专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

81. 发明公开

EP2851841A8 System and method of alerting a driver that visual perception of pedestrian may be difficult 审中-公开
标题翻译：系统和方法，用于从具有一个行人的视觉感知可能是困难的警告驾驶员
公开(公告)号：EP2851841A8
公开(公告)日：2015-07-29
申请号：EP14182908.5
申请日：2014-08-29
申请人： TOYOTA MOTOR ENGINEERING & MANUFACTURING NORTH AMERICA, INC. , TOYOTA JIDOSHA KABUSHIKI KAISHA , Indiana University Research and Technology Corporation
发明人： Takahashi, Hiroyuki , Sherony, Rini , Du, Eliza Y. , Jiang, Pingge , Yang, Kai
IPC分类号： G06K9/00 , G06K9/62
CPC分类号： G06K9/00805 , G06K9/00362 , G06K9/00369 , G06K9/6207 , G06T2207/30236 , G08G1/166
摘要： A pedestrian perception alert system configured to issue a warning during real-time when a driver's visual detection of a pedestrian is difficult, and a method thereof is provided. The system includes a video camera, an alert for issuing a warning, a processor, and a Pedestrian Detection Unit ("PDU"). The PDU analyzes the video camera image to detect a pedestrian. A Global Clutter Analysis Unit ("GCAU") generates a global clutter score. A Local Pedestrian Clutter Analysis Unit ("LPCAU") generates a local pedestrian clutter score. The processer processes the global clutter score and local pedestrian clutter score so as to generate a pedestrian detection score. The alert is actuated when the pedestrian detection score is outside of a predetermined threshold so as to notify the driver that perception of a pedestrian is difficult at that time.

82. 发明公开

EP2851841A3 System and method of alerting a driver that visual perception of pedestrian may be difficult 审中-公开
标题翻译：警告驾驶员对行人的视觉感知可能困难的系统和方法
公开(公告)号：EP2851841A3
公开(公告)日：2015-05-20
申请号：EP14182908.5
申请日：2014-08-29
申请人： Toyota Motor Engineering & Manufacturing North America, Inc. , Toyota Jidosha Kabushiki Kaisha , Indiana University Research and Technology Corporation
发明人： Takahashi, Hiroyuki , Sherony, Rini , Du, Eliza Y. , Jiang, Pingge , Yang, Kai
IPC分类号： G06K9/00 , G06K9/62
CPC分类号： G06K9/00805 , G06K9/00362 , G06K9/00369 , G06K9/6207 , G06T2207/30236 , G08G1/166
摘要： A pedestrian perception alert system configured to issue a warning during real-time when a driver's visual detection of a pedestrian is difficult, and a method thereof is provided. The system includes a video camera, an alert for issuing a warning, a processor, and a Pedestrian Detection Unit ("PDU"). The PDU analyzes the video camera image to detect a pedestrian. A Global Clutter Analysis Unit ("GCAU") generates a global clutter score. A Local Pedestrian Clutter Analysis Unit ("LPCAU") generates a local pedestrian clutter score. The processer processes the global clutter score and local pedestrian clutter score so as to generate a pedestrian detection score. The alert is actuated when the pedestrian detection score is outside of a predetermined threshold so as to notify the driver that perception of a pedestrian is difficult at that time.
摘要翻译：提供一种行人感知警报系统及其方法，所述行人感知警报系统被配置为当驾驶员对行人的视觉检测困难时实时发出警告。该系统包括摄像机，发出警告的警报，处理器和行人检测单元（“PDU”）。 PDU分析摄像机图像以检测行人。全球杂波分析单元（“GCAU”）产生全球杂波分数。本地行人杂波分析单元（“LPCAU”）产生本地行人杂波评分。处理器处理全局杂波得分和本地行人杂波得分，从而生成行人检测得分。当行人检测分数超出预定阈值时启动警报，以通知驾驶员当时对行人的感知困难。

