-
1.发明申请公开(公告)号：US20180357503A1
公开(公告)日：2018-12-13
申请号：US15621884
申请日：2017-06-13
Applicant: TUSIMPLE
Inventor： YI WANG , BOLUN ZHANG , YI LUO , KE XU
CPC classification number: G06K9/46 , G01C21/165 , G06K9/00208 , G06K2009/4695 , G06T2207/20012 , H04N19/80
Abstract: A system for generating a ground truth dataset for motion planning is disclosed. The system includes sensors for data acquisition for motion planning of a vehicle, the sensors including a LiDAR; a calculating module configured to calculate LiDAR poses in response to data from the sensors and generate undistorted LiDAR scans; an extracting module configured to extract static points from a target undistorted LiDAR scan and generate a LiDAR static-scene point cloud; and a generating module configured to generate sparse image point correspondences for each pair of images, using the LiDAR static-scene point cloud.
-
公开(公告)号：US20190066330A1
公开(公告)日：2019-02-28
申请号：US15684414
申请日：2017-08-23
Applicant: TUSIMPLE
Abstract: A method of localization for a non-transitory computer readable storage medium storing one or more programs is disclosed. The one or more programs comprise instructions, which when executed by a computing device, cause the computing device to perform utilizing one or more autonomous vehicle driving modules that execute processing of images from a camera and data from a LiDAR the following steps comprising: aligning a 3D submap with a global map; extracting features from the 3D submap and the global map; classifying the extracted features in classes; and establishing correspondence of features in a same class between the 3D submap and the global map.
-
3.发明申请公开(公告)号：US20190066329A1
公开(公告)日：2019-02-28
申请号：US15684339
申请日：2017-08-23
Applicant: TUSIMPLE
Abstract: A method of localization for a non-transitory computer readable storage medium storing one or more programs is disclosed. The one or more programs comprise instructions, which when executed by a computing device, cause the computing device to perform by one or more autonomous vehicle driving modules execution of processing of images from a camera and data from a LiDAR using the following steps comprising: constructing a 3D submap and a global map; extracting features from the 3D submap and the global map; matching features extracted from the 3D submap against features extracted from the global map; refining feature correspondence; and refining location of the 3D submap.
-
公开(公告)号：US20190065863A1
公开(公告)日：2019-02-28
申请号：US15684389
申请日：2017-08-23
Applicant: TUSIMPLE
Abstract: A method of localization for a non-transitory computer readable storage medium storing one or more programs is disclosed. The one or more programs comprise instructions, which when executed by a computing device, cause the computing device to perform by one or more autonomous vehicle driving modules execution of processing of images from a camera and data from a LiDAR using the following steps comprising: computing, in response to features from a 3D submap and features from a global map, matching score between corresponding features of a same class between the 3D submap and the global map; selecting, for each feature in the 3D submap, a corresponding feature with the highest matching score from the global map; determining a feature correspondence to be invalid if a distance between corresponding features is larger than a threshold; and removing the invalid feature correspondence.
-
5.发明申请公开(公告)号：US20180357315A1
公开(公告)日：2018-12-13
申请号：US15621931
申请日：2017-06-13
Applicant: TUSIMPLE
Inventor： YI LUO , YI WANG , PANQU WANG , KE XU
CPC classification number: G06F17/30811 , B60W2420/52 , G01S17/89 , G05D1/024 , G06T3/4007 , G06T7/20
Abstract: A system for generating a ground truth dataset for motion planning of a vehicle is disclosed. The system includes an internet server that further includes an I/O port, configured to transmit and receive electrical signals to and from a client device; a memory; one or more processing units; and one or more programs stored in the memory and configured for execution by the one or more processing units, the one or more programs including instructions for: an identifying module configured to identify, for a pair of undistorted LiDAR scans, points belonging to a static object in an environment; an aligning module configured to align close points based on pose estimates; and a transforming module configured to transform a reference scan that is close in time to a target undistorted LiDAR scan so as to align the reference scan with the target undistorted LiDAR scan.
-
Patent Agency Ranking
6.发明申请公开(公告)号：US20180357314A1
公开(公告)日：2018-12-13
申请号：US15621904
申请日：2017-06-13
Applicant: TUSIMPLE
CPC classification number: G06F17/30811 , B60W2420/52 , G01S17/89 , G05D1/024 , G06T3/4007 , G06T7/20
Abstract: A system for generating a ground truth dataset for motion planning is disclosed. The system includes: a collecting module configured to collect LiDAR scans; a detecting module configured to detect two pose estimates that are closest to LiDAR scan accusation time; a determining module configured to determine LiDAR's poses based on an interpolation; and a transforming module configured to transform LiDAR raw scans into undistorted LiDAR scans.
-
公开(公告)号：US20180356831A1
公开(公告)日：2018-12-13
申请号：US15621937
申请日：2017-06-13
Applicant: TUSIMPLE
Inventor： YI LUO , YI WANG , PANQU WANG , KE XU
CPC classification number: G05D1/0251 , G01S17/023 , G01S17/89 , G06K9/6202 , G06K9/6249 , G06K9/6288 , G06T7/74 , G06T2207/10028 , G06T2207/30244
Abstract: A method of generating a ground truth dataset for motion planning of a vehicle is disclosed. The method includes: corresponding, for each pair of images, a first image of the pair to a LiDAR static-scene point cloud; and computing a camera pose associated with the pair of images in the coordinate of the point cloud.
-
8.发明申请公开(公告)号：US20190082156A1
公开(公告)日：2019-03-14
申请号：US15701398
申请日：2017-09-11
Applicant: TUSIMPLE
Inventor： BOLUN ZHANG , YI WANG , KE XU
Abstract: A method of aligning optical axes of cameras for a non-transitory computer readable storage medium storing one or more programs is disclosed. The one or more programs comprise instructions, which when executed by a computing device, cause the computing device to perform by one or more autonomous vehicle driving modules execution of processing of images using the following steps comprising: calibrating intrinsic parameters of a set of cameras; extracting corner points associated with a pattern; and computing a vanishing point based on information on the extracted corner points.
-
9.发明申请公开(公告)号：US20190080478A1
公开(公告)日：2019-03-14
申请号：US15701409
申请日：2017-09-11
Applicant: TUSIMPLE
Inventor： BOLUN ZHANG , YI WANG , KE XU
Abstract: A method of aligning optical axes of cameras for a non-transitory computer readable storage medium storing one or more programs is disclosed. The one or more programs comprise instructions, which when executed by a computing device, cause the computing device to perform by one or more autonomous vehicle driving modules execution of processing of images using the following steps comprising: disposing a planar pattern that is viewable to a set of cameras; recovering boundary corner points of the planar pattern from a pair of images; constructing a pair of parallel lines based on 2D positions of the recovered boundary corner points; and determining an intersection point of the pair of parallel lines to be a vanishing point in a pixel coordinate.
-
10.发明申请公开(公告)号：US20190066344A1
公开(公告)日：2019-02-28
申请号：US15684363
申请日：2017-08-23
Applicant: TUSIMPLE
Abstract: A method of localization for a non-transitory computer readable storage medium storing one or more programs is disclosed. The one or more programs comprise instructions, which when executed by a computing device, cause the computing device to perform by one or more autonomous vehicle driving modules execution of processing of images from a camera and data from a LiDAR using the following steps comprising: voxelizing a 3D submap and a global map into voxels; estimating distribution of 3D points within the voxels, using a probabilistic model; extracting features from the 3D submap and the global map; and classifying the extracted features into classes.
-
-
-
-
-
-
-
-
-
Search Results
12
records
(took 0.013 seconds)
