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

US08774499B2 Embedded optical flow features 失效
标题翻译：嵌入式光流特征
公开(公告)号：US08774499B2
公开(公告)日：2014-07-08
申请号：US13405986
申请日：2012-02-27
申请人： Jinjun Wang , Jing Xiao
发明人： Jinjun Wang , Jing Xiao
IPC分类号： G06K9/00
CPC分类号： G06K9/00765 , G06K9/00335 , G06K9/6297
摘要： Aspects of the present invention include systems and methods for generating an optical flow-based feature. In embodiments, to extract an optical flow feature, the optical flow at sparse interest points is obtained, and Locality-constrained Linear Coding (LLC) is applied to the sparse interest points to embed each flow into a higher-dimensional code. In embodiments, for an image frame, the multiple codes are combined together using a weighted pooling that is related to the distribution of the optical flows in the image frame. In embodiments, the feature may be used in training models to detect actions, in trained models for action detection, or both.
摘要翻译：本发明的方面包括用于产生基于光流的特征的系统和方法。在实施例中，为了提取光流特征，获得稀疏兴趣点处的光流，并将局部约束线性编码（LLC）应用于稀疏兴趣点以将每个流嵌入更高维码中。在实施例中，对于图像帧，使用与图像帧中的光流的分布相关的加权池来将多个代码组合在一起。在实施例中，可以在训练模型中使用该特征以在用于动作检测的训练模型中或两者中检测动作。

2. 发明授权

US09436780B2 Constructing incremental tree model for vein image recognition and authentication 有权
标题翻译：构建静态图像识别和认证的增量树模型
公开(公告)号：US09436780B2
公开(公告)日：2016-09-06
申请号：US13545820
申请日：2012-07-10
申请人： Jinjun Wang , Jing Xiao
发明人： Jinjun Wang , Jing Xiao
IPC分类号： G06F17/30
CPC分类号： G06F17/30961 , G06F17/30327
摘要： An indexed hierarchical tree search structure implements incremental tree modification to add new registrants to the tree without requiring reconstruction of the tree. Only data within a leaf node that receives new data is used in the incremental tree modification. Consequently, the original data set used in the creation of the hierarchical tree may be deleted after construction of the tree.
摘要翻译：索引的分层树搜索结构实现增量树修改，以将新的注册者添加到树中，而不需要重构树。在增量树修改中仅使用接收新数据的叶节点内的数据。因此，在构建树之后，可以删除在创建层次树中使用的原始数据集。

3. 发明申请

US20140025607A1 Confidence Based Vein Image Recognition and Authentication 有权
标题翻译：基于信度的静脉图像识别和认证
公开(公告)号：US20140025607A1
公开(公告)日：2014-01-23
申请号：US13552422
申请日：2012-07-18
申请人： Jinjun Wang , Jing Xiao
发明人： Jinjun Wang , Jing Xiao
IPC分类号： G06F15/18 , G06F17/30
CPC分类号： G06F17/30961 , G06F17/30247 , G06F17/30979
摘要： An indexed hierarchical tree search structure converts each registration sample into an equivalent registration model based on the clustering of its registration item descriptors in the leaf nodes of the hierarchical tree. Query item descriptors from a query sample from someone wanting to be recognized are distributed into the hierarchical tree. A query model is defined based on the clustering of query item descriptors at the leaf nodes, and registration and verification are made based on comparison of the query model and the registration models.
摘要翻译：索引分层树搜索结构基于分层树叶节点中其注册项描述符的聚类将每个注册样本转换为等效的注册模型。从想要被识别的人的查询样本中查询项目描述符被分发到分层树中。基于叶节点上查询项描述符的聚类定义查询模型，并根据查询模型与注册模型的比较进行注册和验证。

4. 发明申请

US20140019489A1 Constructing Incremental Tree Model for Vein Image Recognition and Authentication 有权
标题翻译：构建静脉图像识别和认证的增量树模型
公开(公告)号：US20140019489A1
公开(公告)日：2014-01-16
申请号：US13545820
申请日：2012-07-10
申请人： Jinjun Wang , Jing Xiao
发明人： Jinjun Wang , Jing Xiao
IPC分类号： G06F17/30
CPC分类号： G06F17/30961 , G06F17/30327
摘要： An indexed hierarchical tree search structure implements incremental tree modification to add new registrants to the tree without requiring reconstruction of the tree. Only data within a leaf node that receives new data is used in the incremental tree modification. Consequently, the original data set used in the creation of the hierarchical tree may be deleted after construction of the tree.
摘要翻译：索引的分层树搜索结构实现增量树修改，以将新的注册者添加到树中，而不需要重构树。在增量树修改中仅使用接收新数据的叶节点内的数据。因此，在构建树之后，可以删除在创建层次树中使用的原始数据集。

