专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US07821453B2 Distributed iterative multimodal sensor fusion method for improved collaborative localization and navigation 有权
标题翻译：分布式迭代多模态传感器融合方法，用于改进协同定位和导航
公开(公告)号：US07821453B2
公开(公告)日：2010-10-26
申请号：US12335574
申请日：2008-12-16
申请人： Shunguang Wu , Suin-Chuon Mau , James Kaba , Tao Zhao
发明人： Shunguang Wu , Suin-Chuon Mau , James Kaba , Tao Zhao
IPC分类号： G01S19/45 , H01Q3/00
CPC分类号： G01S5/0289 , G01S5/0278 , G01S5/0294 , G01S2013/466
摘要： A computer implemented method for fusing position and range measurements to determine the position of at least one node of a plurality of distributed nodes is disclosed. The method includes (a) measuring the position of at least one node; (b) computing an estimate of the position of the at least one node based on the measured position using a filter that takes account of past estimates of position; (c) receiving an estimate of position of at least a second node; (d) measuring inter-node range to the at least a second node; (e) combining the measured inter-node range with the estimate of position of at least a second node using a second filter that takes account of past estimates of position to generate a refined estimate of the position of the at least one node; and (f) when a change in the position of the at least one node is above a predetermined threshold value, setting the refined estimate of the position of the at least one node to the estimate of the position of the at least one node and repeating (c), (e), and (f).
摘要翻译：公开了一种用于对位置和距离测量进行融合以确定多个分布式节点中的至少一个节点的位置的计算机实现的方法。该方法包括（a）测量至少一个节点的位置; （b）使用考虑过去的位置估计的滤波器，基于所测量的位置来计算所述至少一个节点的位置的估计; （c）接收至少第二节点的位置的估计; （d）测量所述至少第二节点的节点间距离; （e）使用考虑过去的位置估计的第二滤波器将所测量的节点间范围与至少第二节点的位置估计相结合，以生成至少一个节点的位置的精确估计; 以及（f）当所述至少一个节点的位置的改变高于预定阈值时，将所述至少一个节点的位置的精细估计设置为所述至少一个节点的位置的估计并重复（c），（e）和（f）。

2. 发明授权

US08180107B2 Active coordinated tracking for multi-camera systems 有权
标题翻译：主动协调跟踪多摄像机系统
公开(公告)号：US08180107B2
公开(公告)日：2012-05-15
申请号：US12704189
申请日：2010-02-11
申请人： Christopher P. Broaddus , Thomas Germano , Nicholas Vandervalk , Shunguang Wu , Ajay Divakaran , Harpreet Singh Sawhney
发明人： Christopher P. Broaddus , Thomas Germano , Nicholas Vandervalk , Shunguang Wu , Ajay Divakaran , Harpreet Singh Sawhney
IPC分类号： G06K9/00 , H04N7/18
CPC分类号： G01S13/867 , G01S3/7864 , G01S13/726 , G06T7/194 , G06T7/292 , G06T2207/20076 , G06T2207/30232 , G08B13/19608 , G08B13/19645 , G08B13/19697
摘要： A method and system for coordinated tracking of objects is disclosed. A plurality of images is received from a plurality of nodes, each node comprising at least one image capturing device. At least one target in the plurality of images is identified to produce at least one local track corresponding to each of the plurality of nodes having the at least one target in its field of view. The at least one local track corresponding to each of the plurality of nodes is fused according to a multi-hypothesis tracking method to produce at least one fused track corresponding to the at least one target. At least one of the plurality of nodes is assigned to track the at least one target based on minimizing at least one cost function comprising a cost matrix using the k-best algorithm for tracking at least one target for each of the plurality of nodes. The at least one fused track is sent to the at least one of the plurality of nodes assigned to track the at least one target based on the at least one fused track.
摘要翻译：公开了一种协调跟踪物体的方法和系统。从多个节点接收多个图像，每个节点包括至少一个图像捕获装置。多个图像中的至少一个目标被识别以产生与其视场中具有至少一个目标的多个节点中的每一个对应的至少一个本地轨迹。根据多假设跟踪方法将与多个节点中的每一个相对应的至少一个本地轨道融合以产生至少一个对应于该至少一个目标的融合轨道。所述多个节点中的至少一个被分配以跟踪所述至少一个目标，所述至少一个目标基于最小化至少一个成本函数，所述至少一个成本函数包括使用所述k最佳算法的成本矩阵，用于跟踪所述多个节点中的每个节点的至少一个目标。至少一个融合轨道被发送到被分配以基于至少一个融合轨道跟踪至少一个目标的多个节点中的至少一个。

