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. 发明申请

US20090153661A1 METHOD FOR BUILDING AND EXTRACTING ENTITY NETWORKS FROM VIDEO 有权
标题翻译：从视频建立和提取实体网络的方法
公开(公告)号：US20090153661A1
公开(公告)日：2009-06-18
申请号：US12271173
申请日：2008-11-14
申请人： Hui Cheng , Jiangjian Xiao , Harpreet Sawhney
发明人： Hui Cheng , Jiangjian Xiao , Harpreet Sawhney
IPC分类号： H04N7/18
CPC分类号： G06T7/20 , G06K9/00771 , G06K2009/3291
摘要： A computer implemented method for deriving an attribute entity network (AEN) from video data is disclosed, comprising the steps of: extracting at least two entities from the video data; tracking the trajectories of the at least two entities to form at least two tracks; deriving at least one association between at least two entities by detecting at least one event involving the at least two entities, said detecting of at least one event being based on detecting at least one spatio-temporal motion correlation between the at least two entities; and constructing the AEN by creating a graph wherein the at least two objects form at least two nodes and the at least one association forms a link between the at least two nodes.
摘要翻译：公开了一种用于从视频数据中导出属性实体网络（AEN）的计算机实现方法，包括以下步骤：从视频数据中提取至少两个实体; 跟踪所述至少两个实体的轨迹以形成至少两个轨道; 通过检测涉及所述至少两个实体的至少一个事件来导出至少两个实体之间的至少一个关联，所述至少一个事件的检测是基于检测所述至少两个实体之间的至少一个时空运动相关性; 以及通过创建图形来构建所述AEN，其中所述至少两个对象形成至少两个节点，并且所述至少一个关联形成所述至少两个节点之间的链接。

2. 发明授权

US08995717B2 Method for building and extracting entity networks from video 有权
标题翻译：从视频建立和提取实体网络的方法
公开(公告)号：US08995717B2
公开(公告)日：2015-03-31
申请号：US13597698
申请日：2012-08-29
申请人： Hui Cheng , Jiangjian Xiao , Harpreet Sawhney
发明人： Hui Cheng , Jiangjian Xiao , Harpreet Sawhney
IPC分类号： G06K9/46 , G06T7/20 , G06K9/00 , G06K9/32
CPC分类号： G06T7/20 , G06K9/00771 , G06K2009/3291
摘要： A computer implemented method for deriving an attribute entity network (AEN) from video data is disclosed, comprising the steps of: extracting at least two entities from the video data; tracking the trajectories of the at least two entities to form at least two tracks; deriving at least one association between at least two entities by detecting at least one event involving the at least two entities, said detecting of at least one event being based on detecting at least one spatio-temporal motion correlation between the at least two entities; and constructing the AEN by creating a graph wherein the at least two objects form at least two nodes and the at least one association forms a link between the at least two nodes.
摘要翻译：公开了一种用于从视频数据中导出属性实体网络（AEN）的计算机实现方法，包括以下步骤：从视频数据中提取至少两个实体; 跟踪所述至少两个实体的轨迹以形成至少两个轨道; 通过检测涉及所述至少两个实体的至少一个事件来导出至少两个实体之间的至少一个关联，所述至少一个事件的检测是基于检测所述至少两个实体之间的至少一个时空运动相关性; 以及通过创建图形来构建所述AEN，其中所述至少两个对象形成至少两个节点，并且所述至少一个关联形成所述至少两个节点之间的链接。

3. 发明授权

US08294763B2 Method for building and extracting entity networks from video 有权
标题翻译：从视频建立和提取实体网络的方法
公开(公告)号：US08294763B2
公开(公告)日：2012-10-23
申请号：US12271173
申请日：2008-11-14
申请人： Hui Cheng , Jiangjian Xiao , Harpreet Sawhney
发明人： Hui Cheng , Jiangjian Xiao , Harpreet Sawhney
IPC分类号： H04N7/18
CPC分类号： G06T7/20 , G06K9/00771 , G06K2009/3291
摘要： A computer implemented method for deriving an attribute entity network (AEN) from video data is disclosed, comprising the steps of extracting at least two entities from the video data, tracking the trajectories of the at least two entities to form at least two tracks, deriving at least one association between at least two entities by detecting at least one event involving the at least two entities, where the detecting of at least one event is based on detecting at least one spatiotemporal motion correlation between the at least two entities, and constructing the AEN by creating a graph wherein the at least two objects form at least two nodes and the at least one association forms a link between the at least two nodes.
摘要翻译：公开了一种用于从视频数据导出属性实体网络（AEN）的计算机实现方法，包括以下步骤：从视频数据中提取至少两个实体，跟踪至少两个实体的轨迹以形成至少两个轨道，导出通过检测涉及所述至少两个实体的至少一个事件，在至少两个实体之间的至少一个关联，其中所述至少一个事件的检测是基于检测所述至少两个实体之间的至少一个时空运动相关性，并且构建 AEN，其中所述至少两个对象形成至少两个节点并且所述至少一个关联形成所述至少两个节点之间的链接。

