-
公开(公告)号：US20220169245A1
公开(公告)日：2022-06-02
申请号：US17593478
申请日：2020-01-27
Applicant: SONY GROUP CORPORATION
Inventor： YUSUKE HIEIDA , RYUTA SATOH
Abstract: A moving range of an object is estimated on the basis of image information. An information processing apparatus includes an input unit that inputs an image, a region estimation unit that estimates a region of an object contained in the image, a moving history information acquisition unit that acquires information associated with a moving history of the object, a contact region determination unit that determines a contact region in contact with the object on the basis of an estimation result obtained by the region estimation unit, and a moving range estimation unit that estimates a moving range of the object on the basis of the moving history containing the contact region of the object. The moving range estimation unit estimates the moving range of the object on the basis of the moving history containing the contact region of the object and a moving track of the object.
-
公开(公告)号：US20220148283A1
公开(公告)日：2022-05-12
申请号：US17440848
申请日：2020-03-13
Applicant: SONY GROUP CORPORATION
Inventor： SUGURU AOKI , RYUTA SATOH
Abstract: An information processing apparatus includes an image processor and a controller. The image processor performs recognition processing of recognizing attributes of predetermined regions that are respectively included in sequentially acquired images captured by a camera. The controller sets a frequency of performing the recognition processing for the predetermined region on the basis of the recognized attribute.
-
公开(公告)号：US20250069374A1
公开(公告)日：2025-02-27
申请号：US18720868
申请日：2022-12-21
Applicant: SONY GROUP CORPORATION
Inventor： RYUTA SATOH , SUGURU AOKI
IPC: G06V10/774 , G06V10/147 , G06V10/776 , H04N25/78
Abstract: An information processing apparatus according to an embodiment includes a generation part (301) that generates, based on a dataset (300, 303) or a first recognizer (310) for training the first recognizer that performs a recognition process based on a first signal read from a first sensor, control information (313) for controlling a recognition process by a second recognizer (312) that performs the recognition process based on a second signal read from a second sensor having a reading unit different from the first sensor.
-
公开(公告)号：US20240056556A1
公开(公告)日：2024-02-15
申请号：US18257717
申请日：2021-12-09
Applicant: SONY GROUP CORPORATION
Inventor： SUGURU AOKI , RYUTA SATOH , ITARU SHIMIZU
CPC classification number: H04N7/183 , G06V20/13 , B64G1/1007 , G06V2201/07
Abstract: The present technology relates to an artificial satellite and a ground system enabling to efficiently hold data in the artificial satellite. An artificial satellite includes: an image processing unit that executes feature amount generation processing of generating a feature amount of a captured satellite image; a storage unit that holds feature amount data obtained as a result of the feature amount generation processing; and a communication unit that transmits the feature amount data to a ground station when communication with the ground station becomes possible. The ground system includes an image processing unit configured to generate complemented data by using complementing data and feature amount data that indicates a feature amount of a satellite image acquired from an artificial satellite and obtained by capturing an image of a ground by the artificial satellite. The present technology can be applied to, for example, a satellite image processing system and the like that process a satellite image.
-
公开(公告)号：US20220094435A1
公开(公告)日：2022-03-24
申请号：US17424203
申请日：2020-01-20
Applicant: SONY GROUP CORPORATION
Inventor： KEITARO YAMAMOTO , RYUTA SATOH
IPC: H04B10/116 , G08G1/16 , G08G1/09 , G06V20/58
Abstract: A visible light communication apparatus according to the present disclosure includes an acquisition section configured to acquire an image captured by a sensor included in a mobile object, a first extraction section configured to detect an object included in the image and extract a first region that includes the object, a second extraction section configured to detect a light source from inside the first region and extract a second region that includes the light source, and a visible light communication section configured to perform visible light communication with the light source included in the second region.
-
Patent Agency Ranking
6.发明公开公开(公告)号：US20240078803A1
公开(公告)日：2024-03-07
申请号：US18262411
申请日：2021-12-03
Applicant: SONY GROUP CORPORATION
Inventor： SUGURU AOKI , RYUTA SATOH , KENJI SUZUKI
Abstract: Information processing is implemented which analyzes the cause of the result of recognition using a machine learning model.
