-
公开(公告)号：US20080317337A1
公开(公告)日：2008-12-25
申请号：US11821980
申请日：2007-06-25
Applicant: Yizhou Wang , Dashan Gao , Haitham Hindi , Minh Binh Do
Inventor： Yizhou Wang , Dashan Gao , Haitham Hindi , Minh Binh Do
IPC: G06K9/00
CPC classification number: G06K9/00469
Abstract: A system and method for decomposing a digital image is provided. A digital image is represented as a word-graph, which includes words and visualized features, and zone hypotheses that group one or more of the words. Causal dependencies of the zone hypotheses are expressed through a learned generative zone model to which costs and constraints are assigned. An optimal set of the zone hypotheses are inferred, which are non-overlapping, through a heuristic search of the costs and constraints.
Abstract translation: 提供了一种用于分解数字图像的系统和方法。 数字图像被表示为包括单词和可视化特征的单词图，以及对一个或多个单词进行分组的区域假设。 区域假设的因果依赖性通过分配成本和约束的学习生成区域模型来表示。 通过对成本和约束的启发式搜索，推断出区域假设的最优集合，它们是不重叠的。
-
公开(公告)号：US09384448B2
公开(公告)日：2016-07-05
申请号：US13339297
申请日：2011-12-28
Applicant: Peter Henry Tu , Ting Yu , Dashan Gao , Thomas Baby Sebastian , Yi Yao
Inventor： Peter Henry Tu , Ting Yu , Dashan Gao , Thomas Baby Sebastian , Yi Yao
CPC classification number: G06N99/005 , G06K9/6256
Abstract: Systems provided herein include a learning environment and an agent. The learning environment includes an avatar and an object. A state signal corresponding to a state of the learning environment includes a location and orientation of the avatar and the object. The agent is adapted to receive the state signal, to issue an action capable of generating at least one change in the state of the learning environment, to produce a set of observations relevant to a task, to hypothesize a set of action models configured to explain the observations, and to vet the set of action models to identify a learned model for the task.
Abstract translation: 本文提供的系统包括学习环境和代理。 学习环境包括头像和对象。 对应于学习环境的状态的状态信号包括化身和对象的位置和方向。 该代理适于接收状态信号，以发出能够产生学习环境状态的至少一个变化的动作，以产生与任务相关的一组观察结果，以假设一组动作模型，其被配置为解释 观察，并且审视一套动作模型，以确定一个学习的任务模型。
-
公开(公告)号：US20110249910A1
公开(公告)日：2011-10-13
申请号：US12756877
申请日：2010-04-08
Applicant: David L. Henderson , Kevin B. Kenny , Dirk R. Padfield , Dashan Gao , Richard R. McKay , Vipul A. Baxi , Robert J. Filkins , Michael C. Montalto
Inventor： David L. Henderson , Kevin B. Kenny , Dirk R. Padfield , Dashan Gao , Richard R. McKay , Vipul A. Baxi , Robert J. Filkins , Michael C. Montalto
IPC: G06K9/64
CPC classification number: G06K9/00134 , G06K9/036 , G06K2009/2045 , G06T7/0012 , G06T2207/10056 , G06T2207/20021 , G06T2207/30024 , G06T2207/30168
Abstract: Image quality is assessed for a digital image that is a composite of tiles or other image segments, especially focus accuracy for a microscopic pathology sample. An algorithm or combination of algorithms correlated to image quality is applied to pixel data at margins where adjacent image segments overlap and thus contain the same content in separately acquired images. The margins may be edges merged to join the image segments smoothly into a composite image, and typically occur on four sides of the image segments. The two versions of the same image content at each margin are processed by the quality algorithm, producing two assessment values. A sign and difference value are compared with other image segments, including by subsets selected for the orientation of the margins on sides on the image segments. The differences are mapped to displays. Selection criteria determine segments to be re-acquired.
Abstract translation: 评估图像质量是数字图像，其是瓦片或其他图像片段的复合物，特别是微观病理样品的聚焦精度。 将与图像质量相关的算法或算法的组合应用于相邻图像片段重叠的边缘处的像素数据，并且因此在单独获取的图像中包含相同的内容。 边缘可以被合并以将图像片段平滑地融合到合成图像中，并且通常发生在图像片段的四边上。 每个边距上的相同图像内容的两个版本由质量算法处理，产生两个评估值。 将符号和差值与其他图像片段进行比较，包括通过为图像片段上的边缘上的边缘的取向选择的子集进行比较。 差异映射到显示。 选择标准确定要重新获得的细分。
-
公开(公告)号：US20170200279A1
公开(公告)日：2017-07-13
申请号：US15326614
申请日：2014-08-28
Applicant: Xin ZHONG , Yu SUN , Dashan GAO , QUALCOMM Incorporated
Inventor： Xin Zhong , Yu Sun , Dashan Gao
CPC classification number: G06T7/248 , G06T7/11 , G06T7/174 , G06T7/187 , G06T7/194 , G06T7/215 , G06T2207/10016 , G06T2207/10024 , G06T2207/20076 , G06T2207/20132 , G06T2207/20156 , G06T2207/20164 , G06T2207/30201
Abstract: A method of generating a temporal saliency map is disclosed. In a particular embodiment, the method includes receiving an object bounding box from an object tracker. The method includes cropping a video frame based at least in part on the object bounding box to generate a cropped image. The method further includes performing spatial dual segmentation on the cropped image to generate an initial mask and performing temporal mask refinement on the initial mask to generate a refined mask. The method also includes generating a temporal saliency map based at least in part on the refined mask.
