-
41.发明授权公开(公告)号：US11689820B2
公开(公告)日：2023-06-27
申请号：US17142672
申请日：2021-01-06
Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC
Inventor： Tzvi Philipp , Michael Slutsky
IPC: H04N23/951 , G06T5/00 , G06T5/50 , G06T3/40 , G06N3/08 , B60R11/04 , G06N3/045 , H04N23/90 , H04N23/617 , H04N23/12
CPC classification number: H04N23/951 , B60R11/04 , G06N3/045 , G06N3/08 , G06T3/4046 , G06T3/4053 , G06T5/006 , G06T5/50 , H04N23/617 , H04N23/90 , B60R2300/105 , B60R2300/303 , G06T2207/10024 , G06T2207/20081 , G06T2207/20084 , G06T2207/30252 , H04N23/12
Abstract: A vehicle control system for automated driver-assistance includes a low-resolution color camera that captures a color image of a field of view at a first resolution. The vehicle control system further includes a high-resolution scanning camera that captures a plurality of grayscale images, each of the grayscale images at a second resolution. The second resolution is higher than the first resolution. The grayscale images encompass the same field of view as the color image. The vehicle control system further includes one or more processors that perform a method that includes overlaying the plurality of grayscale images over the color image. The method further includes correcting motion distortion of one or more objects in the grayscale images. The method further includes generating a high-resolution output image by assigning color values to one or more pixels in the grayscale images based on the color image using a trained neural network.
-
公开(公告)号：US11683458B2
公开(公告)日：2023-06-20
申请号：US17388794
申请日：2021-07-29
Applicant: GM Global Technology Operations LLC
Inventor： Michael Slutsky , Albert Shalumov
IPC: H04N9/31 , B60K35/00 , H04N23/698
CPC classification number: H04N9/3176 , B60K35/00 , H04N23/698 , B60K2370/176 , B60K2370/334
Abstract: Systems and methods for projecting a multi-faceted image onto a convex polyhedron based on an input image are described. A system can include a controller configured to determine a mapping between pixels within a wide-angle image and a multi-faceted image, and generate the multi-faceted image based on the mapping.
-
公开(公告)号：US20230031894A1
公开(公告)日：2023-02-02
申请号：US17388794
申请日：2021-07-29
Applicant: GM Global Technology Operations LLC
Inventor： Michael Slutsky , Albert Shalumov
Abstract: Systems and methods for projecting a multi-faceted image onto a convex polyhedron based on an input image are described. A system can include a controller configured to determine a mapping between pixels within a wide-angle image and a multi-faceted image, and generate the multi-faceted image based on the mapping.
-
44.发明申请公开(公告)号：US20220217272A1
公开(公告)日：2022-07-07
申请号：US17142672
申请日：2021-01-06
Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC
Inventor： Tzvi Phillipp , Michael Slutsky
IPC: H04N5/232 , H04N5/247 , H04N9/07 , G06T5/00 , G06T5/50 , G06T3/40 , G06N3/08 , G06N3/04 , B60R11/04
Abstract: A vehicle control system for automated driver-assistance includes a low-resolution color camera that captures a color image of a field of view at a first resolution. The vehicle control system further includes a high-resolution scanning camera that captures a plurality of grayscale images, each of the grayscale images at a second resolution. The second resolution is higher than the first resolution. The grayscale images encompass the same field of view as the color image. The vehicle control system further includes one or more processors that perform a method that includes overlaying the plurality of grayscale images over the color image. The method further includes correcting motion distortion of one or more objects in the grayscale images. The method further includes generating a high-resolution output image by assigning color values to one or more pixels in the grayscale images based on the color image using a trained neural network.
-
公开(公告)号：US20210295476A1
公开(公告)日：2021-09-23
申请号：US16821081
申请日：2020-03-17
Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC
Inventor： Michael Slutsky , Tzvi Philipp
Abstract: Method and systems for image deblurring in a vehicle. The methods and systems include determining a point spread function based on vehicle motion data and a depth map received from vehicle motion sensors and a depth sensor. A deblur matrix is calculated based on the point spread function. A blurred input image, received from an imaging device, is deblurred based on the deblur matrix to thereby provide a deblurred output image. A function of the vehicle is controlled based on the deblurred output image.
