公开(公告)号：US20230328260A1

公开(公告)日：2023-10-12

申请号：US18295556

申请日：2023-04-04

Applicant: Axis AB

Inventor： Axel KESKIKANGAS ,  Viktor Edpalm

IPC: H04N19/167 ,  G06T7/70 ,  G06V10/25 ,  H04N19/159

CPC classification number: H04N19/167 ,  G06T7/70 ,  G06V10/25 ,  H04N19/159 ,  G06V2201/07 ,  G06T2207/20084

Abstract: A method of encoding an image comprises establishing whether objects constituting one or more predefined object types or performing one or more predefined event types are visible in the image; in response to establishing that the objects are visible, encoding at least one region-of-interest of the image using a non-generative image model, thereby obtaining first image data; and encoding any remainder of the image using a generative image model, thereby obtaining second image data, wherein use of the non-generative image model enables decoding of the first image data without relying on information derived from images other than the encoded image or, if the image is a frame in a video sequence, enables decoding of the first image data without relying on information derived from images outside the video sequence.

公开(公告)号：US11783710B2

公开(公告)日：2023-10-10

申请号：US17357446

申请日：2021-06-24

Applicant: Humanising Autonomy Limited

Inventor： Raunaq Bose ,  Leslie Cees Nooteboom ,  Maya Audrey Lara Pindeus

IPC: G08B23/00 ,  G08G1/16 ,  G06N20/00 ,  G06V20/52 ,  B60W40/09 ,  B60W50/14 ,  G08G1/017 ,  G06V10/80 ,  G06V20/40 ,  G06V20/58 ,  G06V40/20 ,  B60W40/08

CPC classification number: G08G1/166 ,  B60W40/09 ,  B60W50/14 ,  G06N20/00 ,  G06V10/809 ,  G06V20/46 ,  G06V20/52 ,  G06V20/58 ,  G06V40/20 ,  G08G1/0175 ,  B60W2040/0863 ,  B60W2540/26 ,  B60W2540/30 ,  G06V2201/07 ,  G06V2201/08

Abstract: The systems and methods disclosed herein provide a risk prediction system that uses trained machine learning models to make predictions that a VRU will take a particular action. The system first receives, in a video stream, an image depicting a VRU operating a micro-mobility vehicle and extract the depictions from the image. The extraction process may be determined by bounding box classifiers trained to identify various VRUs and micro-mobility vehicles. The system feeds the extracted depictions to machine learning models and receives, as an output, risk profiles for the VRU and the micro-mobility vehicle. The risk profile may include data associated with the VRU/micro-mobility vehicle determined based on classifications of the VRU and the micro-mobility vehicles. The system may then generate a prediction that the VRU operating the micro-mobility vehicle will take a particular action based on the risk profile.

公开(公告)号：US20230316761A1

公开(公告)日：2023-10-05

申请号：US18175146

申请日：2023-02-27

Applicant: Toshiba Tec Kabushiki Kaisha

Inventor： Masachika KURATA

IPC: G06Q20/40 ,  G06V20/52 ,  G06V20/40

CPC classification number: G06V20/52 ,  G06Q20/4016 ,  G06V20/44 ,  G06V2201/07

Abstract: According to one embodiment, a fraudulent act detection device includes a processor and a camera interface to connect to a camera positioned to acquire images of a purchaser at a settlement terminal. The processor is configured to recognize an action of the purchaser at the settlement terminal from an image acquired from the camera via the camera interface, acquire a degree of reliability for the recognition of the action of the purchaser, determine whether a change condition for changing a degree of reliability threshold has been met, set a value for the degree of reliability threshold based on whether or not the change condition has been met, and use the set value for the degree of reliability threshold in determining whether a fraudulent act of the purchaser has been recognized in acquired images of the purchaser at the settlement terminal.

公开(公告)号：US20230315373A1

公开(公告)日：2023-10-05

申请号：US18132669

申请日：2023-04-10

Applicant: Sudheer Kumar Pamuru ,  Madhukiran Dandamudi ,  Vineel Kurma

Inventor： Sudheer Kumar Pamuru ,  Madhukiran Dandamudi ,  Vineel Kurma

IPC: G06F3/14 ,  G06T7/194 ,  G06V10/44 ,  G06V10/60 ,  G06V20/62

CPC classification number: G06F3/14 ,  G06T7/194 ,  G06V10/44 ,  G06V10/60 ,  G06V20/625 ,  G06V2201/07 ,  G06T2207/30252

Abstract: The present disclosure is directed to automatically curating a set of images according to a predetermined set of compliance rules and displaying those images. The machine learning and artificial intelligence technology can differentiate between images and identify features within images. The features may include a desired perspective, inconsistent backgrounds, low detail, blurriness, shadows, glare, reflections, unwanted information, unwanted elements, poles, trees, lack or focus, poor resolution, rain, snow, fumes, smoke, mud, unwanted banners, unwanted overlays, etc.
The technology is trained to identify these features in the images and automatically tag the images with information relating to the features. A user selects a set of predetermined rules to be applied to the images. The technology then uses the tags to apply these selected rules to the images to modify the images and display the modified images in a predetermined sequence and arrangement.

公开(公告)号：US11776271B2

公开(公告)日：2023-10-03

申请号：US17384406

申请日：2021-07-23

Applicant: Honeywell International Inc.

