公开(公告)号：US11162788B2

公开(公告)日：2021-11-02

申请号：US16718172

申请日：2019-12-17

申请人： DeepMap Inc.

发明人： Chen Chen ,  Gregory Coombe

IPC分类号： G01C21/00 ,  G01C11/12 ,  G06T7/73 ,  G06T7/68 ,  G06K9/00 ,  G06T7/55 ,  G06T17/05 ,  G01C11/30 ,  G06T7/246 ,  G06K9/46 ,  G01C11/06 ,  G01C21/36 ,  G06T7/11 ,  G01C21/32 ,  G05D1/00 ,  G05D1/02 ,  G06T7/70 ,  G06T7/593 ,  G06K9/62 ,  B60W40/06 ,  G01S19/42 ,  G08G1/00 ,  G06T17/20 ,  G01S19/47 ,  G01S19/46 ,  G01S17/89

摘要： A high-definition map system receives sensor data from vehicles traveling along routes and combines the data to generate a high definition map for use in driving vehicles, for example, for guiding autonomous vehicles. A pose graph is built from the collected data, each pose representing location and orientation of a vehicle. The pose graph is optimized to minimize constraints between poses. Points associated with surface are assigned a confidence measure determined using a measure of hardness/softness of the surface. A machine-learning-based result filter detects bad alignment results and prevents them from being entered in the subsequent global pose optimization. The alignment framework is parallelizable for execution using a parallel/distributed architecture. Alignment hot spots are detected for further verification and improvement. The system supports incremental updates, thereby allowing refinements of subgraphs for incrementally improving the high-definition map for keeping it up to date.

公开(公告)号：US10962366B2

公开(公告)日：2021-03-30

申请号：US16787469

申请日：2020-02-11

申请人： DeepMap Inc.

发明人： Ronghua Zhang ,  Chen Chen ,  Di Zeng ,  Mark Damon Wheeler

IPC分类号： G06K9/00 ,  G01C11/12 ,  G06T7/73 ,  G06T7/68 ,  G06T7/55 ,  G06T17/05 ,  G01C11/30 ,  G06T7/246 ,  G06K9/46 ,  G01C11/06 ,  G01C21/36 ,  G06T7/11 ,  G01C21/32 ,  G05D1/00 ,  G05D1/02 ,  G06T7/70 ,  G06T7/593 ,  G06K9/62 ,  B60W40/06 ,  G01S19/42 ,  G08G1/00 ,  G06T17/20 ,  G01C21/00 ,  G01S19/47 ,  G01S19/46 ,  G01S17/89

摘要： As an autonomous vehicle moves through a local area, pairwise alignment may be performed to calculate changes in the pose of the vehicle between different points in time. The vehicle comprises an imaging system configured to capture image frames depicting a portion of the surrounding area. Features are identified from the captured image frames, and a 3-D location is determined for each identified feature. The features of different image frames corresponding to different points in time are analyzed to determine a transformation in the pose of the vehicle during the time period between the image frames. The determined poses of the vehicle are used to generate an HD map of the local area.

公开(公告)号：US10598489B2

公开(公告)日：2020-03-24

申请号：US16427037

申请日：2019-05-30

申请人： DeepMap Inc.

发明人： Ronghua Zhang ,  Chen Chen ,  Di Zeng ,  Mark Damon Wheeler

IPC分类号： G06K9/00 ,  G01C11/12 ,  G06T7/73 ,  G06T7/68 ,  G06T7/55 ,  G06T17/05 ,  G01C11/30 ,  G06T7/246 ,  G06K9/46 ,  G01C11/06 ,  G01C21/36 ,  G06T7/11 ,  G01C21/32 ,  G05D1/00 ,  G05D1/02 ,  G06T7/70 ,  G06T7/593 ,  G06K9/62 ,  B60W40/06 ,  G01S19/42 ,  G08G1/00 ,  G06T17/20 ,  G01C21/00 ,  G01S19/47 ,  G01S19/46 ,  G01S17/89

摘要： As an autonomous vehicle moves through a local area, pairwise alignment may be performed to calculate changes in the pose of the vehicle between different points in time. The vehicle comprises an imaging system configured to capture image frames depicting a portion of the surrounding area. Features are identified from the captured image frames, and a 3-D location is determined for each identified feature. The features of different image frames corresponding to different points in time are analyzed to determine a transformation in the pose of the vehicle during the time period between the image frames. The determined poses of the vehicle are used to generate an HD map of the local area.

公开(公告)号：US10422639B2

公开(公告)日：2019-09-24

申请号：US15855547

申请日：2017-12-27

申请人： DeepMap Inc.