-
Patent Agency Ranking
公开(公告)号：US10997737B2
公开(公告)日：2021-05-04
申请号：US16401696
申请日：2019-05-02
Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC
Inventor： Ofer Geva , Michael Slutsky
Abstract: A system and method for aligning image data from a vehicle camera is provided. The method includes: obtaining image data from the vehicle camera; obtaining sensor data from vehicle sensor(s); carrying out a yaw/pitch estimation process to obtain yaw/pitch camera alignment information that includes a yaw misalignment estimate and a pitch misalignment estimate, wherein the yaw/pitch estimation process uses the image data and the sensor data to determine three-dimensional points of identified features within frames of the image data; after the yaw/pitch estimation process, carrying out a roll estimation process to obtain roll alignment information that includes a roll misalignment estimate, wherein the roll estimation process includes using the yaw/pitch camera alignment information; and applying camera alignment information to the image data to obtain aligned image data, wherein the camera alignment information includes information based on the yaw/pitch camera alignment information, the roll alignment information, or both.
-
公开(公告)号：US20210123754A1
公开(公告)日：2021-04-29
申请号：US16663706
申请日：2019-10-25
Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC
Inventor： Emanuel Mordechai , Michael Slutsky
Abstract: A vehicle, system and method for aligning a sensor with the vehicle. A first inertial measurement unit (IMU) associated with the vehicle obtains a first measurement of a kinematic vector of the vehicle. A second IMU associated with the sensor obtains a second measurement of the kinematic vector. A processor determines a current relative orientation between a first reference frame associated with the vehicle and a second reference frame associated with the sensor from the kinematic vector, determines an alignment error between the sensor and the vehicle based on the current relative orientation and a specified relative orientation, and adjusts the sensor from the current relative orientation to the specified relative orientation to correct for the alignment error.
-
公开(公告)号：US20200349723A1
公开(公告)日：2020-11-05
申请号：US16401696
申请日：2019-05-02
Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC
Inventor： Ofer Geva , Michael Slutsky
Abstract: A system and method for aligning image data from a vehicle camera is provided. The method includes: obtaining image data from the vehicle camera; obtaining sensor data from vehicle sensor(s); carrying out a yaw/pitch estimation process to obtain yaw/pitch camera alignment information that includes a yaw misalignment estimate and a pitch misalignment estimate, wherein the yaw/pitch estimation process uses the image data and the sensor data to determine three-dimensional points of identified features within frames of the image data; after the yaw/pitch estimation process, carrying out a roll estimation process to obtain roll alignment information that includes a roll misalignment estimate, wherein the roll estimation process includes using the yaw/pitch camera alignment information; and applying camera alignment information to the image data to obtain aligned image data, wherein the camera alignment information includes information based on the yaw/pitch camera alignment information, the roll alignment information, or both.
-
公开(公告)号：US10509120B2
公开(公告)日：2019-12-17
申请号：US15434492
申请日：2017-02-16
Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC
Inventor： Igal Bilik , Michael Slutsky , Shahar Villeval
IPC: G01S13/86 , G01S7/40 , G01S7/497 , G01S13/93 , G01S17/02 , G01S17/93 , H01Q15/18 , G01S17/66 , G01S17/89 , H01Q1/32
Abstract: A method and apparatus for calibrating a LiDAR system at a first location with a radar system at a second location. A calibration target is placed at a location and orientation with respect to the LiDAR system and the radar system. Coefficients of a plane of the calibration target are determined in a frame of reference of the LiDAR system. Coordinates of the calibration target are determined in a frame of reference of the radar system. A cost function is composed from a planar equation that includes the determined coefficients and the determined coordinates and a relative pose matrix that transforms the frame of reference of the radar system to the frame of reference of the LiDAR system. The cost function is reduced to estimate the relative pose matrix for calibration of the LiDAR system with the radar system.
-
公开(公告)号：US20190041865A1
公开(公告)日：2019-02-07
申请号：US15667070
申请日：2017-08-02
Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC
Inventor： Ariel Lipson , Michael Slutsky , Itai Afek
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 at different wavelengths. The multiple lasers are detected and separated by wavelength in order to decrease acquisition time and/or increase point density.
-
-
-
-
-
-
-
-
-
Search Results
53
records
(took 0.024 seconds)
