专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

51. 发明申请

WO2015127043A1 OPTICAL FLOW SENSING AND PATTERN RECOGNITION WITH ANTISYMMETRIC PHASE GRATINGS 审中-公开
标题翻译：光电流感测与图像识别与抗相位相差
公开(公告)号：WO2015127043A1
公开(公告)日：2015-08-27
申请号：PCT/US2015/016569
申请日：2015-02-19
申请人： RAMBUS INC.
发明人： GILL, Patrick, R. , STORK, David, G. , JOHNSTONE, Patrick
IPC分类号： G02B27/42 , G02B5/18 , G02B27/46
CPC分类号： G06T5/10 , G02B5/18 , G02B27/42 , G02B27/4205 , G02B27/46 , G06T7/2033 , G06T7/246 , G06T2207/10004
摘要： Computational diffractive imagers employ special optical phase gratings integrated with photodetector matrices. Such imagers do not require a lens, and so can be extremely small and inexpensive. Captured interference patterns are unintelligible to a human observer, but the captured data includes sufficient information to allow the image or aspects of the image to be computed. Computational diffractive imagers can be tailored to extract application-specific information or compute decisions (rather than compute an image) based on the optical signal. Both the phase grating and the signal processing can be optimized for the information in the visual field and the task at hand. For example, sequences of interference patterns can be compared to measure changes in angular position, and this information can be used to sense and measure motion. Such interference patterns can also be used for pattern recognition, such as to perform automated face detection and recognition.
摘要翻译：计算衍射成像仪采用与光电检测器矩阵集成的特殊光相位光栅。这样的成像器不需要透镜，因此可以非常小和便宜。捕获的干扰模式对于人类观察者是不可理解的，但是所捕获的数据包括足够的信息来允许计算图像的图像或方面。计算衍射成像器可以被定制以基于光信号提取应用特定信息或计算决定（而不是计算图像）。相位光栅和信号处理都可以针对视野中的信息和手头的任务进行优化。例如，可以比较干涉图案的序列以测量角位置的变化，并且该信息可以用于感测和测量运动。这种干涉图案也可用于图案识别，例如进行自动面部检测和识别。

52. 发明申请

WO2014132090A4 OPTICAL NAVIGATION & POSITIONING SYSTEM 审中-公开
标题翻译：光学导航定位系统
公开(公告)号：WO2014132090A4
公开(公告)日：2014-11-27
申请号：PCT/GB2014050624
申请日：2014-03-03
申请人： GEISSLER MICHAEL PAUL ALEXANDER
发明人： GEISSLER MICHAEL PAUL ALEXANDER
IPC分类号： G06T7/20 , G01S5/16 , H04N5/222
CPC分类号： G06T7/2033 , G01S5/163 , G06T7/246 , G06T7/579 , G06T2207/10016 , G06T2207/30204 , G06T2207/30241 , G06T2207/30244 , H04N5/2224 , H04N2005/2255
摘要： An optical navigation system (10) comprising a camera (16) oriented to face towards a plurality of markers (26) located at spaced apart locations from the camera (16), calculating means adapted to calculate an angle (&thetas;, &phgr;) subtended between pairs of markers (26), the subtended angles (&thetas;, &phgr;) being calculated by monitoring the pixel locations (26') of the markers (26) in a series of images captured by the camera (16), the optical navigation system (10) additionally comprising means for creating a three-dimensional model whereby the location of the camera (16) relative to the markers (26) is determined by triangulating the subtended angles (&thetas;, &phgr;) in the three-dimensional model.
摘要翻译：一种光学导航系统（10），包括定位成朝向位于与照相机（16）间隔开的位置的多个标记（26）的相机（16），适于计算角度（＆amp; 通过监视由相机（16）捕获的一系列图像中的标记（26）的像素位置（26'）来计算对角度（＆amp; 光学导航系统（10）还包括用于创建三维模型的装置，由此相机（16）相对于标记（26）的位置通过三角测量三角形中的对角角度（＆amp; 三维模型。