83. 发明公开

EP2633492A1 METHODE DE PRE-TRAITEMENT D'UNE IMAGE TRIDIMENSIONNELLE DE LA SURFACE D'UN PNEUMATIQUE A L'AIDE DE DEFORMATIONS B-SPLINE SUCCESSIVES 审中-公开
标题翻译： FOR A轮胎的表面的三维图像预处理方法是指连续的B样条曲线的变形
公开(公告)号：EP2633492A1
公开(公告)日：2013-09-04
申请号：EP11770805.7
申请日：2011-10-20
申请人： Compagnie Générale des Etablissements Michelin , MICHELIN Recherche et Technique S.A.
发明人： VINCIGUERRA, Régis , BOURGEOIS, Steve , JOLY, Alexandre
IPC分类号： G06T3/00 , G06K9/64
CPC分类号： G06T7/0004 , G06K9/6207 , G06T3/0068 , G06T2207/10028 , G06T2207/20016 , G06T2207/30108
摘要： The invention relates to a method for inspecting the surface of a tyre by comparing same with a three-dimensional reference surface, said surfaces comprising embossed markings. The invention comprises the following steps consisting in: determining the three-dimensional profile of the surface to be inspected; extracting the contours of the graphical elements; locating the characteristic points on the surface to be inspected and pairing said points with the corresponding characteristic points of the reference surface, such as to create a set of pairs of paired points; associating a first reset B-Spline surface with the reference surface, by associating the characteristic points of said surface with the control points of the first reset B-Spline surface; and deforming the reference surface, by moving the control points of the first reset B-Spline surface so that they are superimposed on the characteristic points of the surface to be inspected with which they were paired.

84. 发明公开

EP2289025A1 METHODS OF AND SYSTEM FOR DETECTION AND TRACKING OF OSTEOPOROSIS 无效
标题翻译：方法和系统进行检测和骨质疏松研究
公开(公告)号：EP2289025A1
公开(公告)日：2011-03-02
申请号：EP09767289.3
申请日：2009-05-27
申请人： Optasia Medical, Inc.
发明人： BRETT, Alan , HASLAM, Jane , HAYES, Curtis , KRASNOW, Joel , VAN KUIJK, Cornelius , MILLER, Colin
IPC分类号： G06K9/62
CPC分类号： G06T7/0012 , G06K9/0014 , G06K9/6206 , G06K9/6207 , G06K9/6209 , G06K9/6263 , G06K2209/05 , G06T2207/10116 , G06T2207/20124 , G06T2207/30012
摘要： A method and system for detection and tracking of osteoporosis is disclosed. A method of characterizing an image of a target vertebra includes building a computer model from a set of sample images of pathological and non-pathological variations of vertebrae representing variations in shape of the vertebrae. The method also includes receiving an image of a target vertebra of a subject and automatically estimating contours of lateral outlines of the superior and the inferior cortical endplates of the image. The parameters of the model are varied to determine a set that represents a model shape that approximates the estimated contours of the outlines of the cortical endplates. The method includes automatically characterizing the target vertebra based on the set of model parameters that are determined and outputting on a display device the characterization of the target vertebra.