-
公开(公告)号：US20130287248A1
公开(公告)日：2013-10-31
申请号：US13456399
申请日：2012-04-26
Applicant: Dashan Gao , Ting Yu , Li Guan , Yi Yao , Kedar Anil Patwardhan , Peter Henry Tu
Inventor： Dashan Gao , Ting Yu , Li Guan , Yi Yao , Kedar Anil Patwardhan , Peter Henry Tu
CPC classification number: G06K9/46 , G06K9/00711 , G06K9/00771 , G06K9/00785 , G06K9/629 , G06T7/155 , G06T7/246 , G06T2207/10016
Abstract: A method for detecting and tracking a target includes detecting the target using a plurality of feature cues, fusing the plurality of feature cues to form a set of target hypotheses, tracking the target based on the set of target hypotheses and a scene context analysis, and updating the tracking of the target based on a target motion model.
Abstract translation: 用于检测和跟踪目标的方法包括使用多个特征提示来检测目标，将多个特征提示融合以形成一组目标假设，基于目标假设集合和场景上下文分析来跟踪目标，以及 基于目标运动模型更新目标的跟踪。
-
Patent Agency Ranking
公开(公告)号：US20130173504A1
公开(公告)日：2013-07-04
申请号：US13339297
申请日：2011-12-28
Applicant: Peter Henry Tu , Ting Yu , Dashan Gao , Thomas Baby Sebastian , Yi Yao
Inventor： Peter Henry Tu , Ting Yu , Dashan Gao , Thomas Baby Sebastian , Yi Yao
IPC: G06F15/18
CPC classification number: G06N99/005 , G06K9/6256
Abstract: Systems provided herein include a learning environment and an agent. The learning environment includes an avatar and an object. A state signal corresponding to a state of the learning environment includes a location and orientation of the avatar and the object. The agent is adapted to receive the state signal, to issue an action capable of generating at least one change in the state of the learning environment, to produce a set of observations relevant to a task, to hypothesize a set of action models configured to explain the observations, and to vet the set of action models to identify a learned model for the task.
Abstract translation: 本文提供的系统包括学习环境和代理。 学习环境包括头像和对象。 对应于学习环境的状态的状态信号包括化身和对象的位置和方向。 该代理适于接收状态信号，以发出能够产生学习环境状态的至少一个变化的动作，以产生与任务相关的一组观察结果，以假设一组动作模型，其被配置为解释 观察，并且审视一套动作模型，以确定一个学习的任务模型。
-
公开(公告)号：US20130138505A1
公开(公告)日：2013-05-30
申请号：US13308376
申请日：2011-11-30
Applicant: Peter Henry Tu , Mark Lewis Grabb , Xiaoming Liu , Ting Yu , Yi Yao , Dashan Gao , Ming-Ching Chang
Inventor： Peter Henry Tu , Mark Lewis Grabb , Xiaoming Liu , Ting Yu , Yi Yao , Dashan Gao , Ming-Ching Chang
IPC: G06Q30/02
CPC classification number: G06Q30/02
Abstract: An advertising system is disclosed. In one embodiment, the system includes a processor and a memory including application instructions for execution by the processor. The application instructions may include a visual analytics engine to analyze visual information including human activity and a content engine separate from the visual analytics engine to provide advertising content to one or more potential customers. Further, the instructions may include an interface module to enable information generated from analysis of the human activity by the visual analytics engine to be transferred to the content engine in accordance with a specification in which the information generated is characterized with a hierarchical, object-oriented data structure. Additional methods, systems, and articles of manufacture are also disclosed.
