-
公开(公告)号：US11062454B1
公开(公告)日：2021-07-13
申请号：US16386249
申请日：2019-04-16
申请人： Zoox, Inc.
摘要： A machine-learning architecture may be trained to determine point cloud data associated with different types of sensors with an object detected in an image and/or generate a three-dimensional region of interest (ROI) associated with the object. In some examples, the point cloud data may be associated with sensors such as, for example, a lidar device, radar device, etc.
-
公开(公告)号：US20190340775A1
公开(公告)日：2019-11-07
申请号：US15970838
申请日：2018-05-03
申请人： Zoox, Inc.
摘要： A monocular image often does not contain enough information to determine, with certainty, the depth of an object in a scene reflected in the image. Combining image data and LIDAR data may enable determining a depth estimate of the object relative to the camera. Specifically, LIDAR points corresponding to a region of interest (“ROI”) in the image that corresponds to the object may be combined with the image data. These LIDAR points may be scored according to a monocular image model and/or a factor based on a distance between projections of the LIDAR points into the ROI and a center of the region of interest may improve the accuracy of the depth estimate. Using these scores as weights in a weighted median of the LIDAR points may improve the accuracy of the depth estimate, for example, by discerning between a detected object and an occluding object and/or background.
-
公开(公告)号：US11816852B2
公开(公告)日：2023-11-14
申请号：US16940216
申请日：2020-07-27
申请人： Zoox, Inc.
CPC分类号： G06T7/521 , G01S17/931 , G05D1/024 , G05D1/0212 , G06N20/00 , G06T7/11 , G06T7/77 , G06T2207/20081 , G06T2207/30261
摘要： A monocular image often does not contain enough information to determine, with certainty, the depth of an object in a scene reflected in the image. Combining image data and LIDAR data may enable determining a depth estimate of the object relative to the camera. Specifically, LIDAR points corresponding to a region of interest (“ROI”) in the image that corresponds to the object may be combined with the image data. These LIDAR points may be scored according to a monocular image model and/or a factor based on a distance between projections of the LIDAR points into the ROI and a center of the region of interest may improve the accuracy of the depth estimate. Using these scores as weights in a weighted median of the LIDAR points may improve the accuracy of the depth estimate, for example, by discerning between a detected object and an occluding object and/or background.
-
公开(公告)号：US20210104056A1
公开(公告)日：2021-04-08
申请号：US16940216
申请日：2020-07-27
申请人： Zoox, Inc.
摘要： A monocular image often does not contain enough information to determine, with certainty, the depth of an object in a scene reflected in the image. Combining image data and LIDAR data may enable determining a depth estimate of the object relative to the camera. Specifically, LIDAR points corresponding to a region of interest (“ROI”) in the image that corresponds to the object may be combined with the image data. These LIDAR points may be scored according to a monocular image model and/or a factor based on a distance between projections of the LIDAR points into the ROI and a center of the region of interest may improve the accuracy of the depth estimate. Using these scores as weights in a weighted median of the LIDAR points may improve the accuracy of the depth estimate, for example, by discerning between a detected object and an occluding object and/or background.
-
公开(公告)号：US11879978B1
公开(公告)日：2024-01-23
申请号：US16549694
申请日：2019-08-23
申请人： Zoox, Inc.
发明人： Subhasis Das , Chuang Wang , Sabeek Mani Pradhan
CPC分类号： G01S17/89 , G01C21/3492 , G01S19/393 , G05D1/0221 , G05D1/0223 , G06N20/00
摘要： Techniques for updating data operations in a perception system are discussed herein. A vehicle may use a perception system to capture data about an environment proximate to the vehicle. The perception system may receive image data, lidar data, and/or radar data to determine information about an object in the environment. As different sensors may be associated with different time periods for capturing and/or processing operations, the techniques include updating object data with data from sensors associated with a shorter time period to generate intermediate object data.