4. 发明授权

US07760911B2 Method and system for segment-based optical flow estimation 失效
标题翻译：基于段的光流估计方法和系统
公开(公告)号：US07760911B2
公开(公告)日：2010-07-20
申请号：US11521109
申请日：2006-09-14
申请人： Jiangjian Xiao , Hui Cheng
发明人： Jiangjian Xiao , Hui Cheng
IPC分类号： G06K9/00 , H04N5/30
CPC分类号： H04N19/577 , G06T7/207 , G06T7/215 , H04N19/186 , H04N19/537 , H04N19/543 , H04N19/553 , H04N19/61
摘要： The methods and systems of the present invention enable the estimation of optical flow by performing color segmentation and adaptive bilateral filtering to regularize the flow field to achieve a more accurate flow field estimation. After creating pyramid models for two input image frames, color segmentation is performed. Next, starting from a top level of the pyramid, additive flow vectors are iteratively estimated between the reference frames by a process including occlusion detection, wherein the symmetric property of backward and forward flow is enforced for the non-occluded regions. Next, a final estimated optical flow field is generated by expanding the current pyramid level to the next lower level and the repeating the process until the lowest level is reached. This approach not only generates efficient spatial-coherent flow fields, but also accurately locates flow discontinuities along the motion boundaries.
摘要翻译：本发明的方法和系统能够通过执行颜色分割和自适应双边滤波来估计光流，以使流场正规化以实现更准确的流场估计。在为两个输入图像帧创建金字塔模型之后，执行颜色分割。接下来，从金字塔的顶级开始，通过包括遮挡检测的处理在参考帧之间迭代地估计加性流矢量，其中对于未遮挡区域强制执行向后和向前流的对称属性。接下来，通过将当前金字塔等级扩展到下一个较低级别并重复该过程直到达到最低级别来生成最终估计的光流场。这种方法不仅产生有效的空间相干流场，而且还准确地定位沿着运动边界的流动不连续性。

5. 发明申请

US20070092122A1 Method and system for segment-based optical flow estimation 失效
标题翻译：基于段的光流估计方法和系统
公开(公告)号：US20070092122A1
公开(公告)日：2007-04-26
申请号：US11521109
申请日：2006-09-14
申请人： Jiangjian Xiao , Hui Cheng
发明人： Jiangjian Xiao , Hui Cheng
IPC分类号： G06K9/00
CPC分类号： H04N19/577 , G06T7/207 , G06T7/215 , H04N19/186 , H04N19/537 , H04N19/543 , H04N19/553 , H04N19/61
摘要： The methods and systems of the present invention enable the estimation of optical flow by performing color segmentation and adaptive bilateral filtering to regularize the flow field to achieve a more accurate flow field estimation. After creating pyramid models for two input image frames, color segmentation is performed. Next, starting from a top level of the pyramid, additive flow vectors are iteratively estimated between the reference frames by a process including occlusion detection, wherein the symmetric property of backward and forward flow is enforced for the non-occluded regions. Next, a final estimated optical flow field is generated by expanding the current pyramid level to the next lower level and the repeating the process until the lowest level is reached. This approach not only generates efficient spatial-coherent flow fields, but also accurately locates flow discontinuities along the motion boundaries.
摘要翻译：本发明的方法和系统能够通过执行颜色分割和自适应双边滤波来估计光流，以使流场正规化以实现更准确的流场估计。在为两个输入图像帧创建金字塔模型之后，执行颜色分割。接下来，从金字塔的顶级开始，通过包括遮挡检测的处理在参考帧之间迭代地估计加性流矢量，其中对于未遮挡区域强制执行向后和向前流的对称属性。接下来，通过将当前金字塔等级扩展到下一个较低级别并重复该过程直到达到最低级别来生成最终估计的光流场。这种方法不仅产生有效的空间相干流场，而且还准确地定位沿着运动边界的流动不连续性。