An information processing apparatus includes: a recognition processing section configured to perform object recognition processing on sensor information from a sensor section by use of a trained machine learning model; a causal analysis section configured to analyze the cause of a result of recognition by the recognition processing section on the basis of the sensor information from the sensor section and the result of recognition by the reception processing section; and a control section configured to control an output of the sensor section. The sensor section is an image sensor. The causal analysis section determines the cause of a drop in characteristic of recognition by the recognition processing section on the basis of low-resolution high-bit-length image data for causal analysis.-
7.发明公开公开(公告)号：US20230251846A1
公开(公告)日：2023-08-10
申请号：US18003334
申请日：2021-06-21
Applicant: SONY GROUP CORPORATION
Inventor： RYUTA SATOH
CPC classification number: G06F8/65 , G06T7/70 , G06V10/761 , G06V20/56
Abstract: The present disclosure relates to an information processing apparatus, an information processing method, an information processing system, and a program that enable an SW to be easily updated with an adjustment content according to a request of a user. Vehicle accumulation information including an image for relearning the SW that functions as an object recognition section that recognizes an object around a vehicle and an object recognition result is acquired from the image around the vehicle, adjustment content requested by the user of the vehicle regarding the relearning of the SW is decided, and the SW is relearned on the basis of the vehicle accumulation information and the adjustment content. The present disclosure can be applied to an automated driving technology.
-
公开(公告)号：US20220185278A1
公开(公告)日：2022-06-16
申请号：US17593047
申请日：2020-02-19
Applicant: SONY GROUP CORPORATION
Inventor： RYUTA SATOH , SUGURU AOKI
Abstract: An imaging section 20 images a passenger in a moving body. A boarding state detection section 30 detects a boarding state of the passenger on the basis of a captured image acquired by the imaging section 20. An allowable acceleration setting section 40 sets, for each passenger, individual allowable acceleration on the basis of the boarding state of the passenger detected by the boarding state detection section 30, for example, the lateral spacing between the feet of the passenger, the arrangement angle of the feet with respect to the moving direction of the moving body, and the like. Further, integration is performed on the individual allowable acceleration determined for the respective passengers in the moving body, and the acceleration that is allowable for the moving body is set. The allowable acceleration for the moving body is set according to the boarding state of each passenger, thus preventing the moving body from moving at acceleration at which the passengers may be endangered. This allows the safety of the passengers to be improved.
-
9.发明公开公开(公告)号：US20230267708A1
公开(公告)日：2023-08-24
申请号：US18004220
申请日：2021-06-30
Applicant: SONY GROUP CORPORATION
Inventor： SUGURU AOKI , RYUTA SATOH
IPC: G06V10/774 , G06N3/0464 , G06V10/82 , G06V10/776
CPC classification number: G06V10/774 , G06N3/0464 , G06V10/82 , G06V10/776
Abstract: The present technology relates to a method for generating a learning model, a program, and an information processing apparatus that enable image recognition with reduced influence of brightness in a target image.
A learning model is trained such that a total sum of coefficients in one or more channels of at least one or more convolution filters among the convolution filters for a first layer of a neural network including a plurality of the convolution filters approaches zero, the neural network being applied to the learning model that performs recognition processing on input data.-
10.发明公开公开(公告)号：US20230244471A1
公开(公告)日：2023-08-03
申请号：US18003211
申请日：2021-06-21
Applicant: SONY GROUP CORPORATION
Inventor： RYUTA SATOH
Abstract: The present disclosure relates to an information processing apparatus, an information processing method, an information processing system, and a program that enable update of an SW to be quickly and safely implemented. The software program (SW) is updated from the vehicle group in which the safety is confirmed, the operation state of the SW after the update is confirmed, and if there is no abnormality, the SW of the vehicle groups other than the vehicle group in which the safety is confirmed is also updated. The present disclosure can be applied to an automated driving technology.
-
-
-
-
-
-
-
-
-
Search Results
19
records
(took 0.016 seconds)