发明人： Lin Yang

IPC分类号： G06T7/11 ,  G01C11/12 ,  G06T7/73 ,  G06T7/68 ,  G06K9/00 ,  G06T7/55 ,  G06T17/05 ,  G01C11/30 ,  G06T7/246 ,  G01C21/36 ,  G05D1/00 ,  G05D1/02 ,  G06T7/70 ,  G06T7/593 ,  G06K9/62 ,  B60W40/06 ,  G01S19/42 ,  G08G1/00 ,  G06T17/20 ,  G01C21/00 ,  G06K9/46 ,  G01C11/06 ,  G01S17/89

摘要： A vehicle computing system performs enhances relatively sparse data collected by a LiDAR sensor by increasing the density of points in certain portions of the scan. For instance, the system generates 3D triangles based on a point cloud collected by the LiDAR sensor and filters the 3D triangles to identify a subset of 3D triangles that are proximate to the ground. The system interpolates points within the subset of 3D triangles to identify additional points on the ground. As another example, the system uses data collected by the LiDAR sensor to identify vertical structures and interpolate additional points on those vertical structures. The enhanced data can be used for a variety of applications related to autonomous vehicle navigation and HD map generation, such as detecting lane markings on the road in front of the vehicle or determining a change in the vehicle's position and orientation.

公开(公告)号：US20180188026A1

公开(公告)日：2018-07-05

申请号：US15855116

申请日：2017-12-27

申请人： DeepMap Inc.

发明人： Ronghua Zhang ,  Chen Chen ,  Di Zeng ,  Mark Damon Wheeler

IPC分类号： G01C11/12 ,  G06T7/73 ,  G06T7/68 ,  G06K9/00 ,  G06T7/55 ,  G06T7/246 ,  G06T17/05 ,  G01C11/30

CPC分类号： G06T17/20 ,  B60W40/06 ,  B60W2550/14 ,  G01C11/12 ,  G01C11/30 ,  G01C21/005 ,  G01C21/32 ,  G01C21/3635 ,  G01C21/3694 ,  G01S17/89 ,  G01S19/42 ,  G05D1/0088 ,  G05D1/0246 ,  G05D2201/0213 ,  G06K9/00791 ,  G06K9/00798 ,  G06K9/00805 ,  G06K9/4671 ,  G06K9/6212 ,  G06T7/11 ,  G06T7/246 ,  G06T7/248 ,  G06T7/55 ,  G06T7/593 ,  G06T7/68 ,  G06T7/70 ,  G06T7/73 ,  G06T7/74 ,  G06T17/05 ,  G06T2200/04 ,  G06T2207/10021 ,  G06T2207/10028 ,  G06T2207/20048 ,  G06T2207/30252 ,  G06T2207/30256 ,  G06T2210/56 ,  G06T2215/12 ,  G08G1/20

摘要： As an autonomous vehicle moves through a local area, pairwise alignment may be performed to calculate changes in the pose of the vehicle between different points in time. The vehicle comprises an imaging system configured to capture image frames depicting a portion of the surrounding area. Features are identified from the captured image frames, and a 3-D location is determined for each identified feature. The features of different image frames corresponding to different points in time are analyzed to determine a transformation in the pose of the vehicle during the time period between the image frames. The determined poses of the vehicle are used to generate an HD map of the local area.

公开(公告)号：US09638801B2

公开(公告)日：2017-05-02

申请号：US14551394

申请日：2014-11-24

申请人： Mitsubishi Electric Research Laboratories, Inc.

发明人： Petros T. Boufounos ,  Achuta Kadambi

IPC分类号： G01C11/12 ,  G01S17/89 ,  G01S17/10 ,  G01S7/486

CPC分类号： G01S17/89 ,  G01S7/4865 ,  G01S17/10

摘要： In a system and method for reconstructing a scene, a light source transmits an optical pulse unto the scene, and a set of sensors receive a reflected pulse to acquire sensed signals corresponding to the optical pulse. There is a fixed coded aperture in an optical path between the light source and set of sensors. Then, a processor performs a method to reconstruct the scene as a three-dimensional (3D) depth map using a scene model.

公开(公告)号：US09115986B2

公开(公告)日：2015-08-25

申请号：US14525953

申请日：2014-10-28

申请人： FARO Technologies, Inc.

发明人： Rolf Heidemann ,  Martin Ossig ,  Reinhard Becker

IPC分类号： G01C11/12 ,  G01B11/25

CPC分类号： G01B11/25 ,  G01B11/2513 ,  G01B11/2518

摘要： A device for optically scanning and measuring an environment is provided. The device includes a movable scanner having at least one first projector for producing at least one uncoded first pattern on an object in the environment. The scanner includes at least one camera for recording images of the object provided with the pattern and a controller coupled to the first projector and the camera. The device further includes at least one second projector which projects a stationary uncoded second pattern on the object while the scanner is moved. Wherein the controller has a processor configured to determine a set of three-dimensional coordinates of points on a surface of the object from a set of images acquired by the camera based at least in part on the first pattern. The controller is further configured to register the set of images relative based in part on the stationary second pattern.

