公开(公告)号：US20100091020A1

公开(公告)日：2010-04-15

申请号：US12311471

申请日：2006-10-20

Applicant: Marcin Michal Kmiecik ,  Wojciech Tomasz Nowak

Inventor： Marcin Michal Kmiecik ,  Wojciech Tomasz Nowak

IPC: G06K9/64 ,  G09G5/00 ,  G06T15/20

CPC classification number: G01C21/28 ,  G01C11/02

Abstract: A computer arrangement is disclosed, including a processor and a memory that stores a computer program, object data originating from a first source and including object location data, and laser samples originating from a second source, including a sub-set of laser samples relating to the object and including laser sample location data as to each laser sample. In at least one embodiment, the processor compares the object location data and the laser sample location data of the sub-set of laser samples, and matches the object location data to the laser sample location data of the sub-set of laser samples based on this comparison, and thereby corrects for relative positional errors between the first and second sources of location data. The object may be a building façade, for example.

Abstract translation: 公开了一种计算机装置，包括存储计算机程序的处理器和存储器，源自第一源并包括对象位置数据的对象数据，以及源自第二源的激光采样，包括与 该对象并且包括关于每个激光样本的激光样本位置数据。 在至少一个实施例中，处理器比较对象位置数据和激光样本子集的激光样本位置数据，并将对象位置数据与激光样本子集的激光采样位置数据进行匹配，基于 从而校正第一和第二位置数据源之间的相对位置误差。 例如，物体可以是建筑立面。

公开(公告)号：US20140046990A1

公开(公告)日：2014-02-13

申请号：US13977880

申请日：2010-12-31

Applicant: Marcin Michal Kmiecik ,  Nelson Miguel Da Cruz Gonçalves ,  Ying-Lin Lai

Inventor： Marcin Michal Kmiecik ,  Nelson Miguel Da Cruz Gonçalves ,  Ying-Lin Lai

IPC: H03M7/30

CPC classification number: H03M7/30 ,  A61B5/1112 ,  A61B5/681 ,  A61B5/7232 ,  A61B2503/10 ,  A61B2560/0475 ,  A61B2562/0219 ,  A61B2562/227 ,  G01C22/006

Abstract: A method of compressing data output from an acceleration measurement means configured to be transported, carried or worn by a user is provided. Acceleration values indicative of the movement of the user are measured at a first frequency and values representative of the measured acceleration values are generated at a second frequency, which is lower than the first frequency. The step of generating comprises: defining a plurality of time windows, each time window containing a plurality of measured acceleration values; and applying a transformation to the measured acceleration values within each time window to generate a plurality of transformed values. For each time window, storing at least one of said plurality of transformed values and/or one or more parameters associated therewith.

Abstract translation: 提供一种压缩从被配置为由用户运送，携带或佩戴的加速度测量装置输出的数据的方法。 以第一频率测量表示用户的移动的加速度值，并且以低于第一频率的第二频率生成代表所测量的加速度值的值。 生成步骤包括：定义多个时间窗口，每个时间窗口包含多个测量的加速度值; 以及对每个时间窗内的所测量的加速度值进行变换以产生多个变换值。 对于每个时间窗口，存储所述多个变换值中的至少一个和/或与其相关联的一个或多个参数。

公开(公告)号：US08422736B2

公开(公告)日：2013-04-16

申请号：US12734118

申请日：2007-11-16

Applicant: Marcin Michal Kmiecik ,  Lukasz Piotr Taborowski

Inventor： Marcin Michal Kmiecik ,  Lukasz Piotr Taborowski

IPC: G06K9/00

CPC classification number: G06T5/30 ,  G01C21/20 ,  G01C21/26 ,  G06K9/00798 ,  G06T5/002 ,  G06T2207/30256

Abstract: A method of producing lane information for use in a map database is disclosed. In at least one embodiment, the method includes acquiring one or more source images of a road surface and associated position and orientation data, the road having a direction and lane markings parallel to the direction of the road; acquiring road information representative of the direction of said road; transforming the one or more source images to obtain a transformed image in dependence of the road information, wherein each column of pixels of the transformed image corresponds to a surface parallel to the direction of said road; applying a filter with asymmetrical mask on the transformed image to obtain a filtered image; and producing lane information from the filtered image in dependence of the position and orientation data associated with the one or more source images.