6. 发明授权

US08233704B2 Exemplar-based heterogeneous compositional method for object classification 有权
标题翻译：用于对象分类的基于示例的异构组合方法
公开(公告)号：US08233704B2
公开(公告)日：2012-07-31
申请号：US12136138
申请日：2008-06-10
申请人： Feng Han , Hui Cheng , Jiangjian Xiao , Harpreet Singh Sawhney
发明人： Feng Han , Hui Cheng , Jiangjian Xiao , Harpreet Singh Sawhney
IPC分类号： G06K9/62 , G06E1/00 , G06E3/00 , G06F15/18 , G06G7/00
CPC分类号： G06K9/3241 , G06K9/6256 , G06K9/6292
摘要： A method for automatically generating a strong classifier for determining whether at least one object is detected in at least one image is disclosed, comprising the steps of: (a) receiving a data set of training images having positive images; (b) randomly selecting a subset of positive images from the training images to create a set of candidate exemplars, wherein said positive images include at least one object of the same type as the object to be detected; (c) training a weak classifier based on at least one of the candidate exemplars, said training being based on at least one comparison of a plurality of heterogeneous compositional features located in the at least one image and corresponding heterogeneous compositional features in the one of set of candidate exemplars; (d) repeating steps (c) for each of the remaining candidate exemplars; and (e) combining the individual classifiers into a strong classifier, wherein the strong classifier is configured to determine the presence or absence in an image of the object to be detected.
摘要翻译：公开了一种用于自动生成强分类器以确定在至少一个图像中是否检测到至少一个对象的方法，包括以下步骤：（a）接收具有正图像的训练图像的数据集; （b）从所述训练图像中随机选择正图像的子集以创建一组候选样本，其中所述正图像包括与所述待检测对象相同类型的至少一个对象; （c）基于所述候选样本中的至少一个来训练弱分类器，所述训练基于位于所述至少一个图像中的多个异质成分特征和所述一个图像中的一个中的对应的异质组成特征的至少一个比较候选人样本（d）为每个其余的候选样本重复步骤（c）; 以及（e）将各个分类器组合成强分类器，其中强分类器被配置为确定待检测对象的图像中的存在或不存在。

7. 发明申请

US20080310737A1 EXEMPLAR-BASED HETEROGENEOUS COMPOSITIONAL METHOD FOR OBJECT CLASSIFICATION 有权
标题翻译：用于对象分类的基于EXEMPLAR的异构组合方法
公开(公告)号：US20080310737A1
公开(公告)日：2008-12-18
申请号：US12136138
申请日：2008-06-10
申请人： Feng Han , Hui Cheng , Jiangjian Xiao , Harpreet Singh Sawhney
发明人： Feng Han , Hui Cheng , Jiangjian Xiao , Harpreet Singh Sawhney
IPC分类号： G06K9/62
CPC分类号： G06K9/3241 , G06K9/6256 , G06K9/6292
摘要： A method for automatically generating a strong classifier for determining whether at least one object is detected in at least one image is disclosed, comprising the steps of: (a) receiving a data set of training images having positive images; (b) randomly selecting a subset of positive images from the training images to create a set of candidate exemplars, wherein said positive images include at least one object of the same type as the object to be detected; (c) training a weak classifier based on at least one of the candidate exemplars, said training being based on at least one comparison of a plurality of heterogeneous compositional features located in the at least one image and corresponding heterogeneous compositional features in the one of set of candidate exemplars; (d) repeating steps (c) for each of the remaining candidate exemplars; and (e) combining the individual classifiers into a strong classifier, wherein the strong classifier is configured to determine the presence or absence in an image of the object to be detected.
摘要翻译：公开了一种用于自动生成强分类器以确定在至少一个图像中是否检测到至少一个对象的方法，包括以下步骤：（a）接收具有正图像的训练图像的数据集; （b）从所述训练图像中随机选择正图像的子集以创建一组候选样本，其中所述正图像包括与所述待检测对象相同类型的至少一个对象; （c）基于所述候选样本中的至少一个训练弱分类器，所述训练基于位于所述至少一个图像中的多个异质成分特征和所述一个图像中的一个中的对应的异质组成特征的至少一个比较候选人样本（d）为每个其余的候选样本重复步骤（c）; 以及（e）将各个分类器组合成强分类器，其中强分类器被配置为确定待检测对象的图像中的存在或不存在。

