公开(公告)号：US20230419679A1

公开(公告)日：2023-12-28

申请号：US17846783

申请日：2022-06-22

Applicant: GM Cruise Holdings LLC

Inventor： Burkay Donderici

IPC: G06V20/58 ,  G06V10/774 ,  G06V10/80 ,  G08G1/017

CPC classification number: G06V20/58 ,  G06V10/774 ,  G06V10/80 ,  G08G1/017 ,  G06V2201/08

Abstract: Particular embodiments described herein provide for a system and method for determining an intent of a third-party autonomous vehicle by an autonomous vehicle. The method can include identifying the third-party autonomous vehicle, identifying a third-party autonomous vehicle behavior signature associated with the third-party autonomous vehicle, capturing sensor data related to the third-party autonomous vehicle, analyzing the captured sensor data to determine behaviors of the third-party autonomous vehicle, and using a third-party autonomous vehicle behavior signature to determine if the behaviors of the third-party autonomous vehicle indicate a specific intent of the third-party autonomous vehicle. The third-party autonomous vehicle behavior signature can be created by identifying behaviors of the third-party autonomous vehicle and associating the behaviors with an intent of the third-party autonomous vehicle.

公开(公告)号：US11854280B2

公开(公告)日：2023-12-26

申请号：US17242046

申请日：2021-04-27

Applicant: TOYOTA RESEARCH INSTITUTE, INC.

Inventor： Arjun Bhargava ,  Haofeng Chen ,  Adrien David Gaidon ,  Rares A. Ambrus ,  Sudeep Pillai

IPC: G06V20/00 ,  G06V20/64 ,  G05D1/02 ,  G06V20/40 ,  G06V20/56 ,  G06F18/214 ,  G06F18/21 ,  G06N3/04

CPC classification number: G06V20/64 ,  G05D1/0251 ,  G06F18/214 ,  G06F18/2163 ,  G06V20/41 ,  G06V20/46 ,  G06V20/56 ,  G05D2201/0213 ,  G06N3/04 ,  G06V2201/08

Abstract: A method for 3D object detection is described. The method includes detecting semantic keypoints from monocular images of a video stream capturing a 3D object. The method also includes inferring a 3D bounding box of the 3D object corresponding to the detected semantic vehicle keypoints. The method further includes scoring the inferred 3D bounding box of the 3D object. The method also includes detecting the 3D object according to a final 3D bounding box generated based on the scoring of the inferred 3D bounding box.

公开(公告)号：US20230410532A1

公开(公告)日：2023-12-21

申请号：US18037020

申请日：2020-12-25

Applicant: Mitsubishi Electric Corporation

Inventor： Tomoya SAWADA ,  Ken FUKUCHI

IPC: G06V20/58 ,  G01J5/00 ,  G06V10/77 ,  G06V10/774 ,  G06V10/82 ,  G06V10/764 ,  G06T7/73 ,  G06T7/00 ,  G06T7/246

CPC classification number: G06V20/58 ,  G01J5/0025 ,  G06V10/7715 ,  G06V10/774 ,  G06V10/82 ,  G06V10/764 ,  G06T7/73 ,  G06T7/0002 ,  G06T7/246 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06V2201/08 ,  G06T2207/30261 ,  G06T2207/10016

Abstract: An object detection device includes an image data acquiring unit that acquires image data indicating an image captured by a camera, a first feature amount extracting unit that generates a first feature map using the image data, a second feature amount extracting unit that generates a second feature map using the image data, and generates a third feature map by performing addition or multiplication of the second feature map using the first feature map and weighting the second feature map, and the object detection unit that detects an object in the captured image using the third feature map. A first feature amount in the first feature map uses a mid-level feature corresponding to objectness, and a second feature amount in the second feature map uses a high-level feature.

公开(公告)号：US20230382380A1

公开(公告)日：2023-11-30

申请号：US17751786

申请日：2022-05-24

Applicant: Honda Motor Co., Ltd.