53. 发明申请

WO2014074139A9 SYSTEM AND METHOD FOR PROCESSING VISUAL INFORMATION FOR EVENT DETECTION 审中-公开
标题翻译：处理用于事件检测的视觉信息的系统和方法
公开(公告)号：WO2014074139A9
公开(公告)日：2014-06-12
申请号：PCT/US2013030700
申请日：2013-03-13
申请人： ALCATEL LUCENT
发明人： O'GORMAN LAWRENCE , HO TIN K , YIN YAFENG
IPC分类号： H04N5/14 , G06T7/20
CPC分类号： G06T7/2033 , G06K9/00718 , G06K9/00744 , G06K2009/00738 , G06T7/246 , G06T7/269 , G06T2207/10016 , H04N5/144 , H04N5/147
摘要： A system and method processes visual information including at least one object in motion. The visual information is processed by locating at least one spatial edge of the object, generating a plurality of spatio-temporal gradients for the at least one spatial edge over N frames, and then generating motion blur images from the spatio-temporal gradients. A regression analysis is performed on the motion blur images to determine direction of motion information of the object, and scene activity vectors are then generated for the N frames based on the direction of motion information. An event is detected in the visual information based on the scene activity vectors.
摘要翻译：系统和方法处理包括至少一个运动对象的视觉信息。通过定位对象的至少一个空间边缘来处理视觉信息，为N帧上的至少一个空间边缘生成多个时空梯度，然后从空间 - 时间梯度生成运动模糊图像。对运动模糊图像执行回归分析以确定对象的运动信息的方向，然后基于运动信息的方向为N个帧生成场景活动向量。基于场景活动向量在视觉信息中检测到事件。

54. 发明申请

WO2013016113A1 TOOL TRACKING DURING SURGICAL PROCEDURES 审中-公开
标题翻译：手术过程中的工具跟踪
公开(公告)号：WO2013016113A1
公开(公告)日：2013-01-31
申请号：PCT/US2012/047320
申请日：2012-07-19
申请人： REITER, Austin , ALLEN, Peter, K.
发明人： REITER, Austin , ALLEN, Peter, K.
IPC分类号： A61B5/05
CPC分类号： G06T7/2033 , A61B34/20 , A61B2034/2065 , G06T7/246 , G06T2207/20076
摘要： A system and method for tracking a surgical implement in a patient can have an imaging system configured to obtain sequential images of the patient, and an image recognition system coupled to the imaging system and configured to identify the surgical implement in individual images. The image recognition system can be configured to identify the surgical implement relative to the patient in one of the images based, at least in part, on an identification of the surgical implement in at least one preceding one of the sequential images, and a probabilistic analysis of individual sections of the one of the images, the sections being selected by the image recognition system based on a position of the surgical implement in the patient as identified in the at least one preceding one of the images.
摘要翻译：用于跟踪患者中的外科器械的系统和方法可以具有被配置为获得患者的顺序图像的成像系统和耦合到成像系统并被配置为在各个图像中识别外科手术器械的图像识别系统。图像识别系统可以被配置为至少部分地基于至少一个先前的顺序图像中的外科手术器械的识别，以及概率分析来识别在一个图像中相对于患者的手术器械所述图像中的一个图像的各个部分，所述部分由所述图像识别系统基于所述至少一个所述图像中识别的所述患者中的所述外科手术器械的位置来选择。

55. 发明申请

WO2012062813A3 RECOVERY OF 3D SCENE STRUCTURE AND CAMERA MOTION FROM A VIDEO SEQUENCE 审中-公开
标题翻译：从视频序列恢复3D场景结构和相机运动
公开(公告)号：WO2012062813A3
公开(公告)日：2012-07-12
申请号：PCT/EP2011069762
申请日：2011-11-09
申请人： TRINITY COLLEGE DUBLIN , YOUS SOFIANE , REDMOND PETER , LACEY GERARD
发明人： YOUS SOFIANE , REDMOND PETER , LACEY GERARD
IPC分类号： G06T7/00
CPC分类号： G06T7/2033 , G06T7/246 , G06T7/55 , G06T7/73 , G06T2207/10016 , G06T2207/30244
摘要： An improved method and a system are disclosed for recovering a three-dimensional (3D) scene structure from a plurality of two-dimensional (2D) image frames obtained from imaging means. Sets of 2D features are extracted from the image frames, and sets corresponding to successive image frames are matched, such that at least one pair of matched 2D features refers to a same 3D point in a 3D scene captured in 2D in the image frames. A 3D ray is generated by back-projection from each 2D feature, and the generated 3D rays are subjected to an anchor-based minimization process, for determining camera motion parameters and 3D scene points coordinates, thereby recovering a structure of the 3D scene.
摘要翻译：公开了一种改进的方法和系统，用于从从成像装置获得的多个二维（2D）图像帧中恢复三维（3D）场景结构。从图像帧中提取2D特征的集合，并且对应于连续图像帧的集合进行匹配，使得至少一对匹配的2D特征指向在图像帧中2D中捕获的3D场景中的相同3D点。通过从每个2D特征的背投产生3D射线，并且生成的3D射线经受基于锚的最小化处理，用于确定相机运动参数和3D场景点坐标，从而恢复3D场景的结构。