5. 发明授权

US08917907B2 Continuous linear dynamic systems 有权
标题翻译：连续线性动态系统
公开(公告)号：US08917907B2
公开(公告)日：2014-12-23
申请号：US13406011
申请日：2012-02-27
申请人： Jinjun Wang , Jing Xiao
发明人： Jinjun Wang , Jing Xiao
IPC分类号： G06K9/00 , G06K9/62
CPC分类号： G06K9/00765 , G06K9/00335 , G06K9/6297
摘要： Aspects of the present invention include systems and methods for segmentation and recognition of action primitives. In embodiments, a framework, referred to as the Continuous Linear Dynamic System (CLDS), comprises two sets of Linear Dynamic System (LDS) models, one to model the dynamics of individual primitive actions and the other to model the transitions between actions. In embodiments, the inference process estimates the best decomposition of the whole sequence into continuous alternating between the two set of models, using an approximate Viterbi algorithm. In this way, both action type and action boundary may be accurately recognized.
摘要翻译：本发明的方面包括用于分割和识别动作原语的系统和方法。在实施例中，被称为连续线性动态系统（CLDS）的框架包括两组线性动态系统（LDS）模型，其中一个模型用于对各个原始动作的动力学进行建模，另一组模型对动作之间的转换进行建模。在实施例中，推理过程使用近似维特比算法来估计整个序列的最佳分解到两组模型之间的连续交替。以这种方式，可以准确地识别动作类型和动作边界。

6. 发明申请

US20120219186A1 Continuous Linear Dynamic Systems 有权
标题翻译：连续线性动态系统
公开(公告)号：US20120219186A1
公开(公告)日：2012-08-30
申请号：US13406011
申请日：2012-02-27
申请人： Jinjun Wang , Jing Xiao
发明人： Jinjun Wang , Jing Xiao
IPC分类号： G06K9/62
CPC分类号： G06K9/00765 , G06K9/00335 , G06K9/6297
摘要： Aspects of the present invention include systems and methods for segmentation and recognition of action primitives. In embodiments, a framework, referred to as the Continuous Linear Dynamic System (CLDS), comprises two sets of Linear Dynamic System (LDS) models, one to model the dynamics of individual primitive actions and the other to model the transitions between actions. In embodiments, the inference process estimates the best decomposition of the whole sequence into continuous alternating between the two set of models, using an approximate Viterbi algorithm. In this way, both action type and action boundary may be accurately recognized.
摘要翻译：本发明的方面包括用于分割和识别动作原语的系统和方法。在实施例中，被称为连续线性动态系统（CLDS）的框架包括两组线性动态系统（LDS）模型，其中一个模型用于对各个原始动作的动力学进行建模，另一组模型对动作之间的转换进行建模。在实施例中，推理过程使用近似维特比算法来估计整个序列的最佳分解到两组模型之间的连续交替。以这种方式，可以准确地识别动作类型和动作边界。

7. 发明授权

US08914313B2 Confidence based vein image recognition and authentication 有权
标题翻译：基于置信度的静脉图像识别和认证
公开(公告)号：US08914313B2
公开(公告)日：2014-12-16
申请号：US13552422
申请日：2012-07-18
申请人： Jinjun Wang , Jing Xiao
发明人： Jinjun Wang , Jing Xiao
IPC分类号： G06F15/18
CPC分类号： G06F17/30961 , G06F17/30247 , G06F17/30979
摘要： An indexed hierarchical tree search structure converts each registration sample into an equivalent registration model based on the clustering of its registration item descriptors in the leaf nodes of the hierarchical tree. Query item descriptors from a query sample from someone wanting to be recognized are distributed into the hierarchical tree. A query model is defined based on the clustering of query item descriptors at the leaf nodes, and registration and verification are made based on comparison of the query model and the registration models.
摘要翻译：索引分层树搜索结构基于分层树叶节点中其注册项描述符的聚类将每个注册样本转换为等效的注册模型。从想要被识别的人的查询样本中查询项目描述符被分发到分层树中。基于叶节点上查询项描述符的聚类定义查询模型，并根据查询模型与注册模型的比较进行注册和验证。