85. 发明公开

EP1198200A4 INTRAVASCULAR ULTRASONIC ANALYSIS USING ACTIVE CONTOUR METHOD AND SYSTEM 有权
标题翻译： INTRAVASKULÄREULTRASCHALLANLAGE UNTER VERWENDUNG EINER AKTIVEN KONTURMETHODE UND EINES ENTSPRECHENDEN SYSTEMS
公开(公告)号：EP1198200A4
公开(公告)日：2004-06-23
申请号：EP00941653
申请日：2000-06-22
申请人： CLEVELAND CLINIC FOUNDATION
发明人： KLINGENSMITH JON D , VINCE DAVID GEOFFREY , SHEKHAR RAJ
IPC分类号： A61B8/12 , A61B5/107 , A61B8/08 , G06K9/64 , G06T1/00 , G06T5/00 , G06T7/60 , A61B8/00 , A61K35/00 , G06K9/00
CPC分类号： A61B8/4461 , A61B5/02007 , A61B5/1076 , A61B8/0833 , A61B8/0858 , A61B8/12 , A61B8/463 , G06K9/6207 , G06T7/12 , G06T7/149 , G06T2207/10132 , G06T2207/20101 , G06T2207/30101
摘要： An intravascular ultrasound (IVUS) analysis system (10) and method is provided which determines luminal and mediCal-adventitial boundaries of a blood vessel. Ultrasonic data is acquired by a rotating transducer mounted to a tip of a catheter which is inserted into the blood vessel (30). An intravascular image is reconstructed from the ultrasound data (15). A boundary contour is generated based on the boundary points (70). Once the final luminal boundary contour is generated, the process is repeated to determine the mediCal-adventitial boundary contour. With the contour data, properties of the blood vessel are analyzed including determining the area of the lumen and percent of occlusion caused by plaque.
摘要翻译：提供了血管内超声（IVUS）分析系统和方法，其确定血管的腔内和外侧 - 外膜边界。通过安装到插入血管的导管的尖端的旋转传感器获取超声波数据。从超声数据重建血管内图像。为了确定容器的管腔边界，用户选择被认为是管腔边界位置的图像上的边界点。基于边界点生成边界轮廓。然后通过基于在极化格式的图像上执行的腔边界的径向确定的边缘调整边界点来优化边界轮廓。一旦生成最终的管腔边界轮廓，重复该过程以确定内侧 - 外膜边界轮廓。使用轮廓数据，分析血管的性质，包括确定管腔面积和由斑块引起的闭塞百分比。

86. 发明公开

EP1400920A2 Image processing device and ultrasonic diagnostic device 审中-公开
标题翻译： Bildverarbeitungsvorrichtung und Ultraschalldiagnostikvorrichtung
公开(公告)号：EP1400920A2
公开(公告)日：2004-03-24
申请号：EP03005341.7
申请日：2003-03-12
申请人： MATSUSHITA ELECTRIC INDUSTRIAL CO., LTD.
发明人： Yamauchi, Masaki
IPC分类号： G06T5/00
CPC分类号： A61B8/08 , A61B5/1075 , A61B8/461 , A61B8/467 , G06K9/00228 , G06K9/6207 , G06T5/008 , G06T5/40 , G06T7/12 , G06T2207/10132 , G06T2207/20012 , G06T2207/20021 , G06T2207/20104 , G06T2207/20192 , G06T2207/30004 , G06T2207/30201
摘要： An area dividing unit 103 divides an ultrasound image into sub-areas in accordance with an initial contour. An evaluation value calculating unit 104 calculates evaluation values on the basis of information which includes, for example, brightness value-related information (e.g. contrast distribution) and position-related information (e.g. a distance from a reference point) of each of the sub-areas, and shape-related information (e.g. presence/absence of an edge). An area selecting unit 106 selects one or more sub-areas according to the calculated evaluation values. An each area processing unit 105 performs image processing appropriate to the selected sub-areas. An image reconstructing unit 107 reconstructs the ultrasound image using the sub-areas for which image processing has been performed.
摘要翻译：区域划分单元103根据初始轮廓将超声图像划分成子区域。评估值计算单元104基于包括例如每个子像素的亮度值相关信息（例如，对比度分布）和位置相关信息（例如，距参考点的距离）的信息来计算评估值，区域和形状相关信息（例如边缘的存在/不存在）。区域选择单元106根据计算的评估值选择一个或多个子区域。每个区域处理单元105执行适合所选择的子区域的图像处理。图像重建单元107使用已经进行图像处理的子区域来重构超声图像。