Inventor： Kirupakar Janakiraman ,  Naga Sundar KandhaMunisamy ,  Rajesh Kulandaivel Sankarapandian ,  Ramesh Arumaikani ,  Keyurbhai Patel ,  Baskaran Muthusamy

IPC: G06V20/40 ,  G11B27/10 ,  G06V20/30 ,  G06V20/52

CPC classification number: G06V20/47 ,  G06V20/30 ,  G06V20/52 ,  G11B27/10 ,  G06V2201/07 ,  G06V2201/10

Abstract: Systems and methods for creating a story board with forensic video analysis on a video repository are provided. Some methods can include storing a plurality of video data streams in a data repository, storing asynchronous streams of metadata of each of the plurality of video data streams in the data repository, identifying a first object captured by at least one of the plurality of video data streams, using the asynchronous streams of metadata to identify correlations or interactions between the first object and a plurality of other objects over time, and replicating a story of the first object.

公开(公告)号：US20230298340A1

公开(公告)日：2023-09-21

申请号：US18101784

申请日：2023-01-26

Applicant: HONDA MOTOR CO., LTD.

Inventor： Naoki HOSOMI

IPC: G06V10/98 ,  G06V20/58 ,  G06V10/776 ,  G06V10/77

CPC classification number: G06V10/987 ,  G06V10/7715 ,  G06V10/776 ,  G06V20/58 ,  G06V2201/07

Abstract: An information processing apparatus of the present invention comprises acquires a captured image; detects a plurality of targets included in the captured image, and extracts a plurality of features for each of the detected plurality of targets; acquires an impurity for each extracted feature, the impurity indicating a degree to which a predetermined target is inseparable from among the plurality of targets in a case where a user is asked a question for presuming the predetermined target from among the plurality of targets based on each feature; and generates the question to reduce a number of questions for minimizing the impurity based on the extracted features and the impurity for each of the features.

公开(公告)号：US20230298174A1

公开(公告)日：2023-09-21

申请号：US18180899

申请日：2023-03-09

Applicant: CANON KABUSHIKI KAISHA

Inventor： Itaru OTOMARU

IPC: G06T7/00 ,  G06T15/00 ,  G06V10/75 ,  G06F3/14

CPC classification number: G06T7/0012 ,  G06T15/00 ,  G06V10/751 ,  G06F3/14 ,  G06V2201/07 ,  G06T2207/20081 ,  G06T2207/30048

Abstract: An image processing apparatus includes a memory storing a program, and a processor which, by executing the program, causes the image processing apparatus to acquire data including a three-dimensional image obtained by capturing an image of a subject under examination, a standard plane parameter representing a predetermined standard plane in the three-dimensional image, and an anatomical landmark position in the three-dimensional image, and acquire a vicinity cross section image defining a cross section in the vicinity of the predetermined standard plane. The processor further causes the image processing apparatus to acquire the anatomical landmark position on the vicinity cross section image, and acquire a learning model generated by using information including the vicinity cross section image and the anatomical landmark position acquired by the image processing apparatus to estimate, from the cross section image, an anatomical landmark position on the cross section image.

公开(公告)号：US20230289998A1

公开(公告)日：2023-09-14

申请号：US18019431

申请日：2020-08-14

Applicant: NEC Corporation

Inventor： Tetsuo Inoshita

IPC: G06T7/73 ,  G06V20/52

CPC classification number: G06T7/73 ,  G06V20/52 ,  G06T2207/20044 ,  G06V2201/07

Abstract: In an object recognition device, an estimation means estimates a possession of the person based on a pose of a person in an image. An object detection means detects an object from surroundings of the person in the image. A weighting means sets weights with respect to an estimation result of the possession and a detection result of the object based on the image. A combination unit combines the estimation result of the possession and the detection result of the object by using the weights being set, and recognizes the possession of the person.

公开(公告)号：US20230286164A1

公开(公告)日：2023-09-14

申请号：US18171841

申请日：2023-02-21

Applicant: TOYOTA JIDOSHA KABUSHIKI KAISHA

Inventor： Suomi TANISHIGE ,  Nobuyuki Matsuno

IPC: B25J9/16 ,  B25J9/00 ,  G06V10/764 ,  G06V20/64

CPC classification number: B25J9/1697 ,  B25J9/0093 ,  G06V10/764 ,  G06V20/64 ,  G06V2201/06 ,  G06V2201/07

Abstract: A conveyance system includes: a first recognition device configured to identify whether or not a target object is an object of a first type; and a work robot configured to classify the target object as the object of the first type when the target object is identified as the object of the first type by the first recognition device and to classify the target object as an object of a type corresponding to position information in a conveyance container when the target object is an object that is not identified as the object of the first type by the first recognition device.

公开(公告)号：US11756338B2

公开(公告)日：2023-09-12

申请号：US17682000

申请日：2022-02-28

Applicant: NEC Corporation

Inventor： Takashi Shibata ,  Shoji Yachida ,  Chisato Funayama ,  Masato Tsukada ,  Yuka Ogino ,  Keiichi Chono ,  Emi Kitagawa ,  Yasuhiko Yoshida ,  Yusuke Mori

IPC: G06V40/70 ,  G06V40/18 ,  G06V20/52 ,  G06V40/16 ,  G06V40/19 ,  G06V40/10

CPC classification number: G06V40/70 ,  G06V20/52 ,  G06V40/103 ,  G06V40/171 ,  G06V40/19 ,  G06V40/197 ,  G06V2201/07

Abstract: The disclosure is detecting an authentication target who is moving in a predetermined direction in a video; inputting a first image in which an entire body of the target; calculating characteristic information from an image of the entire body in the first image, comparing the calculated characteristic information with characteristic information of the entire body stored in first memory that stores characteristic information of entire bodies of targets, and extracting candidate information of the targets from the first memory based on a first authentication result; inputting a second image in which an iris of the target; and comparing characteristic information of irises stored in second memory that stores the characteristic information of the irises of targets with characteristic information of an iris from the second image, calculating a verification score, executing second authentication on the target in the second image based on the verification score, and outputting an authentication result.