公开(公告)号：US09350810B2

公开(公告)日：2016-05-24

申请号：US13979012

申请日：2011-01-18

申请人： Guiheng Zhou ,  Yizhen Zhao ,  Bo Zheng

发明人： Guiheng Zhou ,  Yizhen Zhao ,  Bo Zheng

IPC分类号： G06G7/48 ,  H04L29/08 ,  G01C21/34 ,  G01C21/32 ,  G06F17/50

CPC分类号： H04L67/12 ,  G01C21/32 ,  G01C21/3484 ,  G06F17/509

摘要： Information about different road networks is retrieved from different sources. Applicable rules and parameter values for constructing an integrated road network are determined for each road network. Roads are first extended at their endpoints. Intersection points among the extended roads are detected. Roads are then divided into road segments at the detected intersection points, and shorted by removing road segments extended beyond intersection points. To process a large scale of road information, extended roads are divided into road segments and distributed to reducers based on their geographic locations for the reducers to detect intersection points among the received road segments. The resulting road segments are then distributed to reducers based on the roads they belong to for the reducers to first reassemble the road segments, then divide the reassembled roads at the detected intersection points, and finally remove road segments extended beyond intersection points.

摘要翻译： 从不同来源检索有关不同道路网络的信息。 为每个道路网络确定用于构建综合道路网络的适用规则和参数值。 道路首先在其终点延伸。 检测到延长道路之间的交点。 然后将道路在检测的交叉点分成道路段，并通过移除超出交叉点的道路段进行短路。 为了处理大量的道路信息，扩展道路被划分为道路段，并根据其地理位置分配给减速器，以减少接收路段之间的交点。 然后将所得到的路段分配到减速机，基于其所属的道路用于减速机，以首先重新组装路段，然后将重新组装的道路划分在检测的交叉点，最后移除超出交叉点的道路段。

公开(公告)号：US20130290400A1

公开(公告)日：2013-10-31

申请号：US13979012

申请日：2011-01-18

申请人： Guiheng Zhou ,  Yizhen Zhao ,  Bo Zheng

发明人： Guiheng Zhou ,  Yizhen Zhao ,  Bo Zheng

IPC分类号： H04L29/08

CPC分类号： H04L67/12 ,  G01C21/32 ,  G01C21/3484 ,  G06F17/509

摘要： Information about different road networks is retrieved from different sources. Applicable rules and parameter values for constructing an integrated road network are determined for each road network. Roads are first extended at their endpoints. Intersection points among the extended roads are detected. Roads are then divided into road segments at the detected intersection points, and shorted by removing road segments extended beyond intersection points. To process a large scale of road information, extended roads are divided into road segments and distributed to reducers based on their geographic locations for the reducers to detect intersection points among the received road segments. The resulting road segments are then distributed to reducers based on the roads they belong to for the reducers to first reassemble the road segments, then divide the reassembled roads at the detected intersection points, and finally remove road segments extended beyond intersection points.

摘要翻译： 从不同来源检索有关不同道路网络的信息。 为每个道路网络确定用于构建综合道路网络的适用规则和参数值。 道路首先在其终点延伸。 检测到延长道路之间的交点。 然后将道路在检测的交叉点分成道路段，并通过移除超出交叉点的道路段进行短路。 为了处理大量的道路信息，扩展道路被划分为道路段，并根据其地理位置分配给减速器，以减少接收路段之间的交点。 然后将所得到的路段分配到减速机，基于其所属的道路用于减速机，以首先重新组装路段，然后将重新组装的道路划分在检测的交叉点，最后移除超出交叉点的道路段。

公开(公告)号：US08805091B1

公开(公告)日：2014-08-12

申请号：US13588681

申请日：2012-08-17

申请人： Chase Hensel ,  Guiheng Zhou

发明人： Chase Hensel ,  Guiheng Zhou

IPC分类号： G06K9/68

CPC分类号： G06K9/68 ,  G06K9/6218 ,  G06T3/4038 ,  G06T11/60

摘要： Systems, methods, and computer storage mediums are provided for matching multiple photographs together. An example method includes receiving a first collection of photographic images. The photographic images in the first collection are clustered into one or more composite sets of photographic images based on a comparison of the metadata associated with each photographic image in the first collection meeting a predetermined similarity threshold. An image overlap is determined between each photographic image within each of the one or composite sets of photographic images. When the image overlap exceeds a predetermined image overlap threshold, a pair of photographic images are matched, for all of the photographic images within each composite set of photographic images to form one or more composite images.

摘要翻译： 提供系统，方法和计算机存储介质，用于将多张照片在一起进行匹配。 一种示例性方法包括接收摄影图像的第一集合。 基于与第一集合中的每个摄影图像相关联的元数据的比较满足预定相似性阈值，将第一集合中的摄影图像聚类成一组或多组复合摄影图像。 在摄影图像的一个或复合组中的每一个之间的每个摄影图像之间确定图像重叠。 当图像重叠超过预定图像重叠阈值时，对于每个复合照相图像集合内的所有摄影图像，匹配一对照片图像以形成一个或多个合成图像。