for causing the information-processing device, when executed by the CPU, to: select M (M≤N) images from N (N>1) images; generate a combined image by arranging the selected M images in M frames defined in advance, respectively; and determine a total assessment value in association with the generated combined image, the total assessment value including at least a linear sum of a selection assessment value being a linear sum of single image assessment values of the selected M images and a combination assessment value being a single image assessment value of the combined image.
-
公开(公告)号：US20240104754A1
公开(公告)日：2024-03-28
申请号：US18013173
申请日：2021-12-27
Applicant: Rakuten Group, Inc.
Inventor： Tomoyuki MUKASA , Mitsuru NAKAZAWA
CPC classification number: G06T7/37 , G06T3/60 , G06T7/32 , G06T7/337 , G06T7/38 , G06T7/55 , G06T7/80 , G06T2207/10016 , G06T2207/10032
Abstract: [Problem] The present disclosure has an object of correcting the orientation of a captured image captured during flight.
[Solving Means] An information processing system includes: a captured image acquisition unit that acquires a captured image captured during flight by an imaging device mounted on an airplane; a relevant information acquisition unit that acquires information detected using a sensor mounted on the airplane; and an image correction unit that acquires, by correcting the captured image on a basis of information acquired using the relevant information, a correction image in which a predetermined direction in a state where the image is erected and a reference direction in the image are matched to each other.-
公开(公告)号：US20230116047A1
公开(公告)日：2023-04-13
申请号：US17595339
申请日：2020-11-27
Applicant: RAKUTEN GROUP, INC.
Inventor： Mitsuru NAKAZAWA , Jun TAKIZAWA
IPC: G05D1/12 , G05D1/10 , G05D1/00 , G05D1/02 , G06V20/10 , G06V20/17 , G06V20/56 , G06T7/00 , A01G25/16 , B64C39/02
Abstract: The sensing system S extracts a target area to be subjected to short-distance sensing by the UGV 2 on the basis of the long-distance sensing data obtained by the UAV 1 in the air performing long-distance sensing on a lower place, perform movement control for moving the UGV 2 toward the target area. And then, the sensing system acquires short-distance sensing data obtained by performing short-distance sensing on the whole or a part of the target area by the UGV 2 that has moved according to the movement control.
-
4.发明公开公开(公告)号：US20240320956A1
公开(公告)日：2024-09-26
申请号：US18579498
申请日：2022-03-28
Inventor： Takayoshi YAMASHITA , Hironobu FUJIYOSHI , Tsubasa HIRAKAWA , Mitsuru NAKAZAWA , Yeongnam CHAE , Bjorn STENGER
IPC: G06V10/771 , G06V20/40
CPC classification number: G06V10/771 , G06V20/42
Abstract: A computer vision system, with at least one processor configured to: acquire, from a sports match video, a plurality of pieces of consecutive image data indicating a portion of the sports match video, the plurality of pieces of consecutive image data including a plurality of pieces of first consecutive image data that are consecutive and a plurality of pieces of second consecutive image data that are consecutive after the plurality of pieces of first consecutive image data; and execute an estimation, by using a machine learning model, of whether the portion is of a predetermined scene type.
-
公开(公告)号：US20230206483A1
公开(公告)日：2023-06-29
申请号：US18088017
申请日：2022-12-23
Applicant: Rakuten Group, Inc.
Inventor： Mitsuru NAKAZAWA , Takashi TOMOOKA
CPC classification number: G06T7/70 , G06T17/00 , G06T5/50 , G06T7/50 , G06V10/44 , G06V2201/07 , G06T2207/20221
Abstract: Disclosed is an image processing apparatus including a receiving section that receives a captured image of a target object, an instruction section that gives a user an instruction on which direction to capture an image of the target object, an inferencing section that performs an inference of an imaging direction on the basis of the received captured image, and a verifying section that performs predetermined verification processing related to the target object on the basis of an imaging direction as the instructed direction and the imaging direction as a result of the inference.
