专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

21. 发明申请

US20170068853A1 FAST AND ROBUST IDENTIFICATION OF EXTREMITIES OF AN OBJECT WITHIN A SCENE 有权
标题翻译：快速，可靠地识别场景中的对象
公开(公告)号：US20170068853A1
公开(公告)日：2017-03-09
申请号：US14844313
申请日：2015-09-03
申请人： gestigon GmbH
发明人： Sascha Klement , Florian Hartmann , Foti Coleca , Ibrahim Awada
IPC分类号： G06K9/00 , G06K9/62 , G06T7/60 , G06K9/46
CPC分类号： G06K9/00375 , G06K9/00 , G06K9/00201 , G06K9/00208 , G06K9/00335 , G06K9/00362 , G06K9/34 , G06K9/342 , G06K9/469 , G06K9/627 , G06K9/6296 , G06T7/66
摘要： Described herein are a system and method for identifying extremities of an object within a scene. The method comprises operating an image processing system to receive image data from a sensor. The image data represents an image of the scene with the object. The image data comprises a two-dimensional array of pixels and each pixel contains a depth value indicating distance from the sensor. The image processing system slices the image into slices. Each respective slice comprises those pixels with depth values that lie within a respective range of distances defined relative to a reference. For each of the slices, the method identifies one or more connected regions of pixels that are neighbors in the two-dimensional array of pixels. The method builds, based on the connected region of pixels that have been identified for the slices and depth information inherent to the respective slices, a graph consisting of interconnected nodes. The connected regions form the nodes of the graph and the nodes are interconnected in the graph based on their relative distance to the reference. Extremities of the object are determined based on the graph.
摘要翻译：这里描述了一种用于识别场景内的对象的四肢的系统和方法。该方法包括操作图像处理系统以从传感器接收图像数据。图像数据表示具有对象的场景的图像。图像数据包括像素的二维阵列，并且每个像素包含指示距离传感器的距离的深度值。图像处理系统将图像切片成切片。每个相应的切片包括深度值位于相对于基准定义的相应距离范围内的那些像素。对于每个切片，该方法识别在二维像素阵列中的邻近的像素的一个或多个连接的区域。该方法基于已经针对切片识别的像素的连接区域和相应切片固有的深度信息构建由互连节点组成的图形。连接的区域形成图的节点，并且节点在图中基于它们与参考的相对距离而互连。基于图形确定对象的四肢。

22. 发明申请

US20160300126A1 METHOD OF CONSTRUCTION OF ANOMALY MODELS FROM ABNORMAL DATA 有权
标题翻译：从异常数据构建异常模型的方法
公开(公告)号：US20160300126A1
公开(公告)日：2016-10-13
申请号：US15100612
申请日：2013-11-29
申请人： GE AVIATION SYSTEMS LIMITED
发明人： Robert Edward CALLAN , David Stephen HARDWICK
IPC分类号： G06K9/66 , G06K9/62
CPC分类号： G06K9/66 , G06K9/6215 , G06K9/6257 , G06K9/6259 , G06K9/6284 , G06K9/6296
摘要： A method (100) of constructing a probabilistic graphical model (10) of a system from data that includes both normal and anomalous data includes the step of learning parameters of a structure for the probabilistic graphical model (10). The structure includes at least one latent variable (26) on which other variables (12, 14, 16, 18, 20, 22, 24) are conditional, and has a plurality of components. The method further includes the steps of: iteratively associating one or more of the plurality of components of the latent variable (26) with normal data; constructing a matrix of the associations; detecting abnormal components of the latent variable (26) based on one of a low association with the normal data or the matrix of associations; and deleting the abnormal components of the latent variable (26) from the probabilistic graphical model (10).
摘要翻译：从包括正常数据和异常数据的数据构建系统的概率图形模型（10）的方法（100）包括学习用于概率图形模型（10）的结构的参数的步骤。该结构包括至少一个潜在变量（26），其上的其他变量（12,14,16,18,20,22,24）是有条件的并且具有多个分量。该方法还包括以下步骤：将潜在变量（26）的多个分量中的一个或多个与正常数据进行迭代关联; 构建关联矩阵; 基于与正常数据或关联矩阵的低关联性来检测潜变量（26）的异常成分; 以及从所述概率图形模型（10）中删除所述潜在变量（26）的异常分量。

