公开(公告)号：US20230260397A1

公开(公告)日：2023-08-17

申请号：US18176648

申请日：2023-03-01

Applicant: Hayden AI Technologies, Inc.

Inventor： Bo SHEN ,  Bryan John SHEA ,  Stuart Montagu MCKEE

IPC: G08G1/017 ,  H04L9/32 ,  G06V10/82 ,  H04L9/00 ,  G06V20/62 ,  G06F21/62

CPC classification number: G08G1/0175 ,  H04L9/3236 ,  G06V10/82 ,  H04L9/50 ,  G06V20/625 ,  G06F21/6254 ,  G06Q2220/00 ,  G06V2201/08 ,  G06V2201/07

Abstract: Disclosed herein are methods and systems for managing traffic violation or enforcement data using a distributed ledger. The distributed ledger provides a transparent chain of custody/evidence related to all digital interactions with traffic violation or enforcement data. The distributed ledger can be audited for data accuracy and integrity by nodes making up the system each time one of the nodes interacts with the traffic violation or enforcement data. For example, a digital evidence package related to a traffic violation event can be generated by a node within the system and a package digest can be logged in the distributed ledger beginning with the creation of the digital evidence package and each time that the digital evidence package is processed, modified, or reviewed by nodes within the system.

公开(公告)号：US20230260287A1

公开(公告)日：2023-08-17

申请号：US18302386

申请日：2023-04-18

Applicant: SITA Information Networking Computing Canada Inc.

Inventor： Sid RYAN

IPC: G06V20/54 ,  G06V20/40 ,  G06V10/764 ,  G06T7/70

CPC classification number: G06V20/54 ,  G06V20/44 ,  G06V10/764 ,  G06T7/70 ,  G06V2201/07 ,  G06T2207/10028

Abstract: A system for generating a labelled dataset is provided. The system comprises processor configured to: receive first data wherein the first data comprises one or more frames and wherein the first data comprises data defining an object of interest within a predetermined area; receive second data wherein the second data is associated with the object of interest within the predetermined area; analyse the one or more frames of the first data to identify, based on the second data, the object of interest present in the first data; label the one or more frames of the first data based on the analysis to generate a labelled dataset; and output the labelled dataset. Also provided is a method for generating a labelled dataset, a system for training a machine learning model, and a detection system for detecting one or more objects of interest.

公开(公告)号：US11727795B1

公开(公告)日：2023-08-15

申请号：US17805296

申请日：2022-06-03

Applicant: Hayden Al Technologies, Inc.

Inventor： Bo Shen ,  Bryan John Shea ,  Stuart Montagu McKee

IPC: G06F21/62 ,  G08G1/017 ,  H04L9/32 ,  G06V10/82 ,  G06V20/62 ,  H04L9/00

CPC classification number: G08G1/0175 ,  G06F21/6254 ,  G06V10/82 ,  G06V20/625 ,  H04L9/3236 ,  H04L9/50 ,  G06Q2220/00 ,  G06V2201/07 ,  G06V2201/08

Abstract: Disclosed herein are methods and systems for managing traffic violation or enforcement data using a distributed ledger. The distributed ledger provides a transparent chain of custody/evidence related to all digital interactions with traffic violation or enforcement data. The distributed ledger can be audited for data accuracy and integrity by nodes making up the system each time one of the nodes interacts with the traffic violation or enforcement data. For example, a digital evidence package related to a traffic violation event can be generated by a node within the system and a package digest can be logged in the distributed ledger beginning with the creation of the digital evidence package and each time that the digital evidence package is processed, modified, or reviewed by nodes within the system.

公开(公告)号：US20230254549A1

公开(公告)日：2023-08-10

申请号：US18012587

申请日：2021-06-03

Applicant: CANON KABUSHIKI KAISHA

Inventor： Franck DENOUAL ,  Frédéric MAZE ,  Hervé RUELLAN

IPC: H04N21/81 ,  G06T7/50 ,  G06T7/60 ,  G06V10/25 ,  H04N21/84

CPC classification number: H04N21/8153 ,  G06T7/50 ,  G06T7/60 ,  G06V10/25 ,  H04N21/84 ,  G06V2201/07

Abstract: The present invention concerns a method of generating a media file, the method comprising: generating a first track of media data samples; generating at least one annotated region, the annotated region being associated with a geometry of the annotated region, the annotated region being associated with at least one region annotation describing the annotated region; wherein the annotated region is associated with the first track of media data samples; and generating a media file including the first track and the at least one annotated region, associated geometry and associated region annotation.

公开(公告)号：US20230252736A1

公开(公告)日：2023-08-10

申请号：US18101147

申请日：2023-01-25

Applicant: Apple Inc.

Inventor： Elizabeth V. Petrov ,  Ioana Negoita

IPC: G06T19/00 ,  H04N5/265 ,  G06V10/764 ,  H04L51/046 ,  H04L51/08

CPC classification number: G06T19/006 ,  H04N5/265 ,  G06V10/764 ,  H04L51/046 ,  H04L51/08 ,  G06V2201/07

Abstract: In one implementation, a method for surfacing an XR object corresponding to an electronic message. The method includes: obtaining an electronic message from a sender; in response to determining that the electronic message is associated with a real-world object, determining whether a current field-of-view (FOV) of a physical environment includes the real-world object; and in accordance with a determination that the current FOV of the physical environment includes the real-world object, presenting, via the display device, an extended reality (XR) object that corresponds to the electronic message in association with the real-world object.

