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

US07499574B1 Video-based face recognition using probabilistic appearance manifolds 有权
标题翻译：基于视频的面部识别使用概率外观歧管
公开(公告)号：US07499574B1
公开(公告)日：2009-03-03
申请号：US10703288
申请日：2003-11-06
申请人： Ming-Hsuan Yang , Jeffrey Ho , Kuang-Chih Lee
发明人： Ming-Hsuan Yang , Jeffrey Ho , Kuang-Chih Lee
IPC分类号： G06K9/00
CPC分类号： G06K9/00335 , G06K9/00275 , G06K9/00288 , G06K9/3208 , G06K9/6232
摘要： The present invention meets these needs by providing temporal coherency to recognition systems. One embodiment of the present invention comprises a manifold recognition module to use a sequence of images for recognition. A manifold training module receives a plurality of training image sequences (e.g. from a video camera), each training image sequence including an individual in a plurality of poses, and establishes relationships between the images of a training image sequence. A probabilistic identity module receives a sequence of recognition images including a target individual for recognition, and identifies the target individual based on the relationship of training images corresponding to the recognition images. An occlusion module masks occluded portions of an individual's face to prevent distorted identifications.
摘要翻译：本发明通过向识别系统提供时间一致性来满足这些需求。本发明的一个实施例包括使用一系列图像进行识别的歧管识别模块。歧管训练模块接收多个训练图像序列（例如，从摄像机），每个训练图像序列包括多个姿势中的个体，并且建立训练图像序列的图像之间的关系。概率识别模块接收包括用于识别的目标个体的识别图像序列，并且基于与识别图像相对应的训练图像的关系来识别目标个体。闭塞模块遮挡个人脸部的遮挡部分以防止变形的识别。

2. 发明申请

US20090041310A1 VIDEO-BASED FACE RECOGNITION USING PROBABILISTIC APPEARANCE MANIFOLDS 有权
标题翻译：基于视觉的面部识别使用概念外观图
公开(公告)号：US20090041310A1
公开(公告)日：2009-02-12
申请号：US10703288
申请日：2003-11-06
申请人： Ming-Hsuan Yang , Jeffrey Ho , Kuang-Chih Lee
发明人： Ming-Hsuan Yang , Jeffrey Ho , Kuang-Chih Lee
IPC分类号： G06K9/00 , G06K9/54 , G06K9/60
CPC分类号： G06K9/00335 , G06K9/00275 , G06K9/00288 , G06K9/3208 , G06K9/6232
摘要： The present invention meets these needs by providing temporal coherency to recognition systems. One embodiment of the present invention comprises a manifold recognition module to use a sequence of images for recognition. A manifold training module receives a plurality of training image sequences (e.g. from a video camera), each training image sequence including an individual in a plurality of poses, and establishes relationships between the images of a training image sequence. A probabilistic identity module receives a sequence of recognition images including a target individual for recognition, and identifies the target individual based on the relationship of training images corresponding to the recognition images. An occlusion module masks occluded portions of an individual's face to prevent distorted identifications.
摘要翻译：本发明通过向识别系统提供时间一致性来满足这些需求。本发明的一个实施例包括使用一系列图像进行识别的歧管识别模块。歧管训练模块接收多个训练图像序列（例如，从摄像机），每个训练图像序列包括多个姿势中的个体，并且建立训练图像序列的图像之间的关系。概率识别模块接收包括用于识别的目标个体的识别图像序列，并且基于与识别图像相对应的训练图像的关系来识别目标个体。闭塞模块遮挡个人脸部的遮挡部分以防止变形的识别。