Abstract translation: 公开了一种生成用于地图数据库中的车道信息的方法。 在至少一个实施例中，该方法包括获取路面的一个或多个源图像和相关联的位置和方向数据，道路具有平行于道路方向的方向和车道标记; 获取代表所述道路方向的道路信息; 变换所述一个或多个源图像以根据所述道路信息获得变换图像，其中所述变换图像的每列像素对应于与所述道路的方向平行的表面; 在变换图像上应用具有不对称掩模的滤波器以获得滤波图像; 以及根据与一个或多个源图像相关联的位置和取向数据，从经滤波的图像生成车道信息。

公开(公告)号：US08396255B2

公开(公告)日：2013-03-12

申请号：US12311461

申请日：2006-10-20

Applicant: Marcin Michal Kmiecik ,  Rafal Jan Gliszczynski

Inventor： Marcin Michal Kmiecik ,  Rafal Jan Gliszczynski

IPC: G06K9/00

CPC classification number: G01C11/025 ,  G06T7/11 ,  G06T7/194 ,  G06T7/42 ,  G06T2207/10028 ,  G06T2207/20056

Abstract: A computer arrangement is disclosed, including a processor that can communicate with a memory. The memory stores a computer program that can be run by the processor, and stores a set of laser scan samples including a sub-set of laser scan samples relating to a façade of a building and stores location data as to each laser scan sample. The memory also stores a picture of the same façade including location data as to pixels of the picture. The picture includes data as to a wall of the façade and data as to texture elements in the wall. In at least one embodiment, the processor automatically identifies the wall and the texture elements in the picture while using the laser scan samples.

Abstract translation: 公开了一种计算机装置，包括可与存储器进行通信的处理器。 存储器存储可由处理器运行的计算机程序，并且存储一组激光扫描样本，其包括与建筑物的外观相关的激光扫描样本的子集，并存储关于每个激光扫描样本的位置数据。 存储器还存储相同外观的图片，包括关于图片的像素的位置数据。 图片包括关于外墙的数据和关于墙壁中的纹理元素的数据。 在至少一个实施例中，处理器在使用激光扫描样本时自动识别图片中的壁和纹理元素。

公开(公告)号：US08351704B2

公开(公告)日：2013-01-08

申请号：US12733844

申请日：2007-10-02

Applicant: Marcin Michal Kmiecik ,  Wojciech Tomasz Nowak

Inventor： Marcin Michal Kmiecik ,  Wojciech Tomasz Nowak

IPC: G06K9/46

CPC classification number: G06T3/0043 ,  G01C21/32 ,  G06T2207/30256

Abstract: A method of producing linear features along a reference-line across a surface for use in a map database is disclosed. In at least one embodiment, the method includes generating, from reference-line data representative of coordinates of the reference-line in a geographic coordinate reference system and source images of the surface adjacent to the reference-line and associated position and orientation data in the geographic coordinate reference system, a reference-line referenced data set, wherein the reference-line referenced data set includes a plurality of sets of image data and associated data defining a reference-line' across a surface in the geographic coordinate reference system, the sets of image data including pixels wherein a set of image data corresponds to an orthorectified view representation of a line section of the surface in the geographic coordinate reference system, each set of image data includes a reference pixel being associated with a position on the reference-line, wherein each pixel represents a surface having a position at a distance from the position of the reference pixel along the line section, and wherein the line section perpendicularly crosses the reference-line at the position associated with the reference pixel; and, post processing the reference-line referenced data set to produce linear features along the reference-line and associated locations in the geographic coordinate reference system for use in a map database.

