公开(公告)号：US20140350850A1

公开(公告)日：2014-11-27

申请号：US14344640

申请日：2012-09-13

Applicant: Marcin Michal Kmiecik ,  Rafal Jan Gliszczynski

Inventor： Marcin Michal Kmiecik ,  Rafal Jan Gliszczynski

IPC: G01C21/34 ,  G01S19/49

CPC classification number: G01C21/3407 ,  G01C21/005 ,  G01C22/006 ,  G01S19/19 ,  G01S19/49

Abstract: A method is disclosed involving receiving GPS data from a personal portable training device. A smoothing operation is performed on the GPS data to generate a more accurate representation of the route travelled for display to a user (504). In the smoothing operation, a cubic spine algorithm is used to obtain an initial estimate of the route representation (500). The estimate is then subjected to a refinement using at least received user motion data recorded by the personal training device (502). In addition one or more of: data indicative of the GPS accuracy; historical route data; and digital map data, such as building footprints and bodies of water, may be used in refining the estimate.

Abstract translation: 公开了一种涉及从个人便携式训练装置接收GPS数据的方法。 对GPS数据进行平滑处理，以生成更准确地表示所行驶的用于向用户显示的路线（504）。 在平滑处理中，使用立方脊算法来获得路线表示的初始估计（500）。 然后使用由个人训练装置（502）记录的至少接收到的用户运动数据对该估计进行细化。 另外还有一个或多个：表示GPS精度的数据; 历史路线数据; 并且数字地图数据，例如建筑物的足迹和水体可用于改进估计。

公开(公告)号：US20110123068A1

公开(公告)日：2011-05-26

申请号：US12736915

申请日：2008-09-25

Applicant: Krzysztof Miksa ,  Marcin Michal Kmiecik

Inventor： Krzysztof Miksa ,  Marcin Michal Kmiecik

IPC: G06K9/46 ,  G06K9/00

CPC classification number: G06T5/002 ,  G06T5/20 ,  G06T2207/30201 ,  G06T2207/30252

Abstract: A method of reducing the spatial resolution of images is disclosed. At least one embodiment of the method includes: —acquiring an input image including image parts having a spatial resolution larger than SR pixels/meter; —acquiring a depth map associated with the input image; —determining for each pixel p(x,y) a spatial resolution value by means of the depth map; —processing a region of pixels of the input image for which holds that the spatial resolution value is larger than a predefined threshold corresponding to SR pixels/meter to obtain a corresponding region of pixels having a spatial resolution smaller then or equal to SR pixels/meter in an output image. The method enables to removes privacy information from images by reducing the spatial resolution to a level that the privacy information cannot be recognized in the image anymore.

Abstract translation: 公开了降低图像的空间分辨率的方法。 该方法的至少一个实施例包括： - 获取包括具有大于SR像素/米的空间分辨率的图像部分的输入图像; - 获取与输入图像相关联的深度图; - 通过深度图确定每个像素p（x，y）的空间分辨率值; 处理其输入图像的像素区域，其中空间分辨率值大于对应于SR像素/米的预定义阈值，以获得具有小于或等于SR像素/米的空间分辨率的像素的对应区域 在输出图像中。 该方法能够通过将空间分辨率降低到无法再在图像中识别隐私信息的水平来从图像中去除隐私信息。

公开(公告)号：US20100166256A1

公开(公告)日：2010-07-01

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：US20100086174A1

公开(公告)日：2010-04-08

申请号：US12450907

申请日：2008-04-18

Applicant: Marcin Michal Kmiecik ,  Lukasz Piotr Taborowski

Inventor： Marcin Michal Kmiecik ,  Lukasz Piotr Taborowski

IPC: G06K9/00

CPC classification number: G06K9/00798 ,  G06T3/00 ,  G06T7/12 ,  G06T7/90 ,  G06T2207/10016 ,  G06T2207/30256

Abstract: An embodiment of the present invention discloses a method of producing road information for use in a map database including: acquiring a source image from an image sequence obtained by means of a terrestrial based camera mounted on a moving vehicle; determining a road color sample from pixels associated with a predefined area in the source image representative of the road surface in front of or behind the moving vehicle; generating a road surface image from the source image in dependence of the road color sample; and, producing road information in dependence of the road surface image and position and orientation data associated with the source image.

