VANISHING POINT CALCULATOR
    361.
    发明公开

    公开(公告)号:US20240087336A1

    公开(公告)日:2024-03-14

    申请号:US18242572

    申请日:2023-09-06

    Inventor: Kohtaroh NAGAOKA

    CPC classification number: G06V20/588 G06T7/13 G06V10/44 G06V2201/07

    Abstract: A vanishing point calculator includes a controller connected to an imaging device configured to image in a vehicle traveling direction; and a storage device connected to the controller, wherein the controller is configured to: input an image imaged by the imaging device; extract positions of feature points from the image; store the positions of feature points related to a stationary object including a line segment parallel to road among the extracted feature points in the storage device for each image; overlap the feature points in a predetermined number of the images stored in the storage device based on the positions of the feature points; and calculate the position of vanishing point in the image imaged by the imaging device based on a line segment obtained by the overlapped feature points.

    OBJECT DETECTION SYSTEM AND METHOD FOR UPDATING CARTESIAN REPRESENTATION OF REGION OF INTEREST

    公开(公告)号:US20240087302A1

    公开(公告)日:2024-03-14

    申请号:US17931751

    申请日:2022-09-13

    Applicant: CRON AI LTD.

    Inventor: ROBERT DE TEMPLE

    CPC classification number: G06V10/803 G06V10/25 G06V10/82 G06V2201/07

    Abstract: A method for updating a cartesian representation includes receiving a sensor POV data based on a sensor data generated by at least one sensor for a plurality of view cones and generating a polar feature vector based on the sensor POV data. The polar feature vector includes a plurality of cone vectors corresponding to the plurality of view cones. The method further includes mapping at least one cell from a plurality of cells of the cartesian representation with at least one cone vector from the plurality of cone vectors, receiving at least one offset vector corresponding to the at least one cell, concatenating at least the at least one cone vector and the at least one offset vector to generate at least one transformed tensor for the at least one cell, and generating at least one learned output based on the at least one transformed tensor.

    INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD, AND RECORDING MEDIUM

    公开(公告)号:US20240087296A1

    公开(公告)日:2024-03-14

    申请号:US18271434

    申请日:2021-01-14

    CPC classification number: G06V10/774 G06V10/22 G06V10/87 G06V2201/07

    Abstract: An information processing device according to the present invention includes: a memory; and at least one processor coupled to the memory. The processor performs operations. The operations include: generating, based on inference target data include a detection target object, aggregate data smaller than the inference target data; and applying the aggregate data to a trained model to infer a first region that is a region of the detection target object in the aggregate data, generating packed data that is data packed with the first region or a region of the inference target data, applying the packed data to a trained model to infer a second region that is a region of the detection target object that is included, and inferring the detection target object in the inference target data based on the second region.

    Method Of Recognizing Position And Attitude Of Object, And Non-Transitory Computer-Readable Storage Medium

    公开(公告)号:US20240070896A1

    公开(公告)日:2024-02-29

    申请号:US18456761

    申请日:2023-08-28

    CPC classification number: G06T7/70 G06V10/771 G06V2201/07

    Abstract: A method of the present disclosure includes (a) generating an input image by imaging a scene containing the M objects by a camera, (b) obtaining a feature map showing feature amounts relating to the N keypoints from the input image using a learned machine learning model with the input image as input and the feature map as output, (c) obtaining three-dimensional coordinates of the N keypoints belonging to each of the M objects using the feature map, and (d) determining positions and attitudes of one or more objects of the M objects using the three-dimensional coordinates of the N keypoints belonging to each of the M objects, wherein (c) includes (c1) obtaining M×N keypoints having undetermined correspondence relationships with the M objects and determining the three-dimensional coordinates of the M×N keypoints, and (c2) grouping the M×N keypoints to the N keypoints belonging to each of the M objects.

    OBJECT LOCATION DETERMINATION
    369.
    发明公开

    公开(公告)号:US20240070893A1

    公开(公告)日:2024-02-29

    申请号:US17898079

    申请日:2022-08-29

    CPC classification number: G06T7/70 G06T1/60 G06V10/44 G06V10/761 G06V2201/07

    Abstract: Methods, apparatuses, and non-transitory machine-readable media associated with determining a location of an object are described. An object location determination can include receiving a user request associated with an object, receiving first signaling from a first image source, and receiving second signaling from a second image source. The object location determination can include writing data that is based at least in part on a combination of the user request, the first signaling, and the second signaling and determining a confidence level of identification of the object associated with the user request based on the user request, the first signaling, and the second signaling. The object location determination can include identifying output data representative of a location of the object based on the confidence level and transmitting the output data representative of the location of the object via third signaling.

Patent Agency Ranking