23. 发明申请

US20160180192A1 SYSTEM AND METHOD FOR PARTIALLY OCCLUDED OBJECT DETECTION 有权
标题翻译：用于部分监测对象检测的系统和方法
公开(公告)号：US20160180192A1
公开(公告)日：2016-06-23
申请号：US14641506
申请日：2015-03-09
申请人： Honda Motor Co., Ltd.
发明人： Alper Ayvaci , Kai-Chi Chan , Bernd Heisele
IPC分类号： G06K9/52 , G06K9/00 , G06K9/62
CPC分类号： G06K9/00362 , G06K9/00805 , G06K9/4638 , G06K9/4642 , G06K9/6296
摘要： A method for partially occluded object detection includes obtaining a response map for a detection window of an input image, the response map based on a trained model and including a root layer and a parts layer. The method includes determining visibility flags for each root cell of the root layer and each part of the parts layer. The visibility flag is one of visible or occluded. The method includes determining an occlusion penalty for each root cell with a visibility flag of occluded and for each part with a visibility flag of occluded. The occlusion penalty is based on a location of the root cell or the part with respect to the detection window. The method determines a detection score for the detection window based on the visibility flags and the occlusion penalties and generates an estimated visibility map for object detection based on the detection score.
摘要翻译：一种用于部分遮挡的物体检测的方法包括获得输入图像的检测窗口的响应图，基于经过训练的模型的响应图，并且包括根层和部分层。该方法包括确定根层的每个根单元和零件层的每个部分的可见性标志。可见度标志是可见或闭塞之一。该方法包括用遮挡的可见性标志以及具有遮挡的可见性标志的每个部分确定每个根细胞的遮挡罚分。遮挡罚分是基于根单元或相对于检测窗口的部分的位置。该方法基于可见性标志和遮挡罚分来确定检测窗口的检测分数，并且基于检测分数生成用于对象检测的估计可见度图。

24. 发明申请

US20160042223A1 METHOD AND APPARATUS FOR FACIAL RECOGNITION 审中-公开
标题翻译：方法和装置用于真实识别
公开(公告)号：US20160042223A1
公开(公告)日：2016-02-11
申请号：US14795002
申请日：2015-07-09
申请人： Samsung Electronics Co., Ltd.
发明人： Sungjoo SUH , Wonjun HWANG , Wonjun KIM , Jaejoon HAN
IPC分类号： G06K9/00 , G06K9/62
CPC分类号： G06K9/00221 , G06K9/00228 , G06K9/00248 , G06K9/00281 , G06K9/00288 , G06K9/6209 , G06K9/6278 , G06K9/6296 , G06K2209/21
摘要： At least some example embodiments disclose a method and apparatus for facial recognition. The facial recognition method includes detecting initial landmarks from a facial image, first normalizing the facial image using the initial landmarks, updating a position of at least one of intermediate landmarks based on the first normalizing, the intermediate landmarks being landmarks transformed from the initial landmarks through the first normalizing, second normalizing the facial image after the updating and recognizing a face using a feature of the second normalized facial image.
摘要翻译：至少一些示例性实施例公开了用于面部识别的方法和装置。面部识别方法包括从面部图像检测初始界标，首先使用初始地标标准化面部图像，基于第一归一化来更新中间地标中的至少一个的位置，中间地标是从初始地标变换的地标，通过第一归一化，使用第二标准化脸部图像的特征更新并识别脸部之后，对面部图像进行二次归一化。

