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

US08538200B2 Systems and methods for resolution-invariant image representation 有权
标题翻译：用于分辨率不变图像表示的系统和方法
公开(公告)号：US08538200B2
公开(公告)日：2013-09-17
申请号：US12469098
申请日：2009-05-20
申请人： Jinjun Wang , Shenghuo Zhu , Yihong Gong
发明人： Jinjun Wang , Shenghuo Zhu , Yihong Gong
IPC分类号： G06K9/32
CPC分类号： G06T3/4053
摘要： Systems and methods are disclosed for generating super resolution images by building a set of multi-resolution bases from one or more training images; estimating a sparse resolution-invariant representation of an image, and reconstructing one or more missing patches at any resolution level.
摘要翻译：公开了用于通过从一个或多个训练图像构建一组多分辨率基底来产生超分辨率图像的系统和方法; 估计图像的稀疏分辨率不变表示，以及在任何分辨率级别重建一个或多个丢失的斑点。

2. 发明授权

US08345962B2 Transfer learning methods and systems for feed-forward visual recognition systems 有权
标题翻译：转移前馈视觉识别系统的学习方法和系统
公开(公告)号：US08345962B2
公开(公告)日：2013-01-01
申请号：US12277504
申请日：2008-11-25
申请人： Kai Yu , Wei Xu , Yihong Gong
发明人： Kai Yu , Wei Xu , Yihong Gong
IPC分类号： G06K9/62
CPC分类号： G06K9/6256 , G06N3/08
摘要： A method and system for training a neural network of a visual recognition computer system, extracts at least one feature of an image or video frame with a feature extractor; approximates the at least one feature of the image or video frame with an auxiliary output provided in the neural network; and measures a feature difference between the extracted at least one feature of the image or video frame and the approximated at least one feature of the image or video frame with an auxiliary error calculator. A joint learner of the method and system adjusts at least one parameter of the neural network to minimize the measured feature difference.
摘要翻译：一种用于训练视觉识别计算机系统的神经网络的方法和系统，使用特征提取器提取图像或视频帧的至少一个特征; 使用在神经网络中提供的辅助输出近似图像或视频帧的至少一个特征; 并且利用辅助误差计算器测量提取的图像或视频帧的至少一个特征与图像或视频帧的近似的至少一个特征之间的特征差异。该方法和系统的联合学习者调整神经网络的至少一个参数以最小化测量的特征差异。

3. 发明授权

US07860813B2 Monitoring driving safety using semi-supervised sequential learning 有权
标题翻译：使用半监督顺序学习监测驾驶安全
公开(公告)号：US07860813B2
公开(公告)日：2010-12-28
申请号：US12184221
申请日：2008-07-31
申请人： Jinjun Wang , Shenghuo Zhu , Yihong Gong
发明人： Jinjun Wang , Shenghuo Zhu , Yihong Gong
IPC分类号： G06F15/18
CPC分类号： G09B9/052
摘要： A computer-implemented method and system for predicting operation risks of a vehicle. The method and system obtains a training data stream of vehicular dynamic parameters and logging crash time instances; partitions the data stream into units representing dimension vectors, labels the units that overlap the crash time instances as most dangerous; labels the units, which are furthest from the units that are labeled as most dangerous, as most safe; propagates the most dangerous and the most safe labeling information of the labeled units to units which are not labeled; estimates parameters of a danger-level function using the labeled and unlabeled units; and applies the danger-level function to an actual data stream of vehicular dynamic parameters to predict the operation risks of the vehicle.
摘要翻译：一种用于预测车辆操作风险的计算机实现的方法和系统。该方法和系统获取车辆动态参数和日志崩溃时间实例的训练数据流; 将数据流划分为表示维度向量的单位，将与崩溃时间实例重叠的单位标记为最危险的; 标记与最危险的单位最远的单位，最安全; 将标记单位的最危险和最安全的标签信息传播到未标记的单位; 使用标记和未标记的单位估计危险度函数的参数; 并将危险度函数应用于车辆动态参数的实际数据流，以预测车辆的运行风险。

4. 发明申请

US20100185578A1 SOCIAL NETWORK ANALYSIS WITH PRIOR KNOWLEDGE AND NON-NEGATIVE TENSOR FACTORIZATION 有权
标题翻译：具有先前知识和非负性传感器参数的社会网络分析
公开(公告)号：US20100185578A1
公开(公告)日：2010-07-22
申请号：US12469043
申请日：2009-05-20
申请人： Yun Chi , Shenghuo Zhu , Koji Hino , Yihong Gong
发明人： Yun Chi , Shenghuo Zhu , Koji Hino , Yihong Gong
IPC分类号： G06N7/02 , G06N5/02 , G06F17/10
CPC分类号： G06Q30/02
摘要： Systems and methods are disclosed to analyze a social network by generating a data tensor from social networking data; applying a non-negative tensor factorization (NTF) with user prior knowledge and preferences to generate a core tensor and facet matrices; and rendering information to social networking users based on the core tensor and facet matrices.
摘要翻译：公开了通过从社交网络数据生成数据张量来分析社交网络的系统和方法; 应用具有用户先验知识和偏好的非负张量因子分解（NTF）来生成核心张量和小平面矩阵; 并基于核心张量和面矩阵将信息呈现给社交网络用户。