Inventor： Jose I. Herrero Zarzosa

IPC: B60W30/165 ,  B60W30/12 ,  G06V20/56 ,  G06V20/58

CPC classification number: B60W30/165 ,  B60W30/12 ,  G06V20/588 ,  G06V20/584 ,  B60W2420/42 ,  B60W2552/53 ,  B60W2710/20 ,  B60W2554/802 ,  B60W2554/4041 ,  B60W2554/402 ,  B60W2556/40 ,  B60W2556/45 ,  B60W2554/4045 ,  B60W2552/10 ,  G06V2201/08

Abstract: A vehicle is provided. The vehicle includes a plurality of sensors including a first sensor. The vehicle also includes a vehicle controller. The vehicle controller is programmed to (i) collect a plurality of sensor information; (ii) detect a first vehicle ahead of the vehicle in a direction of travel of the vehicle; (iii) detect two or more taillights of the first vehicle based on the plurality of sensor information; (iv) determine a distance between the two or more taillights; (v) calculate a following distance between the first vehicle and the vehicle based on the distance between the two or more taillights and the plurality of sensor information; (vi) detect a plurality of lane markings based on the plurality of sensor information; and (vii) adjust steering of the vehicle to follow the first vehicle based on the plurality of lane markings and the following distance.

公开(公告)号：US11822040B2

公开(公告)日：2023-11-21

申请号：US17255394

申请日：2020-01-06

Applicant: TSINGHUA UNIVERSITY ,  NUCTECH (BEIJING) COMPANY LIMITED ,  NUCTECH COMPANY LIMITED

Inventor： Yanwei Xu ,  Weifeng Yu ,  Yu Hu ,  Chunguang Zong ,  Shangmin Sun

IPC: G01S17/894 ,  G01V5/00

CPC classification number: G01V5/0016 ,  G01S17/894 ,  G06V2201/08

Abstract: The present disclosure relates to a security scanning inspection system and method. The security scanning inspection system comprises a detector, a scanning device and a controller, wherein the detector is configured to detect a protective attribute of an object to be inspected; the scanning device is movably arranged and the scanning device is configured to emit a scanning ray during movement to perform a security scanning inspection on the object to be inspected, the scanning device comprising at least two working modes, wherein a dose of a scanning ray in each working mode is different from a dose of a scanning ray in any other working modes; and the controller configured to select a working mode of the scanning device according to the protective attribute of the object to be inspected detected by the detector.

公开(公告)号：US20230368430A1

公开(公告)日：2023-11-16

申请号：US18227398

申请日：2023-07-28

Applicant: GOOGLE LLC

Inventor： Herbert Czymontek ,  Dan Li ,  Max Greenwald

IPC: G06T11/00 ,  G06V10/75 ,  G01C21/34 ,  G06T7/70 ,  G06Q50/30 ,  G06V20/20

CPC classification number: G06T11/00 ,  G06V10/751 ,  G01C21/3438 ,  G06T7/70 ,  G06Q50/30 ,  G06V20/20 ,  G06T2200/24 ,  G06V2201/08

Abstract: To present a pickup location in a transportation service, a server device receives a request for ridesharing services from a rider's current location to a drop-off location. The server device broadcasts the request to drivers and receives an indication of acceptance of the request from one of the drivers. Then the server device provides a pickup location to the rider and the driver which is presented in a map display of the rider and driver's client devices. When the rider or driver's current location is within a threshold distance of the pickup location, the corresponding client device switches to an augmented reality mode and presents a camera view from a camera of the client device depicting real-world imagery. The server device provides information to the corresponding client device to present in the augmented reality mode overlaying the real-world imagery to assist the rider or driver in finding the pickup location.

公开(公告)号：US20230360412A1

公开(公告)日：2023-11-09

申请号：US18171237

申请日：2023-02-17

Applicant: Agot Co.

