中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

53 records (took 0.038 seconds)

    PERTURBATIVE ALIGNMENT CORRECTION FOR SURROUND CAMERAS
    1.
    发明公开
    PERTURBATIVE ALIGNMENT CORRECTION FOR SURROUND CAMERAS 审中-公开

    公开(公告)号：US20240161339A1

    公开(公告)日：2024-05-16

    申请号：US17980171

    申请日：2022-11-03

    Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

    Inventor： Michael Slutsky ,  Yuval Zelig ,  Lior Stein ,  Avi Resler

    IPC: G06T7/80 ,  G06T7/73

    CPC classification number: G06T7/80 ,  G06T7/73 ,  G06T2207/30244

    Abstract: A method and system for correcting alignment of images received from cameras by estimating camera alignment parameters based on perturbative correction such that corrected alignment parameters satisfy pairwise epipolar constraints as well as global loop closure constraints. The corrected alignment parameters are estimated as a Least-Mean-Square solution to a system of linear equations and an estimation algorithm may be implemented as a part of a Random Sample Consensus criterion estimation for improved robustness. The method and system is fast and efficient and may be implemented in a real-time system.

    DEEP LEARNING BASED PARAMETRIZABLE SURROUND VISION
    2.
    发明申请
    DEEP LEARNING BASED PARAMETRIZABLE SURROUND VISION 有权

    公开(公告)号：US20220284221A1

    公开(公告)日：2022-09-08

    申请号：US17189917

    申请日：2021-03-02

    Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

    Inventor： Michael Slutsky ,  Albert Shalumov

    IPC: G06K9/00 ,  G06T7/70 ,  G06T7/50

    Abstract: Systems and methods for generating a virtual view of a scene captured by a physical camera are described. The physical camera captures an input image with multiple pixels. A desired pose of a virtual camera for showing the virtual view is set. The actual pose of the physical camera is determined, and an epipolar geometry between the actual pose of the physical camera and the desired pose of the virtual camera is defined. The input image and depth data of the pixels of the input image are resampled in epipolar coordinates. A controller performs disparity estimation of the pixels of the input image and a deep neural network, DNN, corrects disparity artifacts in the output image for the desired pose of the virtual camera. The complexity of correcting disparity artifacts in the output image by a DNN is reduced by using epipolar geometry.

    Non-line of sight obstacle detection and localization
    4.
    发明授权
    Non-line of sight obstacle detection and localization 有权

    公开(公告)号：US10395539B2

    公开(公告)日：2019-08-27

    申请号：US15161872

    申请日：2016-05-23

    Applicant: GM Global Technology Operations LLC

    Inventor： Michael Slutsky ,  Igal Bilik

    IPC: G08G1/16 ,  G01S13/62 ,  G01S13/86 ,  G01S13/42 ,  G01S13/536 ,  G01S13/538 ,  G01S13/93 ,  G01S13/88 ,  G05D1/02

    Abstract: A non-line of sight obstacle detection and localization system and method of detecting and localizing a non-line of sight object include receiving reflections at a detection system of a moveable platform, the reflections including direct and multipath reflections, identifying the reflections associated with static targets to retain the reflections associated with moving targets, and distinguishing between line of sight objects and non-line of sight objects among the moving targets. The method also includes localizing the non-line of sight objects relative to the platform and indicating approaching non-line of sight objects among the non-line of sight objects, the approaching non-line of sight objects moving toward the platform on a path that intersects the platform.

    THREE-DIMENSIONAL ALIGNMENT OF RADAR AND CAMERA SENSORS
    5.
    发明申请
    THREE-DIMENSIONAL ALIGNMENT OF RADAR AND CAMERA SENSORS 审中-公开

    公开(公告)号：US20190120934A1

    公开(公告)日：2019-04-25

    申请号：US15788048

    申请日：2017-10-19

    Applicant: GM Global Technology Operations LLC

    Inventor： Michael Slutsky ,  Daniel I. Dobkin ,  Shahar Villeval ,  Igal Bilik

    IPC: G01S7/40 ,  G01S13/86 ,  G06T7/73 ,  G06T7/33

    Abstract: A system and method to perform a three-dimensional alignment of a radar and a camera with an area of overlapping fields of view position a corner reflector within the area. The method includes obtaining sensor data for the corner reflector with the radar and the camera, and iteratively repositioning the corner reflector within the area and repeating the obtaining the sensor data. A rotation matrix and a translation vector are determined that align the radar and the camera such that a three-dimensional detection by the radar projects to a location on a two-dimensional image obtained by the camera according to the rotation matrix and the translation vector.

    Method and Apparatus Cross Segment Detection in a Lidar System
    6.
    发明申请
    Method and Apparatus Cross Segment Detection in a Lidar System 审中-公开

    公开(公告)号：US20190041522A1

    公开(公告)日：2019-02-07

    申请号：US15667062

    申请日：2017-08-02

    Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

    Inventor： Michael Slutsky ,  Ariel Lipson ,  Itai Afek

    IPC: G01S17/93

    Abstract: The present application generally relates communications and hazard avoidance within a monitored driving environment. More specifically, the application teaches a system for improved target object detection in a vehicle equipped with a laser detection and ranging LIDAR system by simultaneously transmitting multiple lasers in an array and resolving angular ambiguities using a plurality of horizontal detectors and a plurality of vertical detectors.

Patent Agency Ranking