3. 发明申请

US20090212995A1 DISTRIBUTED ITERATIVE MULTIMODAL SENSOR FUSION METHOD FOR IMPROVED COLLABORATIVE LOCALIZATION AND NAVIGATION 有权
标题翻译：分布式迭代多模传感器融合方法，用于改进协作本地化和导航
公开(公告)号：US20090212995A1
公开(公告)日：2009-08-27
申请号：US12335574
申请日：2008-12-16
申请人： Shunguang Wu , Suin-Chuon Mau , James Kaba , Tao Zhao
发明人： Shunguang Wu , Suin-Chuon Mau , James Kaba , Tao Zhao
IPC分类号： G01S13/50
CPC分类号： G01S5/0289 , G01S5/0278 , G01S5/0294 , G01S2013/466
摘要： A computer implemented method for fusing position and range measurements to determine the position of at least one node of a plurality of distributed nodes is disclosed. The method includes (a) measuring the position of at least one node; (b) computing an estimate of the position of the at least one node based on the measured position using a filter that takes account of past estimates of position; (c) receiving an estimate of position of at least a second node; (d) measuring inter-node range to the at least a second node; (e) combining the measured inter-node range with the estimate of position of at least a second node using a second filter that takes account of past estimates of position to generate a refined estimate of the position of the at least one node; and (f) when a change in the position of the at least one node is above a predetermined threshold value, setting the refined estimate of the position of the at least one node to the estimate of the position of the at least one node and repeating (c), (e), and (f).
摘要翻译：公开了一种用于对位置和距离测量进行融合以确定多个分布式节点中的至少一个节点的位置的计算机实现的方法。该方法包括（a）测量至少一个节点的位置; （b）使用考虑过去的位置估计的滤波器，基于所测量的位置来计算所述至少一个节点的位置的估计; （c）接收至少第二节点的位置的估计; （d）测量所述至少第二节点的节点间距离; （e）使用考虑过去的位置估计的第二滤波器将所测量的节点间范围与至少第二节点的位置估计相结合，以生成至少一个节点的位置的精确估计; 以及（f）当所述至少一个节点的位置的改变高于预定阈值时，将所述至少一个节点的位置的精细估计设置为所述至少一个节点的位置的估计并重复（c），（e）和（f）。

4. 发明申请

US20100208941A1 ACTIVE COORDINATED TRACKING FOR MULTI-CAMERA SYSTEMS 有权
标题翻译：主动协调跟踪多摄像机系统
公开(公告)号：US20100208941A1
公开(公告)日：2010-08-19
申请号：US12704189
申请日：2010-02-11
申请人： Christopher P. Broaddus , Thomas Germano , Nicholas Vandervalk , Shunguang Wu , Ajay Divakaran , Harpreet Singh Sawhney
发明人： Christopher P. Broaddus , Thomas Germano , Nicholas Vandervalk , Shunguang Wu , Ajay Divakaran , Harpreet Singh Sawhney
IPC分类号： G06T7/00
CPC分类号： G01S13/867 , G01S3/7864 , G01S13/726 , G06T7/194 , G06T7/292 , G06T2207/20076 , G06T2207/30232 , G08B13/19608 , G08B13/19645 , G08B13/19697
摘要： A method and system for coordinated tracking of objects is disclosed. A plurality of images is received from a plurality of nodes, each node comprising at least one image capturing device. At least one target in the plurality of images is identified to produce at least one local track corresponding to each of the plurality of nodes having the at least one target in its field of view. The at least one local track corresponding to each of the plurality of nodes is fused according to a multi-hypothesis tracking method to produce at least one fused track corresponding to the at least one target. At least one of the plurality of nodes is assigned to track the at least one target based on minimizing at least one cost function comprising a cost matrix using the k-best algorithm for tracking at least one target for each of the plurality of nodes. The at least one fused track is sent to the at least one of the plurality of nodes assigned to track the at least one target based on the at least one fused track.
摘要翻译：公开了一种协调跟踪物体的方法和系统。从多个节点接收多个图像，每个节点包括至少一个图像捕获装置。多个图像中的至少一个目标被识别以产生与其视场中具有至少一个目标的多个节点中的每一个对应的至少一个本地轨迹。根据多假设跟踪方法将与多个节点中的每一个相对应的至少一个本地轨道融合以产生至少一个对应于该至少一个目标的融合轨道。所述多个节点中的至少一个被分配以跟踪所述至少一个目标，所述至少一个目标基于最小化至少一个成本函数，所述至少一个成本函数包括使用所述k-最佳算法的成本矩阵，用于跟踪所述多个节点中的每个节点的至少一个目至少一个融合轨道被发送到被分配以基于至少一个融合轨道跟踪至少一个目标的多个节点中的至少一个。

5. 发明申请

US20090292468A1 COLLISION AVOIDANCE METHOD AND SYSTEM USING STEREO VISION AND RADAR SENSOR FUSION 审中-公开
标题翻译：使用立体视觉和雷达传感器融合的碰撞避免方法和系统
公开(公告)号：US20090292468A1
公开(公告)日：2009-11-26
申请号：US12410602
申请日：2009-03-25
申请人： Shunguang Wu , Theodore Camus , Chang Peng
发明人： Shunguang Wu , Theodore Camus , Chang Peng
IPC分类号： G08G1/16 , G01S13/08 , G01S13/00
CPC分类号： G01S13/867 , B60W30/08 , G01S13/726 , G01S13/862 , G01S13/865 , G01S13/931 , G01S2013/9375 , G08G1/165
摘要： A system and method for fusing depth and radar data to estimate at least a position of a threat object relative to a host object is disclosed. At least one contour is fitted to a plurality of contour points corresponding to the plurality of depth values corresponding to a threat object. A depth closest point is identified on the at least one contour relative to the host object. A radar target is selected based on information associated with the depth closest point on the at least one contour. The at least one contour is fused with radar data associated with the selected radar target based on the depth closest point to produce a fused contour. Advantageously, the position of the threat object relative to the host object is estimated based on the fused contour. More generally, a method is provided for aligns two possibly disparate sets of 3D points.
摘要翻译：公开了一种用于对深度和雷达数据进行融合以至少估计威胁对象相对于主机对象的位置的系统和方法。至少一个轮廓装配到对应于对应于威胁对象的多个深度值的多个轮廓点。在相对于主体对象的至少一个轮廓上标识深度最接近的点。基于与至少一个轮廓上的深度最接近点相关联的信息来选择雷达目标。基于深度最接近的点将至少一个轮廓与与所选雷达目标相关联的雷达数据进行融合，以产生融合轮廓。有利地，基于融合轮廓来估计威胁对象相对于主机对象的位置。更一般地，提供了一种用于对准两个可能不同的3D点集合的方法。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式