Abstract translation: 公开了沿着用于地图数据库中的表面的参考线产生线性特征的方法。 在至少一个实施例中，该方法包括从参考线数据生成表示地理坐标参考系中的参考线的坐标以及与参考线相邻的表面的源图像以及相关位置和取向数据 地理坐标参考系，参考线参考数据集，其中参考线参考数据集包括多组图像数据和相关联的数据，其定义横跨地理坐标参考系中的表面的参考线，所述集合 包括像素的图像数据，其中一组图像数据对应于地理坐标参考系统中的表面的线段的正视校正视图表示，每组图像数据包括与参考线上的位置相关联的参考像素 ，其中每个像素表示具有距离参考像素alon的位置一定距离的位置的表面 g所述线路部分，并且其中所述线路部分在与所述参考像素相关联的位置垂直地穿过所述参考线; 并且后处理参考线参考数据集以沿着地理坐标参考系中的参考线和相关联的位置产生线性特征，以在地图数据库中使用。

公开(公告)号：US08325979B2

公开(公告)日：2012-12-04

申请号：US12311465

申请日：2007-10-30

Applicant: Lukasz Piotr Taborowski ,  Rafal Jan Gliszczynski ,  Arkadiusz Wysocki ,  Marcin Michal Kmiecik

Inventor： Lukasz Piotr Taborowski ,  Rafal Jan Gliszczynski ,  Arkadiusz Wysocki ,  Marcin Michal Kmiecik

IPC: G06K9/00

CPC classification number: G01C21/32 ,  G01C11/025 ,  G06T7/55 ,  G06T7/70 ,  G06T2207/10016 ,  G06T2207/10028 ,  G06T2207/30184 ,  G06T2207/30236 ,  G06T2207/30252

Abstract: A method of detecting objects from terrestrial based mobile mapping data is disclosed, wherein the terrestrial based mobile mapping data has been captured by way of a terrestrial based mobile mapping vehicle driving on a road having a driving direction, the mobile mapping data including laser scanner data, source images obtained by at least one camera and position and orientation data of the vehicle, wherein the laser scanner data includes laser points, each laser point having associated position and orientation data, and each source image comprises associated position and orientation data. In at least one embodiment, the method includes: retrieving a position and orientation of the vehicle; filtering the laser scanner data in dependence of the position and orientation of the vehicle to obtain laser points corresponding to regions of interest; retrieving a source image associated with the position and orientation of the vehicle; mapping the laser points corresponding to regions of interest to image coordinates of the source image to generate a recognition mask; combining the recognition mask and the source image to obtain candidate 3D images representative of possible objects within the regions of interest; and, detecting a group of objects from the candidate 3D images. By combining image recognition and laser scanner recognition the detection rate can be increased to a very high percentage, thereby substantially reducing human effort. Furthermore, the generating of regions of interest in the laser data, enables a significant reduction of the processing power and/or the processing time needed to detect the objects in the images.

Abstract translation: 公开了一种从基于地面的移动地图数据中检测对象的方法，其中基于地面的移动地图绘制数据已经通过在具有驱动方向的道路上行驶的基于陆地的移动地图绘图车辆进行捕获，移动地图数据包括激光扫描器数据 通过至少一个相机获得的源图像以及车辆的位置和方向数据，其中激光扫描器数据包括激光点，每个激光点具有相关联的位置和取向数据，并且每个源图像包括相关联的位置和取向数据。 在至少一个实施例中，该方法包括：检索车辆的位置和方位; 根据车辆的位置和方向对激光扫描器数据进行滤波，以获得对应于感兴趣区域的激光点; 检索与所述车辆的位置和方向相关联的源图像; 将对应于感兴趣区域的激光点映射到源图像的图像坐标以产生识别掩模; 组合识别掩模和源图像以获得表示感兴趣区域内的可能对象的候选3D图像; 以及从候选3D图像中检测一组对象。 通过组合图像识别和激光扫描仪识别，检测率可以提高到非常高的百分比，从而大大减少人的努力。 此外，在激光数据中产生感兴趣区域能够显着降低检测图像中的物体所需的处理能力和/或处理时间。