3. 发明授权

US08218817B2 Online articulate object tracking with appearance and shape 有权
标题翻译：在线表达对象跟踪与外观和形状
公开(公告)号：US08218817B2
公开(公告)日：2012-07-10
申请号：US12339029
申请日：2008-12-18
申请人： Ming-Hsuan Yang , Jeffrey Ho
发明人： Ming-Hsuan Yang , Jeffrey Ho
IPC分类号： G06K9/00
CPC分类号： G06K9/3241 , G06K9/00369 , G06K9/4647 , G06T7/248 , G06T2207/10016
摘要： A visual tracker tracks an object in a sequence of input images. A tracking module detects a location of the object based on a set of weighted blocks representing the object's shape. The tracking module then refines a segmentation of the object from the background image at the detected location. Based on the refined segmentation, the set of weighted blocks are updated. By adaptively encoding appearance and shape into the block configuration, the present invention is able to efficiently and accurately track an object even in the presence of rapid motion that causes large variations in appearance and shape of the object.
摘要翻译：视觉跟踪器以输入图像序列跟踪对象。跟踪模块基于表示对象形状的一组加权块检测对象的位置。跟踪模块然后在检测到的位置处从背景图像中精细地分割对象。基于精细分割，更新加权块集合。通过将外观和形状自适应地编码成块结构，本发明能够即使在存在引起物体的外观和形状的大的变化的快速运动的情况下也能有效且准确地跟踪物体。

4. 发明申请

US20090226037A1 Online Articulate Object Tracking With Appearance And Shape 有权
标题翻译：具有外观和形状的在线铰链对象跟踪
公开(公告)号：US20090226037A1
公开(公告)日：2009-09-10
申请号：US12339029
申请日：2008-12-18
申请人： Ming-Hsuan Yang , Jeffrey Ho
发明人： Ming-Hsuan Yang , Jeffrey Ho
IPC分类号： G06K9/00
CPC分类号： G06K9/3241 , G06K9/00369 , G06K9/4647 , G06T7/248 , G06T2207/10016
摘要： A visual tracker tracks an object in a sequence of input images. A tracking module detects a location of the object based on a set of weighted blocks representing the object's shape. The tracking module then refines a segmentation of the object from the background image at the detected location. Based on the refined segmentation, the set of weighted blocks are updated. By adaptively encoding appearance and shape into the block configuration, the present invention is able to efficiently and accurately track an object even in the presence of rapid motion that causes large variations in appearance and shape of the object.
摘要翻译：视觉跟踪器以输入图像序列跟踪对象。跟踪模块基于表示对象形状的一组加权块检测对象的位置。跟踪模块然后在检测到的位置处从背景图像中精细地分割对象。基于精细分割，更新加权块集合。通过将外观和形状自适应地编码成块结构，本发明能够即使在存在引起物体的外观和形状的大的变化的快速运动的情况下也能有效且准确地跟踪物体。

5. 发明授权

US07103225B2 Clustering appearances of objects under varying illumination conditions 有权
标题翻译：在不同照明条件下物体的聚类外观
公开(公告)号：US07103225B2
公开(公告)日：2006-09-05
申请号：US10703294
申请日：2003-11-06
申请人： Ming-Hsuan Yang , Jeffrey Ho
发明人： Ming-Hsuan Yang , Jeffrey Ho
IPC分类号： G06K9/62 , G06K9/00
CPC分类号： G06K9/4661 , G06K9/00275 , G06K9/6218
摘要： Taking a set of unlabeled images of a collection of objects acquired under different imaging conditions, and decomposing the set into disjoint subsets corresponding to individual objects requires clustering. Appearance-based methods for clustering a set of images of 3-D objects acquired under varying illumination conditions can be based on the concept of illumination cones. A clustering problem is equivalent to finding convex polyhedral cones in the high-dimensional image space. To efficiently determine the conic structures hidden in the image data, the concept of conic affinity can be used which measures the likelihood of a pair of images belonging to the same underlying polyhedral cone. Other algorithms can be based on affinity measure based on image gradient comparisons operating directly on the image gradients by comparing the magnitudes and orientations of the image gradient.
摘要翻译：采用在不同成像条件下获取的对象集合的一组未标记图像，并将该集合分解为与各个对象对应的不相关的子集需要聚类。用于聚类在变化的照明条件下获取的3-D物体的一组图像的基于外观的方法可以基于照明锥的概念。聚类问题相当于在高维图像空间中发现凸多面体锥。为了有效地确定隐藏在图像数据中的圆锥形结构，可以使用锥形亲和度的概念，其测量属于相同底层多面体锥体的一对图像的可能性。其他算法可以基于通过比较图像梯度的幅度和方向基于图像梯度直接操作的图像梯度比较的亲和测量。