-
公开(公告)号：US11628855B1
公开(公告)日：2023-04-18
申请号：US16866839
申请日：2020-05-05
申请人： Zoox, Inc.
IPC分类号： B60W60/00 , G05D1/00 , G01S17/931 , G01S13/931 , G05D1/02
摘要： Ground truth data may be too sparse to supervise training of a machine-learned (ML) model enough to achieve an ML model with sufficient accuracy/recall. For example, in some cases, ground truth data may only be available for every third, tenth, or hundredth frame of raw data. Training an ML model to detect a velocity of an object when ground truth data for training is sparse may comprise training the ML model to predict a future position of the object based at least in part on image, radar, and/or lidar data (e.g., for which no ground truth may be available). The ML model may be altered based at least in part on a difference between ground truth data associated with a future time and the future position.
-
公开(公告)号：US10726567B2
公开(公告)日：2020-07-28
申请号：US15970838
申请日：2018-05-03
申请人： Zoox, Inc.
摘要： A monocular image often does not contain enough information to determine, with certainty, the depth of an object in a scene reflected in the image. Combining image data and LIDAR data may enable determining a depth estimate of the object relative to the camera. Specifically, LIDAR points corresponding to a region of interest (“ROI”) in the image that corresponds to the object may be combined with the image data. These LIDAR points may be scored according to a monocular image model and/or a factor based on a distance between projections of the LIDAR points into the ROI and a center of the region of interest may improve the accuracy of the depth estimate. Using these scores as weights in a weighted median of the LIDAR points may improve the accuracy of the depth estimate, for example, by discerning between a detected object and an occluding object and/or background.
-
公开(公告)号：US20240241257A1
公开(公告)日：2024-07-18
申请号：US18417356
申请日：2024-01-19
申请人： Zoox, Inc.
发明人： Subhasis Das , Chuang Wang , Sabeek Mani Pradhan
CPC分类号： G01S17/89 , G01C21/3492 , G01S19/393 , G06N20/00
摘要： Techniques for updating data operations in a perception system are discussed herein. A vehicle may use a perception system to capture data about an environment proximate to the vehicle. The perception system may receive image data, lidar data, and/or radar data to determine information about an object in the environment. As different sensors may be associated with different time periods for capturing and/or processing operations, the techniques include updating object data with data from sensors associated with a shorter time period to generate intermediate object data. Such intermediate object data may reduce a delay in updating a position of an object in an environment, which may improve reaction time(s) and/or safety outcomes in systems implementing such perception systems, such as an autonomous vehicle.
-
公开(公告)号：US11703566B2
公开(公告)日：2023-07-18
申请号：US17373550
申请日：2021-07-12
申请人： Zoox, Inc.
IPC分类号： G06N20/20 , G01S7/41 , G06T7/11 , G01S17/89 , G06N3/08 , G06V10/25 , G06V10/764 , G06V10/82 , G06V20/64
CPC分类号： G01S7/417 , G01S17/89 , G06N3/08 , G06N20/20 , G06T7/11 , G06V10/25 , G06V10/764 , G06V10/82 , G06V20/64 , G06T2207/10028
摘要： A machine-learning architecture may be trained to determine point cloud data associated with different types of sensors with an object detected in an image and/or generate a three-dimensional region of interest (ROI) associated with the object. In some examples, the point cloud data may be associated with sensors such as, for example, a lidar device, radar device, etc.
-
公开(公告)号：US20210343022A1
公开(公告)日：2021-11-04
申请号：US17373550
申请日：2021-07-12
申请人： Zoox, Inc.
摘要： A machine-learning architecture may be trained to determine point cloud data associated with different types of sensors with an object detected in an image and/or generate a three-dimensional region of interest (ROI) associated with the object. In some examples, the point cloud data may be associated with sensors such as, for example, a lidar device, radar device, etc.
-
-
-
-
-
-
-
-
-
搜索结果
10 条记录 (耗时 0.015 秒)
