公开(公告)号：EP3404613A2

公开(公告)日：2018-11-21

申请号：EP18171871.9

申请日：2018-05-11

申请人： Siemens Healthcare GmbH

发明人： DUTTA, Komal ,  BAKER, Scott

IPC分类号： G06T7/11 ,  G06T7/187 ,  G06T7/194

CPC分类号： G06T7/0012 ,  G06T7/11 ,  G06T7/13 ,  G06T7/187 ,  G06T7/194 ,  G06T11/60 ,  G06T2207/10028 ,  G06T2207/10116 ,  G06T2207/20221 ,  G06T2207/30016 ,  G06T2207/30101 ,  G06T2210/12 ,  G06T2211/404

摘要： A framework for isolating an aneurysm and parent vessel in volumetric image data is provided herein. In accordance with one aspect, the framework generates a refined mask by performing region growing starting at an aneurysm dome point to eliminate vessels that are indirectly connected to an aneurysm or parent vessel in volumetric image data. A final mask may be generated based at least in part on the refined mask by eliminating any kissing vessel connected with the aneurysm from the refined mask. The final mask may then be used for segmentation of the aneurysm and the parent vessel in the volumetric image data.

公开(公告)号：EP3374836A1

公开(公告)日：2018-09-19

申请号：EP15903939.5

申请日：2015-10-30

申请人： SZ DJI Technology Co., Ltd.

发明人： WANG, Mingyu ,  ZHAO, Tao ,  YU, Yun ,  ZHOU, Guyue ,  TANG, Ketan ,  ZHAO, Cong ,  LIU, Ang ,  ZHOU, You ,  PANG, Minjian ,  HU, Xiao ,  ZHANG, Litian

IPC分类号： G05D1/10 ,  G05D3/00

CPC分类号： H04N5/2328 ,  B64C39/024 ,  B64C2201/127 ,  B64C2201/141 ,  B64C2201/145 ,  G01S3/7864 ,  G05D1/0094 ,  G05D1/101 ,  G05D1/12 ,  G06T7/20 ,  G06T7/248 ,  G06T7/70 ,  G06T2207/10032 ,  G06T2210/12 ,  H04N5/232

摘要： A method for determining position of a target includes determining at least two measurement points of the target, obtaining vector data of at least two direction vectors based on an imaging position of the target on an imaging system and parameter data of the imaging system, and determining a distance between the target and the imaging system according to the vector data and a current vertical height of the imaging system. Each of the at least two direction vectors is a vector from the imaging system to a corresponding one of the at least two measurement points.

公开(公告)号：EP3352697A1

公开(公告)日：2018-08-01

申请号：EP16848205.7

申请日：2016-07-29

申请人： Novadaq Technologies ULC

发明人： WALLE-JENSEN, Jorgen ,  BROWNE, Gregory, Vincent

IPC分类号： A61B34/10 ,  A61B5/00 ,  A61B8/00 ,  G06F19/00

CPC分类号： G06T5/009 ,  G06T5/50 ,  G06T7/0012 ,  G06T11/206 ,  G06T2200/24 ,  G06T2207/10064 ,  G06T2207/20208 ,  G06T2210/12

摘要： Systems and methods for storing data for a first time series of fluorescence images of the subject acquired during a first imaging session, storing data for a second time series of fluorescence images of the subject acquired during a second imaging session, receiving a request to view attributes of the subject, and in response to receiving the request, displaying a user interface on the display, the user interface comprising a first image showing a visually enhanced attribute of the subject, wherein the first image is generated from the data for the first time series of fluorescence images, and a second image showing the visually enhanced attribute of the subject, wherein the second image is generated from the data for the second time series of fluorescence images.

公开(公告)号：EP3319047A1

公开(公告)日：2018-05-09

申请号：EP17198959.3

申请日：2017-10-27

申请人： Samsung Electronics Co., Ltd.

发明人： SHIN, Young-sam ,  LEE, Won-jong

IPC分类号： G06T15/06

CPC分类号： G06T15/06 ,  G06T1/20 ,  G06T15/005 ,  G06T17/005 ,  G06T2210/12

摘要： A method for generating an acceleration structure used for ray tracing includes generating (S710) a linear code, the linear code representing a position of each of a plurality of primitives (811-821) included in a three-dimensional (3D) space, arranging (S720) the plurality of primitives (811-821) according to the generated linear code, determining (S730) a rate of change of a size of a generated bounding box (1010, 1020, 1030, 1040, 1050) while sequentially inputting the plurality of arranged primitives (811-821) into the generated bounding box (1010, 1020, 1030, 1040, 1050), selecting (S740) one of the plurality of arranged primitives (811-821) based on the rate of change of the size of the generated bounding box (1010, 1020, 1030, 1040, 1050) and classifying (S750) the plurality of arranged primitives (811-821) into a plurality of determined bounding boxes (1210, 1220) according to the selected primitive.