公开(公告)号：US08280107B2

公开(公告)日：2012-10-02

申请号：US12311470

申请日：2007-11-05

Applicant: Marcin Michal Kmiecik ,  Arkadiusz Wysocki

Inventor： Marcin Michal Kmiecik ,  Arkadiusz Wysocki

IPC: G06K9/00

CPC classification number: G06K9/00818 ,  G01C11/06 ,  G06T7/593 ,  G06T2207/30252

Abstract: A method of identifying a planar object in source images is disclosed. In at least one embodiment, the method includes: retrieving a first source image obtained by a first terrestrial based camera; retrieving a second source image obtained by a second terrestrial based camera; retrieving position data associated with the first and second source image; retrieving orientation data associated with the first and second source image; performing a looking axis rotation transformation on the first and second source image by use of the associated position data and orientation data to obtain first and second intermediate images, wherein the first and second intermediate images have an identical looking axis; performing a radial logarithmic space transformation on the first and second intermediate images to obtain first and second radial logarithmic data images; detecting an area in the first image potentially being a planar object; comparing the potential planar object having similar dimensions in the second radial logarithmic data image and similar rgb characteristics; and finally, identifying the area as a planar object and determining its position. At least one embodiment of the method enables the engineer to detect very efficiently planar perpendicular objects in subsequent images.

Abstract translation: 公开了一种识别源图像中的平面物体的方法。 在至少一个实施例中，该方法包括：检索由第一地面摄像机获得的第一源图像; 检索由第二地面摄像机获得的第二源图像; 检索与第一和第二源图像相关联的位置数据; 检索与第一和第二源图像相关联的定向数据; 通过使用相关联的位置数据和取向数据对第一和第二源图像执行观察轴旋转变换以获得第一和第二中间图像，其中第一和第二中间图像具有相同的观察轴; 对所述第一和第二中间图像执行径向对数空间变换以获得第一和第二径向对数数据图像; 检测可能是平面物体的第一图像中的区域; 将第二径向对数数据图像中类似尺寸的潜在平面物体与类似的rgb特征进行比较; 并且最后，将该区域识别为平面物体并确定其位置。 该方法的至少一个实施例使得工程师能够在随后的图像中检测非常有效的平面垂直对象。

公开(公告)号：US20100091017A1

公开(公告)日：2010-04-15

申请号：US12311467

申请日：2007-10-09

Applicant: Marcin Michal Kmiecik ,  Wojciech Tomasz Nowak

Inventor： Marcin Michal Kmiecik ,  Wojciech Tomasz Nowak

IPC: G06T17/00 ,  G06F19/00 ,  H04N7/18

CPC classification number: G06T3/00 ,  G01C11/02 ,  G01C21/32 ,  G06T3/4038 ,  G06T5/006 ,  G09B29/102 ,  G11C11/02

Abstract: A method is disclosed for generating an orthorectified tile. In at least one embodiment, the method includes retrieving source images obtained by way of a terrestrial based camera; retrieving position data associated with the source images; retrieving orientation data associated with the source images; and converting source image by means of corresponding position data and orientation data to obtain the orthorectified tile. Orthorectified tiles are used to generate an orthorectified mosaic. As such, images recorded by terrestrial based camera may be used to generate a map of a road surface with corresponding road signs.

Abstract translation: 公开了一种用于产生正射校正砖的方法。 在至少一个实施例中，该方法包括检索通过地面摄像机获得的源图像; 检索与源图像相关联的位置数据; 检索与源图像相关联的定向数据; 并通过对应的位置数据和取向数据转换源图像以获得正射校正图块。 正交修补的瓦片用于生成正射校正马赛克。 因此，可以使用由地面摄像机记录的图像来生成具有相应道路标志的路面的地图。