6. 发明申请

US20050141769A1 Image clustering with metric, local linear structure, and affine symmetry 有权
标题翻译：具有度量，局部线性结构和仿射对称性的图像聚类
公开(公告)号：US20050141769A1
公开(公告)日：2005-06-30
申请号：US10989967
申请日：2004-11-15
申请人： Jeffrey Ho , Jongwoo Lim , Ming-Hsuan Yang
发明人： Jeffrey Ho , Jongwoo Lim , Ming-Hsuan Yang
IPC分类号： G06K20060101 , G06K9/00 , G06K9/62
CPC分类号： G06K9/6224 , G06K9/6215 , G06K9/6252
摘要： A system and a method are disclosed for clustering images of objects seen from different viewpoints. That is, given an unlabelled set of images of n objects, an unsupervised algorithm groups the images into N disjoint subsets such that each subset only contains images of a single object. The clustering method makes use of a broad geometric framework that exploits the interplay between the geometry of appearance manifolds and the symmetry of the 2D affine group.
摘要翻译：公开了一种系统和方法，用于对从不同视点看到的对象的图像进行聚类。也就是说，给定n个对象的未标记的图像集合，无监督的算法将图像分组为N个不相交的子集，使得每个子集仅包含单个对象的图像。聚类方法利用了广泛的几何框架，利用了外观多样性的几何和2D仿射组的对称性之间的相互作用。

7. 发明授权

US07248738B2 Image clustering with metric, local linear structure, and affine symmetry 有权
标题翻译：具有度量，局部线性结构和仿射对称性的图像聚类
公开(公告)号：US07248738B2
公开(公告)日：2007-07-24
申请号：US10989967
申请日：2004-11-15
申请人： Jeffrey Ho , Jongwoo Lim , Ming-Hsuan Yang
发明人： Jeffrey Ho , Jongwoo Lim , Ming-Hsuan Yang
IPC分类号： G06K9/62
CPC分类号： G06K9/6224 , G06K9/6215 , G06K9/6252
摘要： A system and a method are disclosed for clustering images of objects seen from different viewpoints. That is, given an unlabelled set of images of n objects, an unsupervised algorithm groups the images into N disjoint subsets such that each subset only contains images of a single object. The clustering method makes use of a broad geometric framework that exploits the interplay between the geometry of appearance manifolds and the symmetry of the 2D affine group.
摘要翻译：公开了一种系统和方法，用于对从不同视点看到的对象的图像进行聚类。也就是说，给定n个对象的未标记的图像集合，无监督的算法将图像分组为N个不相交的子集，使得每个子集仅包含单个对象的图像。聚类方法利用了广泛的几何框架，利用了外观多样性的几何和2D仿射组的对称性之间的相互作用。

8. 发明申请

US20130305949A1 Systems and Methods for Delivering a Dosage of a Drug to a Target 审中-公开
标题翻译：将药物用量提供给靶标的系统和方法
公开(公告)号：US20130305949A1
公开(公告)日：2013-11-21
申请号：US13475957
申请日：2012-05-19
申请人： Mark A. Hanchett , Andrew F. Hinz , Jeffrey Ho
发明人： Mark A. Hanchett , Andrew F. Hinz , Jeffrey Ho
IPC分类号： F42B12/54
CPC分类号： F42B12/54 , F41H13/0025
摘要： Methods and apparatus for delivering a dosage of a drug to a target use an electrode that may deliver the drug and/or a current through the target to impede locomotion of the target. Delivery of a dosage may be accomplished by selecting one or more electrodes from a plurality of electrodes to deliver the drug or by metering deliver of the drug from one or more electrodes. Delivery of the current may be accomplished by one or more, preferably two electrodes. The electrodes that deliver the current through the target may also cooperate to deliver the dosage of the drug to the target.
摘要翻译：用于将药物剂量递送到靶的方法和装置使用可以递送药物和/或通过靶的电流以阻止靶的运动的电极。可以通过从多个电极中选择一个或多个电极来递送药物或通过计量药物从一个或多个电极的递送来完成剂量的递送。电流的传递可以由一个或多个，优选两个电极实现。通过目标传递电流的电极也可以配合以将药物的剂量递送到靶。