5. 发明申请

US20100049675A1 Recovery of 3D Human Pose by Jointly Learning Metrics and Mixtures of Experts 有权
标题翻译：通过联合学习指标和专家组合恢复3D人体姿势
公开(公告)号：US20100049675A1
公开(公告)日：2010-02-25
申请号：US12277284
申请日：2008-11-24
申请人： Huazhong Ning , Wei Xu , Yihong Gong
发明人： Huazhong Ning , Wei Xu , Yihong Gong
IPC分类号： G06F15/18 , G06N5/04
CPC分类号： G06K9/00342 , G06K9/6212
摘要： Systems and methods are disclosed for determining human pose by generating an Appearance and Position Context (APC) local descriptor that achieves selectivity and invariance while requiring no background subtraction; jointly learning visual words and pose regressors in a supervised manner; and estimating the human pose.
摘要翻译：公开了用于通过生成实现选择性和不变性而不需要背景减除的外观和位置上下文（APC）局部描述符来确定人类姿势的系统和方法; 以监督的方式联合学习视觉词和姿态回归; 并估计人的姿势。

6. 发明授权

US07607083B2 Test summarization using relevance measures and latent semantic analysis 有权
标题翻译：使用相关性测度和潜在语义分析测试摘要
公开(公告)号：US07607083B2
公开(公告)日：2009-10-20
申请号：US09817591
申请日：2001-03-26
申请人： Yihong Gong , Xin Liu
发明人： Yihong Gong , Xin Liu
IPC分类号： G06F17/00
CPC分类号： G06F17/27 , G06F19/00 , G06Q10/02 , G06Q40/08 , G06Q50/24 , Y10S707/99942 , Y10S707/99943
摘要： Text summarizers using relevance measurement technologies and latent semantic analysis techniques provide accurate and useful summarization of the contents of text documents. Generic text summaries may be produced by ranking and extracting sentences from original documents; broad coverage of document content and decreased redundancy may simultaneously be achieved by constructing summaries from sentences that are highly ranked and different from each other. In one embodiment, conventional Information Retrieval (IR) technologies may be applied in a unique way to perform the summarization; relevance measurement, sentence selection, and term elimination may be repeated in successive iterations. In another embodiment, a singular value decomposition technique may be applied to a terms-by-sentences matrix such that all the sentences from the document may be projected into the singular vector space; a text summarizer may then select sentences having the largest index values with the most important singular vectors as part of the text summary.
摘要翻译：使用相关性测量技术和潜在语义分析技术的文本摘要提供准确有用的摘要文本文档的内容。一般文本摘要可以通过从原始文件中排序和提取句子来生成; 文档内容的广泛覆盖和减少的冗余可以通过构造高分级和不同的句子的摘要来实现。在一个实施例中，传统的信息检索（IR）技术可以以独特的方式应用于执行摘要; 相关性测量，句子选择和术语消除可以在连续迭代中重复。在另一个实施例中，奇异值分解技术可以应用于逐个句子矩阵，使得来自文档的所有句子都可以投影到单个向量空间中; 然后，文本摘要器可以选择具有最大索引值的句子与最重要的奇异矢量作为文本摘要的一部分。

7. 发明申请

US20090099984A1 SYSTEMS AND METHODS FOR GENERATING PREDICTIVE MATRIX-VARIATE T MODELS 有权
标题翻译：用于生成预测矩阵变量T模型的系统和方法
公开(公告)号：US20090099984A1
公开(公告)日：2009-04-16
申请号：US11869886
申请日：2007-10-10
申请人： Shenghuo Zhu , Kai Yu , Yihong Gong
发明人： Shenghuo Zhu , Kai Yu , Yihong Gong
IPC分类号： G06N5/02 , G06F15/18
CPC分类号： G06N99/005 , G06K9/62
摘要： Systems and methods predict missing elements from a partially-observed matrix by receiving one or more user item ratings; generating a model parameterized by matrices U, S, V; and outputting the model.
摘要翻译：系统和方法通过接收一个或多个用户项目评级来预测来自部分观察矩阵的丢失元素; 生成由矩阵U，S，V参数化的模型; 并输出模型。

