-
公开(公告)号：US10175697B1
公开(公告)日：2019-01-08
申请号：US15906610
申请日：2018-02-27
Applicant: LUMINAR TECHNOLOGIES, INC.
Inventor： Prateek Sachdeva , Dmytro Trofymov
Abstract: Techniques for identifying and labeling distinct objects within 3-D images of environments in which vehicles operate, to thereby generate training data used to train models that autonomously control and/or operate vehicles, are disclosed. A 3-D image may be presented from various perspective views (in some cases, dynamically), and/or may be presented with a corresponding 2-D environment image in a side-by-side and/or a layered manner, thereby allowing a user to more accurately identify groups/clusters of data points within the 3-D image that represent distinct objects. Automatic identification/delineation of various types of objects depicted within 3-D images, automatic labeling of identified/delineated objects, and automatic tracking of objects across various frames of a 3-D video are disclosed. A user may modify and/or refine any automatically generated information. Further, at least some of the techniques described herein are equally applicable to 2-D images.
-
公开(公告)号：US10535191B2
公开(公告)日：2020-01-14
申请号：US15906529
申请日：2018-02-27
Applicant: LUMINAR TECHNOLOGIES, INC.
Inventor： Prateek Sachdeva , Dmytro Trofymov
IPC: G06T19/00 , G06K9/62 , G06T19/20 , G06K9/00 , G06T7/174 , G06T15/20 , G06F3/01 , G06K9/66 , G06F3/0484 , G06T7/12 , H04N13/361 , G06N20/00 , G05D1/02 , G06T17/05 , G06F3/0481 , G06T11/00 , G06T15/30 , G05D1/00 , G06N5/04 , G06N3/08 , G06N3/00 , G06F3/0486 , G06F3/0354
Abstract: Techniques for identifying and labeling distinct objects within 3-D images of environments in which vehicles operate, to thereby generate training data used to train models that autonomously control and/or operate vehicles, are disclosed. A 3-D image may be presented from various perspective views (in some cases, dynamically), and/or may be presented with a corresponding 2-D environment image in a side-by-side and/or a layered manner, thereby allowing a user to more accurately identify groups/clusters of data points within the 3-D image that represent distinct objects. Automatic identification/delineation of various types of objects depicted within 3-D images, automatic labeling of identified/delineated objects, and automatic tracking of objects across various frames of a 3-D video are disclosed. A user may modify and/or refine any automatically generated information. Further, at least some of the techniques described herein are equally applicable to 2-D images.
-
公开(公告)号：US10275689B1
公开(公告)日：2019-04-30
申请号：US15906443
申请日：2018-02-27
Applicant: LUMINAR TECHNOLOGIES, INC.
Inventor： Prateek Sachdeva , Dmytro Trofymov
IPC: G05D1/00 , G05D1/02 , G06F3/01 , G06K9/00 , G06K9/62 , G06K9/66 , G06T15/20 , G06T19/00 , G06T7/174
Abstract: Techniques for identifying and labeling distinct objects within 3-D images of environments in which vehicles operate, to thereby generate training data used to train models that autonomously control and/or operate vehicles, are disclosed. A 3-D image may be presented from various perspective views (in some cases, dynamically), and/or may be presented with a corresponding 2-D environment image in a side-by-side and/or a layered manner, thereby allowing a user to more accurately identify groups/clusters of data points within the 3-D image that represent distinct objects. Automatic identification/delineation of various types of objects depicted within 3-D images, automatic labeling of identified/delineated objects, and automatic tracking of objects across various frames of a 3-D video are disclosed. A user may modify and/or refine any automatically generated information. Further, at least some of the techniques described herein are equally applicable to 2-D images.
-
Patent Agency Ranking
公开(公告)号：US11841440B2
公开(公告)日：2023-12-12
申请号：US17535174
申请日：2021-11-24
Applicant: Luminar Technologies, Inc.
Inventor： Istvan Peter Burbank , Matthew D. Weed , Jason Paul Wojack , Jason M. Eichenholz , Dmytro Trofymov
CPC classification number: G01S17/931 , B60W60/001 , G01S7/484 , G01S7/4814 , G01S7/4817 , G01S17/10 , G01S17/89 , B60W30/09 , B60W30/14 , B60W2420/52
Abstract: In one embodiment, a lidar system includes a light source configured to emit pulses of light and a scanner configured to scan the emitted pulses of light along a high-resolution scan pattern located within a field of regard of the lidar system. The scanner includes one or more scan mirrors configured to (i) scan the emitted pulses of light along a first scan axis to produce multiple scan lines of the high-resolution scan pattern, where each scan line is associated with multiple pixels, each pixel corresponding to one of the emitted pulses of light and (ii) distribute the scan lines of the high-resolution scan pattern along a second scan axis. The high-resolution scan pattern includes one or more of: interlaced scan lines and interlaced pixels.