87. 发明公开

EP1198200A1 INTRAVASCULAR ULTRASONIC ANALYSIS USING ACTIVE CONTOUR METHOD AND SYSTEM 有权
标题翻译： INTRAVASKULÄREULTRASCHALLBILDANALYSE UNTER VERWENDUNG EINER AKTIVEN KONTURMETHODE
公开(公告)号：EP1198200A1
公开(公告)日：2002-04-24
申请号：EP00941653.8
申请日：2000-06-22
申请人： THE CLEVELAND CLINIC FOUNDATION
发明人： Klingensmith, Jon D. , Vince, David Geoffrey , Shekhar, Raj
IPC分类号： A61B8/00 , A61K35/00 , G06K9/00
CPC分类号： A61B8/4461 , A61B5/02007 , A61B5/1076 , A61B8/0833 , A61B8/0858 , A61B8/12 , A61B8/463 , G06K9/6207 , G06T7/12 , G06T7/149 , G06T2207/10132 , G06T2207/20101 , G06T2207/30101
摘要： An intravascular ultrasound (IVUS) analysis system (10) and method is provided which determines luminal and mediCal-adventitial boundaries of a blood vessel. Ultrasonic data is acquired by a rotating transducer mounted to a tip of a catheter which is inserted into the blood vessel (30). An intravascular image is reconstructed from the ultrasound data (15). A boundary contour is generated based on the boundary points (70). Once the final luminal boundary contour is generated, the process is repeated to determine the mediCal-adventitial boundary contour. With the contour data, properties of the blood vessel are analyzed including determining the area of the lumen and percent of occlusion caused by plaque.
摘要翻译：提供了血管内超声（IVUS）分析系统和方法，其确定血管的腔内和外侧 - 外膜边界。通过安装到插入血管的导管的尖端的旋转传感器获取超声波数据。从超声数据重建血管内图像。为了确定容器的管腔边界，用户选择被认为是管腔边界位置的图像上的边界点。基于边界点生成边界轮廓。然后通过基于在极化格式的图像上执行的腔边界的径向确定的边缘调整边界点来优化边界轮廓。一旦生成最终的管腔边界轮廓，重复该过程以确定内侧 - 外膜边界轮廓。使用轮廓数据，分析血管的性质，包括确定管腔面积和由斑块引起的闭塞百分比。

88. 发明公开

EP1151414A1 PROCEDE DE TRAITEMENT D'IMAGES EN PRESENCE DE BRUIT STRUCTURE ET DE BRUIT NON-STRUCTURE 审中-公开
标题翻译：一种用于处理图像，结构化和UNSTRUKTURIENTEN噪声噪声的存在
公开(公告)号：EP1151414A1
公开(公告)日：2001-11-07
申请号：EP00974589.4
申请日：2000-10-27
申请人： COMMISSARIAT A L'ENERGIE ATOMIQUE
发明人： DANCRE, Mathieu , ORIOL, Ludovic , SEQUEIRA, Jean
IPC分类号： G06T5/00
CPC分类号： G06K9/6207 , G06T5/002 , G06T5/30 , G06T7/13 , G06T7/136 , G06T2207/10132
摘要： The invention concerns a method for processing a two-dimensional or three-dimensional image representing an object whereof the contours are disturbed by structured or unstructured noise. The invention is characterised in that it consists in extracting from the image, the active contour of the object by the following steps: a) analysing the unstructured noise, that is the background noise; b) analysing the structured noise, that is detecting the multiple reflections and the signature of the object; c) identifying the edges of the objects from the image obtained in b); and d) identifying the surfaces of the object from the raw image (or initial image) and from the images obtained at steps b) and c).
摘要翻译：本发明涉及用于处理在对象表示WHEREOF轮廓是由结构化或非结构化的噪声干扰的二维或三维图像的方法。本发明DASS它在从所述图像提取besteht，通过以下步骤将对象的活动轮廓：a）所述成就分析非结构化噪声，背景噪声是做; b）中的成就分析结构化噪声，没有检测是多次反射和对象的签名; c）确定从在b）中获得的图像中的对象的边缘; 和d）确定从所述原始图像（或初始图像的所述对象的表面），并从）在步骤B中获得的图像和c）。