8. 发明申请

US20130132316A1 Substructure and Boundary Modeling for Continuous Action Recognition 有权
标题翻译：连续动作识别的子结构和边界建模
公开(公告)号：US20130132316A1
公开(公告)日：2013-05-23
申请号：US13491108
申请日：2012-06-07
申请人： Jinjun Wang , Zhaowen Wang , Jing Xiao
发明人： Jinjun Wang , Zhaowen Wang , Jing Xiao
IPC分类号： G06N5/02
CPC分类号： G06N99/005
摘要： Embodiments of the present invention include systems and methods for improved state space modeling (SSM) comprising two added layers to model the substructure transition dynamics and action duration distribution. In embodiments, the first layer represents a substructure transition model that encodes the sparse and global temporal transition probability. In embodiments, the second layer models the action boundary characteristics by injecting discriminative information into a logistic duration model such that transition boundaries between successive actions can be located more accurately; thus, the second layer exploits discriminative information to discover action boundaries adaptively.
摘要翻译：本发明的实施例包括用于改进状态空间建模（SSM）的系统和方法，所述状态空间建模（SSM）包括两个附加的层，以模拟子结构转变动力学和动作持续时间分布。在实施例中，第一层表示编码稀疏和全局时间转移概率的子结构转换模型。在实施例中，第二层通过将识别信息注入逻辑持续时间模型来建模动作边界特征，使得可以更准确地定位连续动作之间的转移边界; 因此，第二层利用辨别信息自动发现行动界限。

9. 发明申请

US20120219213A1 Embedded Optical Flow Features 失效
标题翻译：嵌入式光流特性
公开(公告)号：US20120219213A1
公开(公告)日：2012-08-30
申请号：US13405986
申请日：2012-02-27
申请人： Jinjun Wang , Jing Xiao
发明人： Jinjun Wang , Jing Xiao
IPC分类号： G06K9/48 , G06K9/62
CPC分类号： G06K9/00765 , G06K9/00335 , G06K9/6297
摘要： Aspects of the present invention include systems and methods for generating an optical flow-based feature. In embodiments, to extract an optical flow feature, the optical flow at sparse interest points is obtained, and Locality-constrained Linear Coding (LLC) is applied to the sparse interest points to embed each flow into a higher-dimensional code. In embodiments, for an image frame, the multiple codes are combined together using a weighted pooling that is related to the distribution of the optical flows in the image frame. In embodiments, the feature may be used in training models to detect actions, in trained models for action detection, or both.
摘要翻译：本发明的方面包括用于产生基于光流的特征的系统和方法。在实施例中，为了提取光流特征，获得稀疏兴趣点处的光流，并将局部约束线性编码（LLC）应用于稀疏兴趣点以将每个流嵌入更高维码中。在实施例中，对于图像帧，使用与图像帧中的光流的分布相关的加权池来将多个代码组合在一起。在实施例中，可以在训练模型中使用该特征以在用于动作检测的训练模型中或两者中检测动作。

10. 发明授权

US08892491B2 Substructure and boundary modeling for continuous action recognition 有权
标题翻译：连续动作识别的子结构和边界建模
公开(公告)号：US08892491B2
公开(公告)日：2014-11-18
申请号：US13491108
申请日：2012-06-07
申请人： Jinjun Wang , Zhaowen Wang , Jing Xiao
发明人： Jinjun Wang , Zhaowen Wang , Jing Xiao
IPC分类号： G06N5/02 , G06T7/20 , G06N99/00
CPC分类号： G06N99/005
摘要： Embodiments of the present invention include systems and methods for improved state space modeling (SSM) comprising two added layers to model the substructure transition dynamics and action duration distribution. In embodiments, the first layer represents a substructure transition model that encodes the sparse and global temporal transition probability. In embodiments, the second layer models the action boundary characteristics by injecting discriminative information into a logistic duration model such that transition boundaries between successive actions can be located more accurately; thus, the second layer exploits discriminative information to discover action boundaries adaptively.
摘要翻译：本发明的实施例包括用于改进状态空间建模（SSM）的系统和方法，所述状态空间建模（SSM）包括两个附加层以对子结构转变动力学和动作持续时间分布进行建模。在实施例中，第一层表示编码稀疏和全局时间转移概率的子结构转换模型。在实施例中，第二层通过将识别信息注入逻辑持续时间模型来建模动作边界特征，使得可以更准确地定位连续动作之间的转移边界; 因此，第二层利用辨别信息自动发现行动界限。

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