56. 发明申请

WO2012062813A2 METHOD AND SYSTEM FOR RECOVERY OF 3D SCENE STRUCTURE AND CAMERA MOTION FROM A VIDEO SEQUENCE 审中-公开
标题翻译：从视频序列恢复3D场景结构和摄像机运动的方法和系统
公开(公告)号：WO2012062813A2
公开(公告)日：2012-05-18
申请号：PCT/EP2011/069762
申请日：2011-11-09
申请人： THE PROVOST, FELLOWS, AND SCHOLARS OF THE COLLEGE OF THE HOLY AND UNDIVIDED TRINITY OF QUEEN ELIZABETH, NEAR DUBLIN , YOUS, Sofiane , REDMOND, Peter , LACEY, Gerard
发明人： YOUS, Sofiane , REDMOND, Peter , LACEY, Gerard
CPC分类号： G06T7/2033 , G06T7/246 , G06T7/55 , G06T7/73 , G06T2207/10016 , G06T2207/30244
摘要： An improved method and a system are disclosed for recovering a three-dimensional (3D) scene structure from a plurality of two-dimensional (2D) image frames obtained from imaging means. Sets of 2D features are extracted from the image frames, and sets corresponding to successive image frames are matched, such that at least one pair of matched 2D features refers to a same 3D point in a 3D scene captured in 2D in the image frames. A 3D ray is generated by back-projection from each 2D feature, and the generated 3D rays are subjected to an anchor-based minimization process, for determining camera motion parameters and 3D scene points coordinates, thereby recovering a structure of the 3D scene.
摘要翻译：公开了一种改进的方法和系统，用于从从成像装置获得的多个二维（2D）图像帧中恢复三维（3D）场景结构。从图像帧提取2D特征的集合，并且对应于连续图像帧的集合进行匹配，使得至少一对匹配的2D特征参考在图像帧中2D中捕获的3D场景中的相同3D点。通过来自每个2D特征的反投影产生3D射线，并且所生成的3D射线经受基于锚的最小化处理，用于确定相机运动参数和3D场景点坐标，从而恢复3D场景的结构。

57. 发明申请

WO2010141120A2 SYSTEM AND METHOD FOR GENERATING THREE DIMENSIONAL IMAGES USING LIDAR AND VIDEO MEASUREMENTS 审中-公开
标题翻译：使用激光和视频测量产生三维图像的系统和方法
公开(公告)号：WO2010141120A2
公开(公告)日：2010-12-09
申请号：PCT/US2010024934
申请日：2010-02-22
申请人： DIGITAL SIGNAL CORP , SEBASTIAN RICHARD LEE , ZHELEZNYAK ANATOLEY T
发明人： SEBASTIAN RICHARD LEE , ZHELEZNYAK ANATOLEY T
IPC分类号： G01C3/08 , G01P3/36
CPC分类号： G01S17/023 , G01C11/02 , G01S7/4815 , G01S7/491 , G01S17/325 , G01S17/42 , G01S17/58 , G01S17/66 , G01S17/89 , G06K9/00335 , G06K9/00744 , G06K9/52 , G06T7/2033 , G06T7/246 , G06T7/248 , G06T7/60 , G06T7/70 , G06T7/74 , G06T2207/10028 , H04N13/021
摘要： A system uses range and Doppler velocity measurements from a lidar system and images from a video system to estimate a six degree-of-freedom trajectory of a target. The system estimates this trajectory in two stages: a first stage in which the range and Doppler measurements from the lidar system along with various feature measurements obtained from the images from the video system are used to estimate first stage motion aspects of the target (i.e., the trajectory of the target); and a second stage in which the images from the video system and the first stage motion aspects of the target are used to estimate second stage motion aspects of the target. Once the second stage motion aspects of the target are estimated, a three-dimensional image of the target may be generated.
摘要翻译：系统使用来自激光雷达系统的距离和多普勒速度测量以及来自视频系统的图像来估计目标的六自由度轨迹。该系统以两个阶段估计该轨迹：其中来自激光雷达系统的范围和多普勒测量以及从视频系统的图像获得的各种特征测量的第一阶段被用于估计目标的第一阶段运动方面（即，目标轨迹）; 以及第二阶段，其中使用来自视频系统的图像和目标的第一阶段运动方面来估计目标的第二阶段运动方面。一旦估计了目标的第二阶段运动方面，就可能产生目标的三维图像。