Abstract translation: 本发明的一个实施例公开了一种在地图数据库中使用的道路信息的制作方法，其特征在于，包括：从安装在移动车辆上的地面摄像机获得的图像序列中获取源图像; 从与代表运动车辆前方或后方的路面的源图像中的预定区域相关联的像素确定道路颜色样本; 根据道路颜色样本从源图像生成路面图像; 并且根据路面图像和与源图像相关联的位置和取向数据来生成道路信息。

公开(公告)号：US08884962B2

公开(公告)日：2014-11-11

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: G06T15/10 ,  G01C21/28 ,  G01C11/02

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：US08725404B2

公开(公告)日：2014-05-13

申请号：US13256463

申请日：2009-12-31

Applicant: Marcin Michal Kmiecik ,  Wojciech Tomasz Nowak

Inventor： Marcin Michal Kmiecik ,  Wojciech Tomasz Nowak

IPC: G01C21/00

CPC classification number: G09B29/10 ,  G01C21/206 ,  G01C21/32 ,  G09B29/003

Abstract: This invention relates to a method for updating digital maps and for matching global navigation devices to a digital map. Such navigation devices rely upon GPS signals (20, 24) from satellites (22, 26). One well-documented cause of position error in navigation devices arises from the phenomenon of GPS multi-path. It has been observed that GPS multi-path errors in the latitude/longitude direction are highly correlated with errors in altitude. By comparing altitude value of GPS probe data with reference specifications for altitude, unreliable probe data (outliers) can be easily identified and culled. Such techniques can be used as well by a mobile navigation device to confirm a match to a particular road segment and if not revert to other positioning techniques such as inertial guidance systems and the like. If the local altitude is not reliably known, an estimation can be derived directly from the collected probe data.

Abstract translation: 本发明涉及一种更新数字地图并将全球导航设备与数字地图相匹配的方法。 这种导航装置依赖于来自卫星（22,26）的GPS信号（20,24）。 导航装置位置误差的一个有据可查的原因来自GPS多路径的现象。 已经观察到，纬度/经度方向上的GPS多径误差与高度误差高度相关。 通过将GPS探头数据的高度值与高度参考规格进行比较，可以轻松识别和淘汰不可靠的探测数据（异常值）。 这样的技术也可以由移动导航装置用于确认与特定路段的匹配，并且如果不能恢复到诸如惯性引导系统等的其他定位技术。 如果本地高度不可靠，则可以从收集的探测数据直接得出估计值。

公开(公告)号：US08571354B2

公开(公告)日：2013-10-29

申请号：US12736915

申请日：2008-09-25

Applicant: Krzysztof Miksa ,  Marcin Michal Kmiecik

Inventor： Krzysztof Miksa ,  Marcin Michal Kmiecik

IPC: G06K9/32

CPC classification number: G06T5/002 ,  G06T5/20 ,  G06T2207/30201 ,  G06T2207/30252

Abstract: A method of reducing the spatial resolution of images is disclosed. At least one embodiment of the method includes: —acquiring an input image including image parts having a spatial resolution larger than SR pixels/meter; —acquiring a depth map associated with the input image; —determining for each pixel p(x,y) a spatial resolution value by means of the depth map; —processing a region of pixels of the input image for which holds that the spatial resolution value is larger than a predefined threshold corresponding to SR pixels/meter to obtain a corresponding region of pixels having a spatial resolution smaller then or equal to SR pixels/meter in an output image. The method enables to removes privacy information from images by reducing the spatial resolution to a level that the privacy information cannot be recognized in the image anymore.

Abstract translation: 公开了降低图像的空间分辨率的方法。 该方法的至少一个实施例包括： - 获取包括具有大于SR像素/米的空间分辨率的图像部分的输入图像; - 获取与输入图像相关联的深度图; - 通过深度图确定每个像素p（x，y）的空间分辨率值; 处理其输入图像的像素区域，其中空间分辨率值大于对应于SR像素/米的预定阈值，以获得具有小于或等于SR像素/米的空间分辨率的像素的对应区域 在输出图像中。 该方法能够通过将空间分辨率降低到无法再在图像中识别隐私信息的水平来从图像中去除隐私信息。

公开(公告)号：US20100104141A1

公开(公告)日：2010-04-29

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：US20100020074A1

公开(公告)日：2010-01-28

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: G06T15/00

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：US09843810B2

公开(公告)日：2017-12-12

申请号：US12735630

申请日：2008-04-18

Applicant: James E. Hagan ,  Arkadiusz Wysocki ,  Marcin Michal Kmiecik

Inventor： James E. Hagan ,  Arkadiusz Wysocki ,  Marcin Michal Kmiecik

IPC: H04N9/47 ,  H04N19/17 ,  H04N19/124 ,  H04N19/136

CPC classification number: H04N19/17 ,  H04N19/124 ,  H04N19/136

Abstract: A method of processing camera data of a mobile mapping system is disclosed. In at least one embodiment, the method includes a) obtaining camera data from at least one camera of the mobile mapping system, b) detecting at least one region in the camera data, c) applying a compression technique on the camera data in a first region, and d) obtaining range sensor data from at least a first range sensor. The range sensor data may at least partially correspond to the camera data. Also, in at least one embodiment, b) includes using the range sensor data to identify the at least one region in the camera data.