Abstract translation: 公开了广告系统。 在一个实施例中，该系统包括处理器和包括由处理器执行的应用指令的存储器。 应用指令可以包括视觉分析引擎，用于分析包括人类活动的视觉信息和与视觉分析引擎分离的内容引擎，以向一个或多个潜在客户提供广告内容。 此外，指令可以包括接口模块，用于根据其中所生成的信息以层次化，面向对象的特征来指示由视觉分析引擎分析人类活动而产生的信息被传送到内容引擎 数据结构。 还公开了附加的方法，系统和制品。
-
公开(公告)号：US20130136298A1
公开(公告)日：2013-05-30
申请号：US13306783
申请日：2011-11-29
Applicant: Ting Yu , Peter Henry Tu , Dashan Gao , Kunter Seref Akbay , Yi Yao
Inventor： Ting Yu , Peter Henry Tu , Dashan Gao , Kunter Seref Akbay , Yi Yao
IPC: G06K9/00
CPC classification number: G06K9/00362 , G06K9/00771 , G06K9/6218 , G06K9/6232 , G06K9/66 , G06T7/70
Abstract: A tracking and recognition system is provided. The system includes a computer vision-based identity recognition system configured to recognize one or more persons, without a priori knowledge of the respective persons, via an online discriminative learning of appearance signature models of the respective persons. The computer vision-based identity recognition system includes a memory physically encoding one or more routines, which when executed, cause the performance of constructing pairwise constraints between the unlabeled tracking samples. The computer vision-based identity recognition system also includes a processor configured to receive unlabeled tracking samples collected from one or more person trackers and to execute the routines stored in the memory via one or more algorithms to construct the pairwise constraints between the unlabeled tracking samples.
Abstract translation: 提供跟踪和识别系统。 该系统包括基于计算机视觉的身份识别系统，其被配置为通过对各个人的外观签名模型的在线辨别学习来识别一个或多个人，而没有相应人员的先验知识。 基于计算机视觉的身份识别系统包括物理地对一个或多个例程进行编码的存储器，当被执行时，引起在未标记的跟踪样本之间构建成对约束的性能。 基于计算机视觉的身份识别系统还包括处理器，其被配置为接收从一个或多个人跟踪器收集的未标记的跟踪样本，并且经由一个或多个算法来执行存储在存储器中的例程，以构建未标记的跟踪样本之间的成对约束。
-
9.发明授权Computer-implemented system and method for recognizing patterns in a digital image through document image decomposition 有权用于通过文档图像分解识别数字图像中的图案的计算机实现的系统和方法公开(公告)号：US08139865B2
公开(公告)日：2012-03-20
申请号：US13012770
申请日：2011-01-24
Applicant: Yizhou Wang , Dashan Gao , Haitham Hindi , Minh Binh Do
Inventor： Yizhou Wang , Dashan Gao , Haitham Hindi , Minh Binh Do
CPC classification number: G06K9/00469
Abstract: A computer-implemented system and method for retrieving a digital image through document image decomposition is provided. A stored digital image is retrieved. Generic visual features are extracted. The features are grouped into a primitive layer including word-graphs that each include words and features. The words are grouped into a layout layer including zone hypotheses that each include one or more of the words. Causal dependencies between the word-graphs and the zone hypotheses are expressed through zone models that include a joint probability defining a pair of probabilistic models generated through a learned binary edge classifier. Each pair of probabilistic models is expressed as an optimal set selection problem including a set of cost functions and constraints. The optimal set selection problem is evaluated through a heuristic search of the cost functions and constraints and a non-overlapping optimal set of the zone hypotheses is provided that characterize the stored digital image.
Abstract translation: 提供了一种用于通过文档图像分解来检索数字图像的计算机实现的系统和方法。 检索存储的数字图像。 提取一般视觉特征。 这些特征被分组成包括单词和特征的单词图形的原始图层。 这些单词被分组成一个布局层，包括区域假设，每一个都包含一个或多个单词。 通过区域模型来表达字图和区域假设之间的因果依赖关系，该区域模型包括定义通过学习的二进制边缘分类器生成的一对概率模型的联合概率。 每对概率模型被表示为包括一组成本函数和约束的最优集合选择问题。 通过对成本函数和约束的启发式搜索来评估最优集合选择问题，并且提供表征存储的数字图像的区域假设的非重叠最优集合。
-
公开(公告)号：US10121256B2
公开(公告)日：2018-11-06
申请号：US15326614
申请日：2014-08-28
Applicant: QUALCOMM Incorporated , Xin Zhong , Yu Sun , Dashan Gao
Inventor： Xin Zhong , Yu Sun , Dashan Gao
Abstract: A method of generating a temporal saliency map is disclosed. In a particular embodiment, the method includes receiving an object bounding box from an object tracker. The method includes cropping a video frame based at least in part on the object bounding box to generate a cropped image. The method further includes performing spatial dual segmentation on the cropped image to generate an initial mask and performing temporal mask refinement on the initial mask to generate a refined mask. The method also includes generating a temporal saliency map based at least in part on the refined mask.
-
-
-
-
-
-
-
-
-
Search Results
18
records
(took 0.014 seconds)