-
公开(公告)号：US20200209858A1
公开(公告)日：2020-07-02
申请号：US16294274
申请日：2019-03-06
Applicant: Luminar Technologies, Inc.
Inventor： Dmytro Trofymov , Pranav Maheshwari , Vahid R. Ramezani
Abstract: To generate a machine learning model for controlling autonomous vehicles, training sensor data is obtained from sensors associated with one or more vehicles, the sensor data indicative of physical conditions of an environment in which the one or more vehicles operate, and a machine learning (ML) model is trained using the training sensor data. The ML model generates parameters of the environment in response to input sensor data. A controller in an autonomous vehicle receives sensor data from one or more sensors operating in the autonomous vehicle, applies the received sensor data to the ML model to obtain parameters of an environment in which the autonomous vehicle operates, provides the generated parameters to a motion planner component to generate decisions for controlling the autonomous vehicle, and causes the autonomous vehicle to maneuver in accordance with the generated decisions.
-
公开(公告)号：US20190197778A1
公开(公告)日：2019-06-27
申请号：US15906529
申请日：2018-02-27
Applicant: LUMINAR TECHNOLOGIES, INC.
Inventor： Prateek Sachdeva , Dmytro Trofymov
IPC: G06T19/00 , G06T11/00 , G06F3/0481 , G06K9/00 , G06T15/30 , G06T7/174 , G06T15/20 , G06K9/62 , G06K9/66
Abstract: Techniques for identifying and labeling distinct objects within 3-D images of environments in which vehicles operate, to thereby generate training data used to train models that autonomously control and/or operate vehicles, are disclosed. A 3-D image may be presented from various perspective views (in some cases, dynamically), and/or may be presented with a corresponding 2-D environment image in a side-by-side and/or a layered manner, thereby allowing a user to more accurately identify groups/clusters of data points within the 3-D image that represent distinct objects. Automatic identification/delineation of various types of objects depicted within 3-D images, automatic labeling of identified/delineated objects, and automatic tracking of objects across various frames of a 3-D video are disclosed. A user may modify and/or refine any automatically generated information. Further, at least some of the techniques described herein are equally applicable to 2-D images.
-
公开(公告)号：US10169680B1
公开(公告)日：2019-01-01
申请号：US15906141
申请日：2018-02-27
Applicant: LUMINAR TECHNOLOGIES, INC.
Inventor： Prateek Sachdeva , Dmytro Trofymov
IPC: G06K9/62 , G06T19/20 , G06K9/00 , G06T7/174 , G06T15/20 , G06F3/01 , G06K9/66 , G06T19/00 , G05D1/02 , G05D1/00
Abstract: Techniques for identifying and labeling distinct objects within 3-D images of environments in which vehicles operate, to thereby generate training data used to train models that autonomously control and/or operate vehicles, are disclosed. A 3-D image may be presented from various perspective views (in some cases, dynamically), and/or may be presented with a corresponding 2-D environment image in a side-by-side and/or a layered manner, thereby allowing a user to more accurately identify groups/clusters of data points within the 3-D image that represent distinct objects. Automatic identification/delineation of various types of objects depicted within 3-D images, automatic labeling of identified/delineated objects, and automatic tracking of objects across various frames of a 3-D video are disclosed. A user may modify and/or refine any automatically generated information. Further, at least some of the techniques described herein are equally applicable to 2-D images.
-
公开(公告)号：US10169678B1
公开(公告)日：2019-01-01
申请号：US15906676
申请日：2018-02-27
Applicant: LUMINAR TECHNOLOGIES, INC.
Inventor： Prateek Sachdeva , Dmytro Trofymov
IPC: G06K9/62 , G06T15/20 , G06K9/00 , G06T7/12 , G06T19/00 , H04N13/361 , G06F3/0486 , G05D1/00 , G05D1/02
Abstract: Techniques for identifying and labeling distinct objects within 3-D images of environments in which vehicles operate, to thereby generate training data used to train models that autonomously control and/or operate vehicles, are disclosed. A 3-D image may be presented from various perspective views (in some cases, dynamically), and/or may be presented with a corresponding 2-D environment image in a side-by-side and/or a layered manner, thereby allowing a user to more accurately identify groups/clusters of data points within the 3-D image that represent distinct objects. Automatic identification/delineation of various types of objects depicted within 3-D images, automatic labeling of identified/delineated objects, and automatic tracking of objects across various frames of a 3-D video are disclosed. A user may modify and/or refine any automatically generated information. Further, at least some of the techniques described herein are equally applicable to 2-D images.
-
-
-
-
-
-
-
Search Results
8
records
(took 0.018 seconds)