Inventor： Evan DeSantola ,  Alex Litzenberger ,  Rassoul Mesbah ,  Prashasti Sar

IPC: G06V20/68 ,  G06V20/00 ,  G06T7/70 ,  G06Q20/20 ,  G06T7/11 ,  G06V10/70 ,  G06V20/52 ,  G01B11/22 ,  G06V10/764 ,  G06V20/20 ,  G06F3/0482 ,  G06N20/00 ,  G01S17/89 ,  G06T7/20 ,  H04N7/18 ,  G06V20/64 ,  G06Q50/12

CPC classification number: G06V20/68 ,  G06V20/36 ,  G06T7/70 ,  G06Q20/20 ,  G06T7/11 ,  H04N23/90 ,  G06V10/70 ,  G06V20/52 ,  G01B11/22 ,  G06V10/765 ,  G06V20/20 ,  G06F3/0482 ,  G06N20/00 ,  G01S17/89 ,  G06F18/214 ,  G06Q10/063112 ,  G06T7/20 ,  H04N7/18 ,  G06V20/64 ,  G06Q50/12 ,  G06T2207/30232 ,  G06T2207/10028 ,  G06T2207/20081 ,  G06V2201/08 ,  G06T2200/24

Abstract: The subject matter of this specification can be implemented in, among other things, methods, systems, computer-readable storage medium. A method can include receiving, by a processing device, image data having one or more image frames indicative of a state of a meal preparation area. The method may further include, determining, based on the image data, a first feature characterization of a first meal preparation item associated with the state of the meal preparation area. The method may further include determining that the first feature characterization does not meet object classification criteria for a set of object classifications. The method may further include causing a notification indicating the first meal preparation item and one of an object classification or a classification status corresponding to the first meal preparation item on a graphical user interface (GUI).

公开(公告)号：US20230351704A1

公开(公告)日：2023-11-02

申请号：US18007045

申请日：2020-07-27

Applicant: Telefonaktiebolaget LM Ericsson (publ)

Inventor： Paul MCLACHLAN ,  Héctor CALTENCO

IPC: G06T19/00 ,  G06T7/20 ,  G06V20/20

CPC classification number: G06T19/006 ,  G06T7/20 ,  G06V20/20 ,  G06T2207/20076 ,  G06V2201/08

Abstract: A method of an electronic device in an edge cloud of a mobile network supports extended reality overlay placement for an object having a location in the real world. The method includes receiving a request from an application of a user equipment, the request including an object identifier for an object that is a target of an extended reality overlay, and determining a static motion probability field (S-MPF) for the object identifier.

公开(公告)号：US20230351447A1

公开(公告)日：2023-11-02

申请号：US18041078

申请日：2021-08-09

Applicant: Truckscreenia SRL

Inventor： Alessandro PANCANI ,  Francesco PANCANI ,  Luciano DELMASTRO ,  Paolo PINTO

IPC: G06Q30/0251 ,  G06V20/58

CPC classification number: G06Q30/0266 ,  G06Q30/0252 ,  G06V20/58 ,  G06V2201/08

Abstract: A method for publishing advertising information comprising the following steps: (a) capturing an image; (b) deleting data which may result in a person and/or a vehicle; (c) deleting the image captured in step (a); (d) analysing the image produced in step (b); (e) deleting the image generated in step (b); (f) acquiring GNSS data and sensor data; (g) determining where in option A) the data remains unchanged, or in option B) the image is replaced by a random image from the land vehicle database after the capturing process in step a), and the captured image is deleted or the information obtained in step f) is replaced by a random image from the land vehicle database; (h) analysing the data obtained in step (d) and/or the data obtained in step (f); (i) selecting information based on the analysis (h) using predefined parameters in a database; (j) publishing the selected information.

公开(公告)号：US11804046B2

公开(公告)日：2023-10-31

申请号：US17489870

申请日：2021-09-30

Applicant: Rekor Systems, Inc.

Inventor： Matthew Anthony Hill ,  Alexandros Konstantinos Kouparoulis ,  Christopher Allen Kadoch

IPC: G06V20/54 ,  G06V10/20 ,  G06V20/62

CPC classification number: G06V20/54 ,  G06V10/255 ,  G06V20/63 ,  G06V20/625 ,  G06V2201/08

Abstract: A surveillance device includes an imaging unit configured generate full-quality image data from a captured image of a vehicle, an image filtering module that converts the full-quality image data to reduced-quality image data. The surveillance device also includes a subsector module that processes the reduced-quality image data to generate subsector data defining one or more sub sectors of the captured image, and an image processing module that identifies one or more specific vehicle characteristics within the one or more subsectors by applying image recognition processing on the full-quality image data only within the one or more subsectors. The reduced quality image data is insufficient for the image recognition processing to identify specific vehicle characteristics therefrom.