公开(公告)号：US20100039318A1

公开(公告)日：2010-02-18

申请号：US12312301

申请日：2006-11-06

Applicant: Marcin Michal Kmiecik ,  Krzysztof Miksa

Inventor： Marcin Michal Kmiecik ,  Krzysztof Miksa

IPC: G01S5/14

CPC classification number: G01C21/28 ,  G01C21/165 ,  G01S19/23 ,  G01S19/47

Abstract: In one embodiment of the present invention, a method of and apparatus for determining inaccurate GPS samples in a set of GPS samples is disclosed, according to the following actions: a) obtaining GPS samples as taken by a global positioning system on board a vehicle when traveling along a trajectory; b) obtaining a first estimation of the trajectory based on the GPS samples; c) obtaining a second estimation of the trajectory at least based on measurements made by an inertial measurement unit on board vehicle when traveling along the trajectory; d) comparing the first and second estimations; e) establishing locations where the first estimation shows a variation compared with the second estimation above a predetermined threshold; f) if no such locations can be established continue with action j), otherwise continue with action g); g) removing GPS samples associated with the locations of high variation as being inaccurate GPS samples, thus forming a set of remaining GPS samples; h) calculating the first estimation anew of the trajectory based on the remaining GPS samples and calculating the second estimation anew; i) repeating actions d) to h); j) ending the actions.

Abstract translation: 在本发明的一个实施例中，公开了一种用于在一组GPS样本集中确定不准确的GPS样本的方法和装置，所述方法和装置根据以下动作：a）获得由车辆上的全球定位系统采取的GPS样本， 沿着轨迹行进; b）基于GPS样本获得轨迹的第一估计; c）至少基于沿着所述轨迹行驶时由所述车辆上的惯性测量单元进行的测量获得所述轨迹的第二估计; d）比较第一和第二估计; e）建立位置，其中所述第一估计显示与所述第二估计高于预定阈值的变化; f）如果不能建立这样的位置，继续采取行动j），否则继续采取行动g）; g）将与高变化位置相关联的GPS样本移除为不准确的GPS样本，从而形成一组剩余的GPS样本; h）基于剩余的GPS样本计算新的轨迹的第一估计，并重新计算第二估计; i）重复动作d）至h）; j）结束行动。

公开(公告)号：US20090228204A1

公开(公告)日：2009-09-10

申请号：US12365119

申请日：2009-02-03

Applicant: Walter B. Zavoli ,  Marcin Michal Kmiecik ,  Stephen T'Siobbel ,  Volker Hiestermann

Inventor： Walter B. Zavoli ,  Marcin Michal Kmiecik ,  Stephen T'Siobbel ,  Volker Hiestermann

IPC: G01C21/26

CPC classification number: G01C21/30 ,  G01S13/86 ,  G01S19/48 ,  G01S19/49

Abstract: A system and method for map matching with sensor detected objects. A direct sensor and object matching technique can be used to disambiguate objects that the driver passes. The technique also makes it possible for the navigation system to refine (i.e. improve the accuracy of) its position estimate. In some embodiments, a camera in the car can be used to produce, dynamically in real time, images of the vicinity of the vehicle. Map and object information can then be retrieved from a map database, and superimposed on those images for viewing by the driver, including accurately defining the orientation or the platform so that the alignment of the map data and the image data is accurate. Once alignment is achieved, the image can be further enhanced with information retrieved from the database about any in-image objects. Objects may be displayed accurately on a map display as icons that help the driver as he/she navigates the roads.

Abstract translation: 用于与传感器检测到的物体进行地图匹配的系统和方法。 可以使用直接传感器和对象匹配技术来消除驱动程序通过的对象。 该技术还使得导航系统可以改进（即，提高其位置估计的准确性）。 在一些实施例中，汽车中的照相机可以用于动态地实时地产生车辆附近的图像。 然后可以从地图数据库检索地图和对象信息，并叠加在这些图像上以供驾驶员查看，包括准确地定义方向或平台，使得地图数据和图像数据的对准准确。 一旦达到对准，就可以使用从数据库检索的关于任何图像内对象的信息进一步增强图像。 对象可以在地图显示上准确地显示为图标，以帮助驾驶员在他/她导航道路时。