25. 发明授权

US09213885B1 Object recognizer and detector for two-dimensional images using Bayesian network based classifier 有权
标题翻译：使用基于贝叶斯网络的分类器的二维图像的对象识别器和检测器
公开(公告)号：US09213885B1
公开(公告)日：2015-12-15
申请号：US13901803
申请日：2013-05-24
申请人： Carnegie Mellon University
发明人： Henry Schneiderman
IPC分类号： G06K9/62 , G06K9/00
CPC分类号： G06K9/6278 , G06K9/00228 , G06K9/00241 , G06K9/00288 , G06K9/6227 , G06K9/6282 , G06K9/6296 , G06K9/66
摘要： System and method for determining a classifier to discriminate between two classes—object or non-object. The classifier may be used by an object detection program to detect presence of a 3D object in a 2D image. The overall classifier is constructed of a sequence of classifiers, where each such classifier is based on a ratio of two graphical probability models. A discreet-valued variable representation at each node in a Bayesian network by a two-stage process of tree-structured vector quantization is discussed. The overall classifier may be part of an object detector program that is trained to automatically detect different types of 3D objects. Computationally efficient statistical methods to evaluate overall classifiers are disclosed. The Bayesian network-based classifier may also be used to determine if two observations belong to the same category.
摘要翻译：用于确定分类器以区分两个类（对象或非对象）的系统和方法。分类器可以被对象检测程序用于检测2D图像中的3D对象的存在。整体分类器由分类器序列构成，其中每个分类器基于两个图形概率模型的比率。讨论了通过树结构矢量量化的两阶段过程在贝叶斯网络中的每个节点处的谨慎值变量表示。总体分类器可以是被检测以自动检测不同类型的3D对象的对象检测器程序的一部分。公开了用于评估整体分类器的计算有效的统计方法。也可以使用基于贝叶斯网络的分类器来确定两个观测值是否属于同一类别。

26. 发明申请

US20150281655A1 SYSTEMS AND METHODS FOR TRACKING INTERACTING OBJECTS 有权
标题翻译：跟踪交互对象的系统和方法
公开(公告)号：US20150281655A1
公开(公告)日：2015-10-01
申请号：US14666906
申请日：2015-03-24
申请人： ECOLE POLYTECHNIQUE FEDERALE DE LAUSANNE (EPFL)
发明人： ENGIN TURETKEN , Pascal FUA , Francois FLEURET , Xinchao WANG
IPC分类号： H04N7/18 , G06K9/62 , G06K9/00 , G06T7/20 , G06T7/00
CPC分类号： H04N7/181 , G06K9/00771 , G06K9/6296 , G06K2009/3291 , G06T7/277 , G06T2207/10016 , G06T2207/20076 , G06T2207/30232 , G06T2207/30236 , G06T2207/30241
摘要： Systems and methods for tracking interacting objects may acquire, with a sensor, and two or more images associated with two or more time instances. A processor may generate image data from the two or more images. The processor may apply an extended Probability Occupancy Map (POM) algorithm to the image data to obtain probability of occupancy for a container class of potentially interacting objects, probability of occupancy for a containee class of the potentially interacting objects, and a size relationship of the potentially interacting objects, over a set of discrete locations on a ground plane for each time instance. The processor may estimate trajectories of an object belonging to each of the two classes by determining a solution of a tracking model on the basis of the occupancy probabilities and a set of rules describing the interaction between objects of different or the same classes.
摘要翻译：用于跟踪交互对象的系统和方法可以使用传感器和与两个或更多个时间实例相关联的两个或多个图像来获取。处理器可以从两个或更多个图像生成图像数据。处理器可以对图像数据应用扩展概率占有映射（POM）算法，以获得容器类潜在交互对象的占用概率，潜在交互对象的受控类的占用概率，以及在每个时间实例的地平面上的一组离散位置上潜在的交互对象。处理器可以通过基于占用概率和描述不同或相同类的对象之间的交互的一组规则来确定跟踪模型的解决方案来估计属于两个类中的每一个的对象的轨迹。