公开(公告)号：US08760632B2

公开(公告)日：2014-06-24

申请号：US13133557

申请日：2009-11-09

申请人： Masayuki Usami

发明人： Masayuki Usami

IPC分类号： G01C3/08 ,  G01C3/10 ,  G01C11/12 ,  G01S11/12

CPC分类号： G01S11/12 ,  G01C3/08 ,  G01C3/10

摘要： Provided is a distance measuring apparatus and a distance measuring method enabling measurement of, based on an image, a relative distance from an object even during nighttime. Included are imaging means for taking an image in a traveling direction of an own-vehicle as a taken image; specifying means for respectively specifying combinations of positions, in the taken image, of direct light which is imaged in the taken image and of a reflected light which is a reflection of the direct light on a travel path surface; and measuring means for measuring a relative distance from an object based on the combinations of the positions of the direct light and the positions of the reflected light, which are specified by the specifying means.

摘要翻译： 提供了一种距离测量装置和距离测量方法，其能够基于图像测量即使在夜间期间与物体的相对距离。 包括用于拍摄作为拍摄图像的本车行驶方向上的图像的成像装置; 指定装置，用于分别指定所拍摄的图像中被拍摄的直射光的位置和作为直接光的反射的反射光在行进路径表面上的位置的组合; 以及测量装置，用于基于由指定装置指定的直射光的位置和反射光的位置的组合来测量与物体的相对距离。

公开(公告)号：US07684613B2

公开(公告)日：2010-03-23

申请号：US11439338

申请日：2006-05-23

申请人： Koji Harada ,  Yoshihisa Abe ,  Takayuki Mukai

发明人： Koji Harada ,  Yoshihisa Abe ,  Takayuki Mukai

IPC分类号： G06K9/00 ,  G01C11/12 ,  G01C3/00

CPC分类号： G06T7/33

摘要： In a method for aligning three-dimensional shape data obtained by performing a three-dimensional measurement of an object, photogrammetry of the object with a target mark is performed to obtain a three-dimensional position and a normal vector of the target mark by a calculation, and the three-dimensional measurement of the object is performed to obtain a three-dimensional position and a normal vector of the target mark. Then, determined is a correspondence between the three-dimensional position of the target mark obtained by the photogrammetry and the three-dimensional position of the target mark obtained by the three-dimensional measurement, by using the three-dimensional position and the normal vector of the target mark obtained by the photogrammetry and those of the target mark obtained by the three-dimensional measurement, and three-dimensional shape data obtained by the three-dimensional measurement is aligned based on the correspondence between the three-dimensional-positions of the target marks.

摘要翻译： 在通过对物体进行三维测量而获得的三维形状数据进行对准的方法中，进行具有目标标记的物体的摄影测量，以通过计算得到目标标记的三维位置和法线矢量 ，并且执行对象的三维测量以获得目标标记的三维位置和法线向量。 然后，通过使用三维位置和法线矢量，确定通过摄影测量法获得的目标标记的三维位置与通过三维测量获得的目标标记的三维位置之间的对应关系 通过摄影测量获得的目标标记和通过三维测量获得的目标标记的目标标记和通过三维测量获得的三维形状数据基于目标的三维位置之间的对应关系 分数。

公开(公告)号：US20080204697A1

公开(公告)日：2008-08-28

申请号：US12005471

申请日：2007-12-27

申请人： Peter Domenicali ,  Clifford Hoyt ,  Scott Determan ,  Peter Miller

发明人： Peter Domenicali ,  Clifford Hoyt ,  Scott Determan ,  Peter Miller

IPC分类号： G01C11/12

CPC分类号： G01C11/12

摘要： The invention provides for surface mapping of in-vivo imaging subjects using a single camera and a moveable stage on which a subject animal for in-vivo imaging is placed. Images are taken and the stage is moved by known amounts along the optical axis, and the heights of individual features on the subject are determined through analysis of focus, given the known stage displacement. Alternatively, height of sub-regions of the subject are determined through analysis of focus. A mesh or other surface can be constructed from individual features, to provide a surface map of the subject. Accuracy of 0.5 mm or better can be attained for mice and similarly sized subjects.

摘要翻译： 本发明提供了使用单个照相机和放置用于体内成像的受试动物的可移动阶段的体内成像对象的表面映射。 拍摄图像并且沿着光轴移动已知量的阶段，并且考虑已知的阶段位移，通过对焦点的分析来确定对象上的个体特征的高度。 或者，通过对焦点的分析确定受试者的子区域的高度。 网格或其他表面可以从各个特征构造，以提供主体的表面图。 对于小鼠和类似大小的受试者，可以获得0.5mm或更好的精度。