89. 发明公开

EP1061748A2 Video object segmentation using active contour modelling with global relaxation 审中-公开
标题翻译：视频播放器Verwendung von Aktivkonturmodellisierung mit globaler Relaxation
公开(公告)号：EP1061748A2
公开(公告)日：2000-12-20
申请号：EP00201976.8
申请日：2000-06-05
申请人： University of Washington
发明人： Sun, Shijun , Kim, Yongmin
IPC分类号： H04N7/26
CPC分类号： G06K9/342 , G06K9/32 , G06K9/38 , G06K9/44 , G06K9/4652 , G06K9/6207 , G06K2009/3291 , G06T7/254 , G06T9/001 , G06T9/20
摘要： A system (10) for image object tracking and segmentation, includes (i) a modified adaptive resonance theory - 2 (M-ART2) model (12) for detecting changes of scenes, (ii) a two-dimensional correlative autopredicitve search (2D CAPS) method (14/46) for object tracking, (iii) a derivation (16/50) of contour energy for use in modelling an object edge, and (iv) an active contour model (18/52) with global relaxation for defining optimal image object boundaries. The modelled object boundary is derived from an edge potential energy calculation and a set of current edge points (176). For each edge point, several candidate data points (186-189) are also selected. Rather than calculate an energy value for each potential contours, a solution is achieved by comparing energy differences along a travel path. The selected contour is built in steps. An optimal path is selected from the potential paths.
摘要翻译：一种用于图像对象跟踪和分割的系统（10）包括（i）用于检测场景变化的修改的自适应共振理论-2（M-ART2）模型（12），（ii）二维相关自动预测搜索 CAPS）方法（14/46），（iii）用于建模物体边缘的轮廓能量的推导（16/50），以及（iv）具有全局放松的主动轮廓模型（18/52）定义最佳图像对象边界。建模对象边界是从边缘势能计算和一组当前边缘点（176）导出的。对于每个边缘点，还选择若干候选数据点（186-189）。不是计算每个潜在轮廓的能量值，而是通过比较行进路径上的能量差异来实现解决方案。所选轮廓内置步骤。从潜在路径中选择最佳路径。

90. 发明公开

EP0785530A1 Procédé d'extraction des deux bords d'une route par propagation de contour actif 失效
标题翻译： Verfahren zur Gewinnung beiderStrassenränderdurch aktive Kontur-Ausbreitung
公开(公告)号：EP0785530A1
公开(公告)日：1997-07-23
申请号：EP97400052.3
申请日：1997-01-13
申请人： ALCATEL ALSTHOM COMPAGNIE GENERALE D'ELECTRICITE
发明人： Rezzouk, Jamal
IPC分类号： G06T5/00
CPC分类号： G06K9/6207 , G06K9/00798 , G06T7/12 , G06T7/149 , G06T2207/30256
摘要： Selon ce procédé, on entre un premier (CS1) et un second (CS2) contour initial se situant respectivement à proximité de l'un et de l'autre bord de la route à extraire d'une image numérisée. On propage le premier contour initial à l'aide d'un premier processus automatique de propagation de contour actif (32) et le second contour initial à l'aide d'un second processus de propagation de contour actif (33). Chaque processus de propagation utilise, d'une part, un modèle d'énergie incluant un terme (E coupl ) relatif à des forces élastiques de couplage (F,T) entre des points appariés du premier et du second contour initial et, d'autre part, une direction de prolongation (Dp) définie comme étant une direction moyenne par rapport à deux directions de prolongation déterminées respectivement pour le premier et le second contour actif.
摘要翻译：从数字摄影图像提取具有两个侧边缘（10,11）的物体（1）的轮廓的方法使用主动轮廓传播的自动处理，并且包括以下阶段。位于图像中物体的一个或另外边缘附近的输入（30），第一（CS1）和第二（CS2）初始轮廓。借助于第二主动轮廓传播过程，借助于主动轮廓传播过程和第二初始轮廓（33）来传播第一初始轮廓（32），用于每个过程：a）能量模型，包括项（Ecoup1）相对于与第一和第二初始轮廓匹配的点之间的弹性耦合力（F，T）; 以及b）所定义的活动轮廓的延长方向（Dp）是分别针对第一和第二主动轮廓确定的两个延长方向（D1，D2）的平均方向。

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