27. 发明授权

US09141886B2 Method for the automated extraction of a planogram from images of shelving 有权
标题翻译：用于从搁架图像自动提取平面图的方法
公开(公告)号：US09141886B2
公开(公告)日：2015-09-22
申请号：US14004714
申请日：2012-03-05
申请人： Adrien Auclair , Anne-Marie Tousch
发明人： Adrien Auclair , Anne-Marie Tousch
IPC分类号： G06K9/62 , G06K9/72 , G06Q10/08 , G06Q30/02
CPC分类号： G06K9/6296 , G06K9/62 , G06K9/6292 , G06K9/72 , G06K2209/17 , G06Q10/087 , G06Q30/0201
摘要： A method for automatically constructing a planogram from photographs of shelving, replacing laborious manual construction includes the following steps: a step (1) in which the images are received, a step (2) in which the images are assembled, a step (3) in which the structure is automatically constructed, a step (4) in which the products are automatically detected, and a step (5) in which the products are positioned in the structure. The product detection step (4) enhances traditional image recognition techniques, using artificial learning techniques to incorporate characteristics specific to the planograms. This product detection step (4) also includes at least two successive classification steps, namely: an initialization step (41) with detection of product categories; and a classification step (42) with the classification of the products themselves, each of these steps including a first image recognition step, followed by a statistical filtering step based on the characteristics specific to the planograms.
摘要翻译：一种用于从搁架照片自动构建平面图的方法，替代费力的手动构造包括以下步骤：步骤（1），其中接收图像;步骤（2），其中组装图像;步骤（3）其中自动构造结构，其中自动检测产品的步骤（4）以及产品位于结构中的步骤（5）。产品检测步骤（4）增强了传统的图像识别技术，使用人工学习技术来结合平面图特有的特征。该产品检测步骤（4）还包括至少两个连续的分级步骤，即：检测产品类别的初始化步骤（41）以及具有产品本身分类的分类步骤（42），这些步骤中的每一个包括第一图像识别步骤，随后是基于对于图表特有的特征的统计过滤步骤。

28. 发明申请

US20150262037A1 VISUAL RECOGNITION USING SOCIAL LINKS 有权
标题翻译：使用社会链接的视觉识别
公开(公告)号：US20150262037A1
公开(公告)日：2015-09-17
申请号：US14215925
申请日：2014-03-17
申请人： YAHOO! INC.
发明人： Jia Li , Xiangnan Kong
IPC分类号： G06K9/66 , G06N99/00 , G06F17/24
CPC分类号： G06F17/241 , G06F17/30598 , G06K9/00677 , G06K9/6296
摘要： System, method and architecture for providing improved visual recognition by modeling visual content, semantic content and an implicit social network representing individuals depicted in a collection of content, such as visual images, photographs, etc. which network may be determined based on co-occurrences of individuals represented by the content, and/or other data linking the individuals. In accordance with one or more embodiments, using images as an example, a relationship structure may comprise an implicit structure, or network, determined from co-occurrences of individuals in the images. A kernel jointly modeling content, semantic and social network information may be built and used in automatic image annotation and/or determination of relationships between individuals, for example.
摘要翻译：系统，方法和架构，用于通过建模视觉内容，语义内容和表示在诸如视觉图像，照片等的内容集合中描绘的个人的隐含的社交网络来提供改进的视觉识别。该网络可以基于共同事件来确定由内容代表的个人和/或连接个人的其他数据。根据一个或多个实施例，使用图像作为示例，关系结构可以包括由图像中的个体的共同出现确定的隐式结构或网络。联合建模内容，语义和社交网络信息的内核可以被构建并用于例如自动图像注释和/或个体之间的关系的确定。