-
Patent Agency Ranking
6.发明申请公开(公告)号：US20220024582A1
公开(公告)日：2022-01-27
申请号：US17311717
申请日：2019-08-20
Applicant: Rakuten Group,Inc.
Inventor： Mitsuru NAKAZAWA , Jun TAKIZAWA
Abstract: The unmanned aerial vehicle system S identifies a landing point candidate that is a candidate for an emergency landing point for causing an UAV 1 flying toward a destination point to make an emergency landing at other than the destination point and calculate a recovery cost regarding a recovery route candidate connecting a reference point and the landing point candidate, the recovery cost being used to determine a recovery route connecting the reference point and the emergency landing point or the emergency landing point.
-
公开(公告)号：US20240362885A1
公开(公告)日：2024-10-31
申请号：US18029668
申请日：2021-09-30
Applicant: RAKUTEN GROUP, INC.
Inventor： Hiya ROY , Mitsuru NAKAZAWA , Bjorn STENGER
IPC: G06V10/26 , G06V10/774 , G06V10/82
CPC classification number: G06V10/26 , G06V10/774 , G06V10/82
Abstract: Provided is an information-processing device including a CPU; and a memory storing instructions for causing the information-processing device, when executed by the CPU, to: include at least a machine learning model configured to receive an input image and an attribute as input, and to output at least one region in the input image and an evaluation value for each of the at least one region, wherein, for a common input image, the region and the evaluation value output when one attribute is given are different from the region and the evaluation value output when another attribute different from the one attribute is given.
-
8.发明公开公开(公告)号：US20240281468A1
公开(公告)日：2024-08-22
申请号：US18018044
申请日：2021-10-26
Applicant: RAKUTEN GROUP, INC.
Inventor： Mitsuru NAKAZAWA , Bjorn STENGER
IPC: G06F16/583 , G06F16/55
CPC classification number: G06F16/5846 , G06F16/55
Abstract: Provided is an information-processing device for extracting an important image from target information including images and a text, the information-processing device including: a CPU; and a memory storing instructions for causing the information-processing device, when executed by the CPU, to: determine a category indicating an attribute of each image; extract a category for each division of the text; determine a score of the category based on the text; and extract, as a most important image, one of the images corresponding to the category selected based on the score.
-
公开(公告)号：US20240135685A1
公开(公告)日：2024-04-25
申请号：US18013169
申请日：2021-12-27
Applicant: RAKUTEN GROUP, INC.
Inventor： Dinesh DAULTANI , Mitsuru NAKAZAWA
CPC classification number: G06V10/774 , G06T5/20 , G06T5/60 , G06T5/92 , G06T7/11 , G06T7/194 , G06T7/80 , G06T11/60 , G06T2207/20081
Abstract: [Problem] Provided is a novel information processing technology relating to a predetermined object in an image.
[Solving Means] An information processing apparatus includes: an image acquisition unit that acquires an image used as teacher data for machine learning, the image being with one or a plurality of annotations for showing a position in the image at which a predetermined object is shown; an adjustment image generation unit that generates an adjustment image in which parameters of the image are adjusted; and a machine learning unit that generates a learning model for detecting the predetermined object in an image by performing machine learning using teacher data including the adjustment image.-
10.发明申请公开(公告)号：US20220171966A1
公开(公告)日：2022-06-02
申请号：US17358023
申请日：2021-06-25
Applicant: RAKUTEN GROUP, INC.
Inventor： Mitsuru NAKAZAWA , Takashi TOMOOKA
Abstract: An information processing system configured to provide an electronic commerce platform. An information processing system is configured to acquire a descriptive text related to an item and at least one image related to the item; identify an object from the descriptive text; detect an object from each of the at least one image; and generate correspondence information based on correspondence between the object identified from the descriptive text and the object detected from the image.
-
-
-
-
-
-
-
-
-
Search Results
32
records
(took 0.016 seconds)