公开(公告)号：US20230245789A1

公开(公告)日：2023-08-03

申请号：US18010156

申请日：2021-05-25

Applicant: NEC Corporation

Inventor： Pujianto Christopher CHIAM ,  Hui Lam ONG ,  Satoshi YAMAZAKI ,  Adeline CHONG

IPC: G16H50/80 ,  G06F16/901 ,  G06V10/56 ,  G06V10/74

CPC classification number: G16H50/80 ,  G06F16/9024 ,  G06V10/56 ,  G06V10/761 ,  G06V2201/07

Abstract: According to an a first aspect, there is a method of adaptively displaying at least one potential subject and a target subject, the method comprising receiving an input selecting the target subject from a network graph including a plurality of subjects who appear in the proximity as the target subject (204); identifying the at least one potential subject based on a threshold, the threshold indicating the minimum level of relatedness from the target subject (206); and displaying the at least one potential subject, the target subject and an edge between each of the at least one potential subject and the target subject, the edge indicating a level of relationship between the at least one potential subject and the target subject (208).

公开(公告)号：US11715251B2

公开(公告)日：2023-08-01

申请号：US17507620

申请日：2021-10-21

Applicant: NVIDIA Corporation

Inventor： Jonathan Tremblay ,  Aayush Prakash ,  Mark A. Brophy ,  Varun Jampani ,  Cem Anil ,  Stanley Thomas Birchfield ,  Thang Hong To ,  David Jesus Acuna Marrero

IPC: G06T15/00 ,  G06T15/04 ,  G06T15/50 ,  G06T15/20 ,  G06F18/214 ,  G06F18/211 ,  G06V10/774 ,  G06V10/82 ,  G06N3/04 ,  G06N3/084

CPC classification number: G06T15/00 ,  G06F18/211 ,  G06F18/2148 ,  G06T15/04 ,  G06T15/20 ,  G06T15/50 ,  G06V10/7747 ,  G06V10/82 ,  G06N3/04 ,  G06N3/084 ,  G06T2210/12 ,  G06V2201/07

Abstract: Training deep neural networks requires a large amount of labeled training data. Conventionally, labeled training data is generated by gathering real images that are manually labelled which is very time-consuming. Instead of manually labelling a training dataset, domain randomization technique is used generate training data that is automatically labeled. The generated training data may be used to train neural networks for object detection and segmentation (labelling) tasks. In an embodiment, the generated training data includes synthetic input images generated by rendering three-dimensional (3D) objects of interest in a 3D scene. In an embodiment, the generated training data includes synthetic input images generated by rendering 3D objects of interest on a 2D background image. The 3D objects of interest are objects that a neural network is trained to detect and/or label.

公开(公告)号：US20230237811A1

公开(公告)日：2023-07-27

申请号：US18187508

申请日：2023-03-21

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Darya Frolova ,  Shahar Ben Ezra ,  Pavel Kisilev ,  Xiaoli She ,  Yu Xie

IPC: G06V20/58 ,  G06V20/56 ,  G06T5/00 ,  G06V10/82

CPC classification number: G06V20/58 ,  G06V20/588 ,  G06T5/002 ,  G06V10/82 ,  G06V2201/07

Abstract: A method and a computing device for object detection and tracking from a video input are described. The method and the computing device may be used to, for example, track objects of interest, such as lane markings, in traffic. A plurality of frames corresponding to a video may be analyzed in a spatiotemporal domain by a neural network. The neural network may be trained using data synthesized in the spatiotemporal domain.

公开(公告)号：US20230237801A1

公开(公告)日：2023-07-27

申请号：US17923883

申请日：2020-07-30

Applicant: Intel Corporation

Inventor： Longwei FANG ,  Qiang LI ,  Wenlong LI ,  Yikai FANG ,  Hang ZHENG

IPC: G06V20/40 ,  G06T7/292 ,  G06V10/26

CPC classification number: G06V20/42 ,  G06T7/292 ,  G06V10/267 ,  G06V2201/07 ,  G06V2201/12

Abstract: Techniques related to performing object or person association or correspondence in multi-view video are discussed. Such techniques include determining correspondences at a particular time instance based on separately optimizing correspondence sub-matrices for distance sub-matrices based on two-way minimum distance pairs between frame pairs, generating and fusing tracklets across time instances, and adjusting correspondence, after such tracklet processing, via elimination of outlier object positions and rearrangement of object correspondence.

公开(公告)号：US20230230390A1

公开(公告)日：2023-07-20

申请号：US17981546

申请日：2022-11-07

Applicant: TOYOTA JIDOSHA KABUSHIKI KAISHA

Inventor： Takenoshin TAKAHASHI

IPC: G06V20/58 ,  G06V20/56

CPC classification number: G06V20/582 ,  G06V20/588 ,  G06V2201/07

Abstract: The wrong-way driving determination method includes acquiring a backward image of the vehicle, recognizing a target included in the backward image, and determining the wrong-way driving of the vehicle based on the recognition information of the target. Here, determining the wrong-way driving includes determining whether or not the recognition information of the target includes the recognition information of the guide display surface of the traffic sign. When it is determined that the recognition information of the guide display surface is included in the recognition information of the target, it is determined that the vehicle is traveling in the wrong direction.