58. 发明申请

WO2008089965A2 METHOD AND SYSTEM FOR REFLECTION DETECTION IN ROAD VIDEO IMAGES 审中-公开
标题翻译：道路视频图像反射检测方法与系统
公开(公告)号：WO2008089965A2
公开(公告)日：2008-07-31
申请号：PCT/EP2008/000485
申请日：2008-01-23
申请人： ITERIS INC. , KUEHNLE, Andreas , BOON, Cathy
发明人： KUEHNLE, Andreas , BOON, Cathy
IPC分类号： G06T7/00
CPC分类号： G06T7/2033 , G06K9/00798 , G06T7/246 , G06T7/60
摘要： A method and system for reflection detection in road video images, is provided. One implementation involves detecting road surface reflections, by receiving an image of a road in front of a vehicle from an image capturing device, determining a region of interest in an identified road in the image, and detecting road surface reflections in the region of interest.
摘要翻译：提供了一种用于道路视频图像中的反射检测的方法和系统。一种实施方式涉及通过从图像捕获装置接收车辆前面的道路图像来检测路面反射，确定图像中识别的道路中的感兴趣区域，以及检测感兴趣区域中的路面反射。

59. 发明授权

KR101792866B1 이벤트 센서와 칼라 센서를 이용한 동작 인식 장치 및 그 방법 有权
公开(公告)号：KR101792866B1
公开(公告)日：2017-11-20
申请号：KR1020110031489
申请日：2011-04-06
申请人： 삼성전자주식회사
发明人： 이준행 , 박근주
IPC分类号： G06F3/03
CPC分类号： G06T7/2033 , G06F3/005 , G06F3/017 , G06F3/0304 , G06F3/0425 , G06K9/00335 , G06K9/4619 , G06K9/4652 , G06T7/246 , G06T2207/10016 , G06T2207/10024 , G06T2207/30241
摘要： 동작인식장치및 그방법이제공된다. 일측면에따르면, 이벤트센서를이용하여, 피사체중 움직임이발생한부분을센싱하여이벤트를출력하고, 이벤트를이용하여움직임이발생한부분인움직임영역을확인하고, 컬러센서를이용해서촬영된컬러이미지를이용해서움직임영역의색 정보와형태정보를확인하고, 움직임영역, 색정보및 형태정보를이용해서움직임궤적과동작패턴을판단해서기기의동작을제어할수 있다.

60. 发明授权

KR101655102B1 이벤트 검출을 위해 시각 정보를 프로세싱하기 위한 시스템 및 방법 有权
标题翻译：用于处理用于事件检测的视觉信息的系统和方法
公开(公告)号：KR101655102B1
公开(公告)日：2016-09-07
申请号：KR1020157011698
申请日：2013-03-13
申请人： 알까뗄 루슨트
发明人： 오'고먼,로렌스 , 호,틴케이. , 인,야펭
IPC分类号： H04N5/14
CPC分类号： G06T7/2033 , G06K9/00718 , G06K9/00744 , G06K2009/00738 , G06T7/246 , G06T7/269 , G06T2207/10016 , H04N5/144 , H04N5/147
摘要： 시스템및 방법은움직이고있는적어도하나의오브젝트를포함하는시각정보를프로세싱한다. 시각정보는오브젝트의적어도하나의공간에지의위치를찾고, N개의프레임들에걸쳐적어도하나의공간에지에대한복수의시공간경사들을생성하고, 그후 시공간경사들로부터모션블러이미지들을생성함으로써프로세싱된다. 회귀분석이오브젝트의모션정보의방향을결정하기위해모션블러이미지들에대해수행되고, 장면활동벡터들이그 후모션정보의방향에기초하여 N개의프레임들에대해생성된다. 이벤트는장면활동벡터들에기초하여시각정보에서검출된다.
摘要翻译：系统和方法处理包括运动中的至少一个物体的视觉信息。通过定位对象的至少一个空间边缘来处理视觉信息，为N帧中的至少一个空间边缘生成多个时空梯度，然后从时空梯度生成运动模糊图像。对运动模糊图像进行回归分析以确定对象的运动信息的方向，然后基于运动信息的方向为N个帧生成场景活动向量。基于场景活动向量在视觉信息中检测到事件。

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