摘要翻译： 用于生成用于射线追踪的加速结构的方法包括生成（S710）线性码，线性码表示包括在三维（3D）空间中的多个图元（811-821）中的每一个的位置，布置 （S720）根据所生成的线性码确定（S730）所述多个图元（811-821），在生成的边界框（1010,1020,1030,1040,1050）的尺寸的变化率 将多个排列的基元（811-821）插入到所生成的边界框（1010,1020,1030,1040,1050）中;基于所述多个排列的基元（811-821）的变化率，选择（S740）所述多个排列的基元 （1010,1020,1030,1040,1050）的大小以及根据所选择的基元将多个排列的基元（811-821）分类为多个确定的边界框（1210,1220）的步骤（S750）。

公开(公告)号：EP2902972B1

公开(公告)日：2017-10-25

申请号：EP15153342.9

申请日：2015-01-30

申请人： DreamWorks Animation LLC

发明人： Gornowicz, Galen G. ,  Borac, Silviu

IPC分类号： G06T13/60 ,  G06F17/12 ,  G06T15/00

CPC分类号： G06T13/80 ,  G06F17/12 ,  G06K9/52 ,  G06T7/20 ,  G06T13/40 ,  G06T17/005 ,  G06T2210/12 ,  G06T2210/21

摘要： One exemplary process for animating hair includes receiving data representing a plurality of hairs and a plurality of objects in a timestep of a frame of animation. A first tree is populated to represent kinematic objects of the plurality of objects and a second tree is populated to represent dynamic objects of the plurality of objects based on the received data. A first elasticity preconditioner is created to represent internal elastic energy of the plurality of hairs based on the received data. Based on the first tree and the second tree, a first set of potential contacts is determined between two or more hairs of the plurality of hairs or between one or more hairs of the plurality of hairs and one or more objects of the plurality of objects. Positions of the plurality of hairs are determined based on the first set of potential contacts and the first elasticity preconditioner.

公开(公告)号：EP3164848A2

公开(公告)日：2017-05-10

申请号：EP15739118.6

申请日：2015-06-29

申请人： Qualcomm Incorporated

发明人： SARKIS, Michel Adib ,  SUNDARESAN, Sairam ,  LIN, Kuen-Han

IPC分类号： G06T1/00 ,  G06T17/00

CPC分类号： G06T7/20 ,  G06T1/0007 ,  G06T17/00 ,  G06T19/00 ,  G06T2200/08 ,  G06T2200/24 ,  G06T2207/20104 ,  G06T2210/12

摘要： A method includes generating, at an electronic device, a three-dimensional model of an object based on a sequence of images captured by an image capture device associated with the electronic device. The method further includes displaying the three-dimensional model via a display device associated with the electronic device. The method also includes, based on detecting that the three-dimensional model includes an anomaly, presenting, via the display device, one or more selectable options to enable correction of the anomaly.

摘要翻译： 一种方法包括基于由与电子设备相关联的图像捕获设备捕获的图像序列在电子设备处生成对象的三维模型。 该方法还包括经由与电子设备相关联的显示设备来显示三维模型。 该方法还包括，基于检测到三维模型包括异常，经由显示设备呈现一个或多个可选择的选项以使得能够校正异常。

公开(公告)号：EP3000229A4

公开(公告)日：2017-05-03

申请号：EP14801676

申请日：2014-05-21

申请人： TRANSOCEAN SEDCO FOREX VENTURES LTD

发明人： KOZICZ JOHN ,  MARTIN TRENTON

IPC分类号： H04N7/18

CPC分类号： G06K9/00771 ,  E21B19/00 ,  E21B41/0021 ,  F16P3/142 ,  G06K9/00369 ,  G06K9/3241 ,  G06T19/00 ,  G06T2210/12 ,  G06T2210/21

摘要： A system and method for automatically preventing a collision between objects is described. One or more images of a working space may be collected, and a first object may be identified based on the one or more images. Three-dimensional coordinates of the first object may be determined, and a virtual boundary enclosing the identified first object in a three-dimensional coordinate system may be generated based on the three-dimensional coordinates of the first object, wherein the virtual boundary specifies a volume in the working space that a second object in the working space should not occupy. The coordinates in the three-dimensional coordinate system corresponding to the generated virtual boundary may be transmitted to a second processor, and the second processor may control the second object to perform an operation in the working space that includes the first object without contacting the virtual boundary of the first object.

摘要翻译： 描述用于自动防止对象之间的碰撞的系统和方法。 可以收集工作空间的一个或多个图像，并且可以基于一个或多个图像来识别第一对象。 可以确定第一对象的三维坐标，并且可以基于第一对象的三维坐标生成在三维坐标系中包围所识别的第一对象的虚拟边界，其中，虚拟边界指定体积 在工作空间中，工作空间中的第二个对象不应占用。 对应于生成的虚拟边界的三维坐标系中的坐标可以被发送到第二处理器，并且第二处理器可以控制第二对象以在不接触虚拟边界的情况下在包括第一对象的工作空间中执行操作 的第一个对象。

公开(公告)号：EP3109829A1

公开(公告)日：2016-12-28

申请号：EP16171160.1

申请日：2016-05-24

申请人： NXP USA, Inc.