8. 发明授权

US08712096B2 Method and apparatus for detecting and tracking vehicles 有权
标题翻译：用于车辆检测和跟踪的方法和装置
公开(公告)号：US08712096B2
公开(公告)日：2014-04-29
申请号：US13041092
申请日：2011-03-04
申请人： Jiangjian Xiao , Harpreet Singh Sawhney , Hui Cheng
发明人： Jiangjian Xiao , Harpreet Singh Sawhney , Hui Cheng
IPC分类号： G06K9/00
CPC分类号： G06K9/6296 , G06K9/00624 , G06T7/254
摘要： The present invention relates to a method and apparatus for detecting and tracking vehicles. One embodiment of a system for detecting and tracking an object (e.g., vehicle) in a field of view includes a moving object indication stage for detecting a candidate object in a series of input video frames depicting the field of view and a track association stage that uses a joint probabilistic graph matching framework to associate an existing track with the candidate object.
摘要翻译：本发明涉及车辆检测跟踪方法和装置。用于在视野中检测和跟踪对象（例如，车辆）的系统的一个实施例包括用于检测描绘视场的一系列输入视频帧中的候选对象的移动对象指示级和跟踪关联级，使用联合概率图匹配框架将现有轨道与候选对象相关联。

9. 发明授权

US08634638B2 Real-time action detection and classification 有权
标题翻译：实时动作检测与分类
公开(公告)号：US08634638B2
公开(公告)日：2014-01-21
申请号：US12488911
申请日：2009-06-22
申请人： Feng Han , Hui Cheng , Jiangjian Xiao , Harpreet Singh Sawhney , Sang-Hack Jung , Rakesh Kumar , Yanlin Guo
发明人： Feng Han , Hui Cheng , Jiangjian Xiao , Harpreet Singh Sawhney , Sang-Hack Jung , Rakesh Kumar , Yanlin Guo
IPC分类号： G06K9/62
CPC分类号： G06K9/00342
摘要： The present invention relates to a method and system for creating a strong classifier based on motion patterns wherein the strong classifier may be used to determine an action being performed by a body in motion. When creating the strong classifier, action classification is performed by measuring similarities between features within motion patterns. Embodiments of the present invention may utilize candidate part-based action sets and training samples to train one or more weak classifiers that are then used to create a strong classifier.
摘要翻译：本发明涉及一种用于基于运动模式创建强分类器的方法和系统，其中强分类器可用于确定由运动中的身体执行的动作。当创建强分类器时，通过测量运动模式中的特征之间的相似度来执行动作分类。本发明的实施例可以利用基于候选部分的动作集和训练样本来训练一个或多个弱分类器，然后将其用于创建强分类器。

10. 发明申请

US20090316983A1 Real-Time Action Detection and Classification 有权
标题翻译：实时行动检测与分类
公开(公告)号：US20090316983A1
公开(公告)日：2009-12-24
申请号：US12488911
申请日：2009-06-22
申请人： Feng Han , Hui Cheng , Jiangjian Xiao , Harpreet Singh Sawhney , Sang-Hack Jung , Rakesh Kumar , Yanlin Guo
发明人： Feng Han , Hui Cheng , Jiangjian Xiao , Harpreet Singh Sawhney , Sang-Hack Jung , Rakesh Kumar , Yanlin Guo
IPC分类号： G06K9/62
CPC分类号： G06K9/00342
摘要： The present invention relates to a method and system for creating a strong classifier based on motion patterns wherein the strong classifier may be used to determine an action being performed by a body in motion. When creating the strong classifier, action classification is performed by measuring similarities between features within motion patterns. Embodiments of the present invention may utilize candidate part-based action sets and training samples to train one or more weak classifiers that are then used to create a strong classifier.
摘要翻译：本发明涉及一种用于基于运动模式创建强分类器的方法和系统，其中强分类器可用于确定由运动中的身体执行的动作。当创建强分类器时，通过测量运动模式中的特征之间的相似度来执行动作分类。本发明的实施例可以利用基于候选部分的动作集和训练样本来训练一个或多个弱分类器，然后将其用于创建强分类器。

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