29. 发明授权

US09129158B1 Method and system for embedding visual intelligence 有权
标题翻译：嵌入视觉智能的方法和系统
公开(公告)号：US09129158B1
公开(公告)日：2015-09-08
申请号：US13412527
申请日：2012-03-05
申请人： Swarup Medasani , Suhas E. Chelian , Shinko Y. Cheng , Rashmi N. Sundareswara , Howard Neely, III
发明人： Swarup Medasani , Suhas E. Chelian , Shinko Y. Cheng , Rashmi N. Sundareswara , Howard Neely, III
IPC分类号： G06K9/62 , G06K9/00 , G06T7/20
CPC分类号： G06K9/00718 , G06K9/00335 , G06K9/00342 , G06K9/6219 , G06K9/6263 , G06K9/6296 , G06T2207/10016
摘要： Described is a method and system for embedding unsupervised learning into three critical processing stages of the spatio-temporal visual stream. The system first receives input video comprising input video pixels representing at least one action and at least one object having a location. Microactions are generated from the input image using a set of motion sensitive filters. A relationship between the input video pixels and the microactions is then learned, and a set of spatio-temporal concepts is learned from the microactions. The system then learns to acquire new knowledge from the spatio-temporal concepts using mental imagery processes. Finally, a visual output is presented to a user based on the learned set of spatio-temporal concepts and the new knowledge to aid the user in visually comprehending the at least one action in the input video.
摘要翻译：描述了将无监督学习嵌入时空视觉流的三个关键处理阶段的方法和系统。系统首先接收包括表示至少一个动作的输入视频像素和至少一个具有位置的对象的输入视频。使用一组运动敏感滤波器从输入图像生成微反应。然后学习输入视频像素和微动作之间的关系，并从微动态学习一组时空概念。该系统然后学习从使用心理图像过程的时空概念中获取新知识。最后，基于学习的时空概念和新知识，向用户呈现视觉输出，以帮助用户直观地理解输入视频中的至少一个动作。

30. 发明授权

US09087361B2 Graph traversal for generating table views 有权
标题翻译：图表遍历用于生成表视图
公开(公告)号：US09087361B2
公开(公告)日：2015-07-21
申请号：US13490238
申请日：2012-06-06
申请人： Jason Mirra , Anthony Sherbondy , Nhan Nguyen , Michael Paulus , Zachary Reynolds , William Chu , Wai Loon Chan , Jerry Zhang , Richard Thomas Martell, III , Justin Ross , Michael Greenbaum , Joe Lonsdale
发明人： Jason Mirra , Anthony Sherbondy , Nhan Nguyen , Michael Paulus , Zachary Reynolds , William Chu , Wai Loon Chan , Jerry Zhang , Richard Thomas Martell, III , Justin Ross , Michael Greenbaum , Joe Lonsdale
IPC分类号： G06Q40/00 , G06Q40/06 , G06F3/048 , G06Q40/08 , G06T15/00 , G06F11/32 , G06K9/62
CPC分类号： G06Q40/06 , G06F3/048 , G06F11/323 , G06K9/6296 , G06Q40/00 , G06Q40/08 , G06T15/005
摘要： A method comprising creating and storing a graph having nodes and edges that represent financial assets and accounts in which the assets are held; individuals who own the assets; or legal entities who own the assets; receiving and storing bucketing factors and column factors; traversing the graph and creating a list of a plurality of paths of nodes and edges in the graph; applying the bucketing factors to the paths to result in associating each set among a plurality of sets of the nodes with a different value node among a plurality of value nodes; applying the column factors to the paths and the value nodes to result in associating column result values with the value nodes; creating and causing displaying a table view by forming rows based on the value nodes and forming columns based on the column result values.
摘要翻译：一种方法，包括创建和存储具有表示所述资产所在的金融资产和账户的节点和边的图; 拥有资产的个人; 或拥有该资产的法人单位; 接收和存储压力因素和柱因素; 遍历图并创建图中多个节点和边缘路径的列表; 将所述衰减因子应用于所述路径以导致将多个节点集合中的每个集合与多个值节点中的不同值节点相关联; 将列因子应用于路径和值节点，以使列结果值与值节点相关联; 通过基于值节点形成行并基于列结果值形成列来创建并导致显示表视图。

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