8. 发明授权

US07499571B1 Video surveillance system with rule-based reasoning and multiple-hypothesis scoring 失效
标题翻译：视频监控系统，具有基于规则的推理和多重假设评分
公开(公告)号：US07499571B1
公开(公告)日：2009-03-03
申请号：US11525795
申请日：2006-09-22
申请人： Mei Han , Yihong Gong , Hai Tao
发明人： Mei Han , Yihong Gong , Hai Tao
IPC分类号： G06K9/00 , H04N7/18 , H04N9/47 , H04N5/225
CPC分类号： G06K9/00771 , G06K9/00335 , G08B13/19608
摘要： A video surveillance system uses rule-based reasoning and multiple-hypothesis scoring to detect predefined behaviors based on movement through zone patterns. Trajectory hypothesis spawning allows for trajectory splitting and/or merging and includes local pruning to managed hypothesis growth. Hypotheses are scored based on a number of criteria, illustratively including at least one non-spatial parameter. Connection probabilities computed during the hypothesis spawning process are based on a number of criteria, illustratively including object size. Object detection and probability scoring is illustratively based on object class.
摘要翻译：视频监控系统使用基于规则的推理和多重假设评分来根据通过区域模式的移动来检测预定义的行为。轨迹假设产卵允许轨迹分裂和/或合并，并包括局部修剪以管理假设增长。假设基于许多标准进行评分，示例性地包括至少一个非空间参数。在假设产卵过程期间计算的连接概率基于许多标准，示例性地包括对象大小。对象检测和概率评分说明性地基于对象类。

9. 发明申请

US20070116356A1 VIDEO FOREGROUND SEGMENTATION METHOD 失效
标题翻译：视频前缀分割方法
公开(公告)号：US20070116356A1
公开(公告)日：2007-05-24
申请号：US11553043
申请日：2006-10-26
申请人： Yihong GONG , Mei HAN , Wei XU
发明人： Yihong GONG , Mei HAN , Wei XU
IPC分类号： G06K9/34
CPC分类号： G06K9/38 , G06T7/12 , G06T7/181 , G06T7/194 , G06T7/215 , G06T7/277 , G06T2207/10016 , H04N7/141
摘要： A fully automatic, computationally efficient segmentation method of video employing sequential clustering of sparse image features. Both edge and corner features of a video scene are employed to capture an outline of foreground objects and the feature clustering is built on motion models which work on any type of object and moving/static camera in which two motion layers are assumed due to camera and/or foreground and the depth difference between the foreground and background. Sequential linear regression is applied to the sequences and the instantaneous replacements of image features in order to compute affine motion parameters for foreground and background layers and consider temporal smoothness simultaneously. The Foreground layer is then extracted based upon sparse feature clustering which is time efficient and refined incrementally using Kalman filtering.
摘要翻译：一种使用稀疏图像特征的顺序聚类的全自动，计算效率高的视频分割方法。使用视频场景的边缘和角落特征来捕获前景对象的轮廓，并且特征聚类建立在对任何类型的对象和移动/静态相机工作的运动模型上，其中由于相机而假设两个运动层， /或前景和前景和背景之间的深度差。序列线性回归应用于图像特征的序列和瞬时替换，以便计算前景和背景层的仿射运动参数，同时考虑时间平滑度。然后基于稀疏特征聚类提取前景层，这是使用卡尔曼滤波进行时间有效和精确地提取的。

10. 发明授权

US07148912B2 Video surveillance system in which trajectory hypothesis spawning allows for trajectory splitting and/or merging 有权
标题翻译：视频监控系统，其中轨迹假设产生允许轨迹分割和/或合并
公开(公告)号：US07148912B2
公开(公告)日：2006-12-12
申请号：US10917201
申请日：2004-08-12
申请人： Mei Han , Yihong Gong , Hai Tao
发明人： Mei Han , Yihong Gong , Hai Tao
IPC分类号： H04N7/18 , H04N5/225
CPC分类号： G08B31/00 , G08B13/19604 , G08B13/19608 , G08B13/19615 , G08B13/19652
摘要： A video surveillance system uses rule-based reasoning and multiple-hypothesis scoring to detect predefined behaviors based on movement through zone patterns. Trajectory hypothesis spawning allows for trajectory splitting and/or merging and includes local pruning to managed hypothesis growth. Hypotheses are scored based on a number of criteria, illustratively including at least one non-spatial parameter. Connection probabilities computed during the hypothesis spawning process are based on a number of criteria, illustratively including object size. Object detection and probability scoring is illustratively based on object class.
摘要翻译：视频监控系统使用基于规则的推理和多重假设评分来根据通过区域模式的移动来检测预定义的行为。轨迹假设产卵允许轨迹分裂和/或合并，并包括局部修剪以管理假设增长。假设基于许多标准进行评分，示例性地包括至少一个非空间参数。在假设产卵过程期间计算的连接概率基于许多标准，示例性地包括对象大小。对象检测和概率评分说明性地基于对象类。

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