9. 发明申请

US20070124003A1 METHODS FOR PROVIDING OPTIMAL LIGHT-CO2 COMBINATIONS FOR PLANT PRODUCTION 有权
标题翻译：提供用于植物生产的最佳二氧化碳组合的方法
公开(公告)号：US20070124003A1
公开(公告)日：2007-05-31
申请号：US11668030
申请日：2007-01-29
申请人： Louis Albright , Konstantinos Ferentinos , Ido Seginer , David de Villiers , Jeffrey Ho
发明人： Louis Albright , Konstantinos Ferentinos , Ido Seginer , David de Villiers , Jeffrey Ho
IPC分类号： G05B13/02
CPC分类号： A01G9/18 , A01G7/02 , G05B13/042 , G05B15/02
摘要： Method for optimizing plant production in a cost effective manner, System (100) includes a processor (102) in communication with resource controllers (110, 112) for controlling resources (106, 108) such as, for example, lighting and carbon dioxide. Each resource has a cost that varies temporally or with other factors. The processor implements an algorithm that receives a desired plant production rate and other input, such as operating conditions of the system and environment, and determines amounts of each resource to expend consistent with plant production goals and resource costs.
摘要翻译：用于以成本有效的方式优化工厂生产的方法，系统（100）包括与用于控制例如照明和二氧化碳的资源（106,108）的资源控制器（110,112）通信的处理器（102）。每个资源的成本会随时间变化或其他因素而变化。处理器实现一种接收所需工厂生产率和其他输入的算法，例如系统和环境的操作条件，并确定每个资源的数量与工厂生产目标和资源成本一致。

10. 发明申请

US20050252078A1 Systems and methods for providing optimal light-CO2 combinations for plant production 有权
标题翻译：为工厂生产提供最佳的光二氧化碳组合的系统和方法
公开(公告)号：US20050252078A1
公开(公告)日：2005-11-17
申请号：US10976958
申请日：2004-10-29
申请人： Louis Albright , Konstantinos Ferentinos , Ido Seginer , David de Villiers , Jeffrey Ho
发明人： Louis Albright , Konstantinos Ferentinos , Ido Seginer , David de Villiers , Jeffrey Ho
IPC分类号： A01C20060101 , A01C1/00 , A01G7/02 , A01G9/18 , G05B13/04 , G05B15/02 , G06F17/00
CPC分类号： A01G9/18 , A01G7/02 , G05B13/042 , G05B15/02
摘要： Method and system for optimizing plant production in a cost effective manner. System (100) includes a processor (102) in communication with resource controllers (110, 112) for controlling resources (106, 108) such as, for example, lighting and carbon dioxide. Each resource has a cost that varies temporally or with other factors. The processor implements an algorithm that receives a desired plant production rate and other input, such as operating conditions of the system and environment, and determines amounts of each resource to expend consistent with plant production goals and resource costs.
摘要翻译：以成本有效的方式优化工厂生产的方法和系统。系统（100）包括与用于控制诸如照明和二氧化碳的资源（106,108）的资源控制器（110,112）通信的处理器（102）。每个资源的成本会随时间变化或其他因素而变化。处理器实现一种接收所需工厂生产率和其他输入的算法，例如系统和环境的操作条件，并确定每个资源的数量与工厂生产目标和资源成本一致。

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