发明人： KRUTSCH, Robert Cristian ,  BIBEL, Oliver ,  SCHLAGENHAFT, Rolf

IPC分类号： G06T15/00

CPC分类号： G06T1/20 ,  G06T11/20 ,  G06T15/005 ,  G06T15/80 ,  G06T2210/12

摘要： The present application relates to an apparatus for verifying the integrity of transformed vertex data and a method of operating thereof. The apparatus comprises a graphics processing pipeline with a vertex shader unit, a buffer and a comparator unit. The vertex shader unit receives a stream of vertex data according to a vertex specification. The vertex shader unit applies a transformation on each of the vertices in the received stream of vertex data to and outputs a stream of transformed vertex data. The buffer is coupled to the vertex shader unit to buffer the transformed vertex data. The comparator is further configured to verify the integrity of at least a subset of the transformed vertex data on the basis of reference data and to issue a fault indication signal in case the verification fails.

摘要翻译： 本申请涉及到装置用于验证经变换的顶点的数据的完整性和它们的操作的方法。 该装置包括与顶点着色器单元，缓冲器和一个比较器单元中的图形处理管线。 顶点着色器单元接收的顶点数据gemäß流至顶点规范。 顶点着色器单元适用于每个顶点的数据的接收到的流中的顶点的变换，并输出变换的顶点的数据的流。 该缓冲器耦合到所述顶点着色器单元来缓冲经变换的顶点数据。 该比较器被进一步配置为验证至少基准数据的基础上变换的顶点数据的子集的完整性和发出的情况下，验证失败的故障指示信号。

公开(公告)号：EP3097694A1

公开(公告)日：2016-11-30

申请号：EP15705129.3

申请日：2015-01-22

申请人： Cisco Technology, Inc.

发明人： MALUF, David A. ,  SUKHAAKAR, Raghuram S. ,  STANLEY III, James D. ,  ADDEPALLI, Sateesh K.

IPC分类号： H04N21/231 ,  G06F17/30 ,  H04N21/234 ,  H04N21/235 ,  H04N21/433 ,  H04N21/435 ,  H04N21/44 ,  H04N21/4728

CPC分类号： G06F17/30247 ,  G06F17/30 ,  G06F17/30321 ,  G06F17/30858 ,  G06T7/30 ,  G06T2210/12 ,  H04N21/23109 ,  H04N21/23418 ,  H04N21/235 ,  H04N21/4728

摘要： In one embodiment, a stream of data packets originated by a visual data source is received at an edge device in a network. The data packets include at least one of video data, image data, and geo spatial data. Next, a visual data attribute is extracted at the edge device from the stream of data packets according to an edge-based extraction algorithm. The extracted visual data attribute is vectorized at the edge device via quantization vectors. The vectorized visual data attribute is then indexed at the edge device in a schema-less database that stores indexed visual data attributes.

摘要翻译： 在一个实施例中，由视觉数据源发起的数据分组流在网络中的边缘设备处被接收。 数据分组包括视频数据，图像数据和地理空间数据中的至少一个。 接下来，根据基于边缘的提取算法，在边缘设备处从数据分组流中提取可视数据属性。 提取的视觉数据属性通过量化向量在边缘设备上向量化。 然后，向量化的可视数据属性在存储索引的可视数据属性的无模式数据库中的边缘设备处进行索引。

公开(公告)号：EP3091427A1

公开(公告)日：2016-11-09

申请号：EP15305696.5

申请日：2015-05-06

申请人： Thomson Licensing

发明人： Verdier, Alain ,  Cazettes, Christophe ,  Gandon, Cyrille

IPC分类号： G06F3/0484 ,  G06T11/60 ,  G06F3/0488

CPC分类号： G06F3/04845 ,  G06F3/04883 ,  G06T11/60 ,  G06T2210/12

摘要： A method for selecting a partial area of an image on a screen (140), in particular a touchscreen. A processor (110) of an apparatus (100) receives (612, 622) and stores the coordinates of a first touch applied to the touchscreen (140) as well as multiple coordinates along a trace made by the user, and is notified of the release of the touchscreen (140). The processor analyzes (633) the stored coordinates to obtain the position and the dimensions of the selection area and displays (634) a geometrical shape corresponding to the selection area on the screen. Different analysis methods are described. The shapes are preferably simple geometric shapes such as a rectangle. Also provided is the apparatus (100). The invention can allow simple and fast selection of a partial area in an image.

摘要翻译： 一种用于在屏幕（140），特别是触摸屏上选择图像的局部区域的方法。 装置（100）的处理器（110）接收（612,622）并且存储应用于触摸屏（140）的第一触摸的坐标以及沿着由用户制作的轨迹的多个坐标，并被通知 释放触摸屏（140）。 处理器分析（633）存储的坐标以获得选择区域的位置和尺寸，并显示（634）与屏幕上的选择区域对应的几何形状。 描述不同的分析方法。 形状优选为简单的几何形状，例如矩形。 还提供了装置（100）。 本发明可以允许对图像中的局部区域进行简单而快速的选择。