公开(公告)号：US20090153661A1

公开(公告)日：2009-06-18

申请号：US12271173

申请日：2008-11-14

Applicant: Hui Cheng ,  Jiangjian Xiao ,  Harpreet Sawhney

Inventor： Hui Cheng ,  Jiangjian Xiao ,  Harpreet Sawhney

IPC: H04N7/18

CPC classification number: G06T7/20 ,  G06K9/00771 ,  G06K2009/3291

Abstract: 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.

Abstract translation: 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。

公开(公告)号：US20080310737A1

公开(公告)日：2008-12-18

申请号：US12136138

申请日：2008-06-10

Applicant: Feng Han ,  Hui Cheng ,  Jiangjian Xiao ,  Harpreet Singh Sawhney

Inventor： Feng Han ,  Hui Cheng ,  Jiangjian Xiao ,  Harpreet Singh Sawhney

IPC: G06K9/62

CPC classification number: G06K9/3241 ,  G06K9/6256 ,  G06K9/6292

Abstract: 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.

Abstract translation: 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。

公开(公告)号：US20060077255A1

公开(公告)日：2006-04-13

申请号：US11200869

申请日：2005-08-10

Applicant: Hui Cheng

Inventor： Hui Cheng

IPC: H04N7/18 ,  H04N9/47

CPC classification number: H04N5/232 ,  G06K9/0063 ,  G06K2009/2045 ,  G06T1/0007 ,  G06T7/33 ,  G06T2200/32 ,  G06T2207/20228 ,  G06T2207/30181 ,  G08B13/19643 ,  G08B13/1965 ,  H04N5/2224 ,  H04N7/185

Abstract: An adaptive image acquisition system and method that generates virtual view of a surveillance scene to a user (operator), in which, the user operates the system. Through viewing the virtual view, the user controls sensors that create the virtual view. The sensors comprise at least one first sensor having a higher resolution than at least one second sensor. Images from the second sensor are processed to create an image mosaic that is overlaid with images from the higher resolution first sensor. In one embodiment of the invention, the first sensor is moved using Saccade motion. In another embodiment of the invention, a user's intent is used to control the Saccade motion.

Abstract translation: 一种自适应图像获取系统和方法，其向用户（操作者）生成监视场景的虚拟视图，其中用户操作系统。 通过查看虚拟视图，用户控制创建虚拟视图的传感器。 传感器包括至少一个具有比至少一个第二传感器更高分辨率的第一传感器。 来自第二传感器的图像被处理以产生覆盖有来自较高分辨率的第一传感器的图像的图像马赛克。 在本发明的一个实施例中，使用Saccade运动来移动第一传感器。 在本发明的另一个实施例中，用户的意图被用于控制Saccade运动。

公开(公告)号：US20060073449A1

公开(公告)日：2006-04-06

申请号：US11206678

申请日：2005-08-18

Applicant: Rakesh Kumar ,  Aydin Arpa ,  Hui Cheng ,  Vincent Paragano ,  Keith Hanna

Inventor： Rakesh Kumar ,  Aydin Arpa ,  Hui Cheng ,  Vincent Paragano ,  Keith Hanna

IPC: G09B19/00

CPC classification number: G09B7/02 ,  F41A33/00 ,  F41G3/26 ,  F41J5/10 ,  F41J5/14

Abstract: A method and system for performing automated training environment monitoring and evaluation. The training environment may include a mixed reality elements to enhance a training experience.

Abstract translation: 一种用于执行自动化培训环境监测和评估的方法和系统。 培训环境可能包括混合的现实要素，以增强培训经验。

公开(公告)号：US06954541B2

公开(公告)日：2005-10-11

申请号：US10158027

申请日：2002-05-29

Applicant: Zhigang Fan ,  Hui Cheng ,  Robert J. Rolleston

Inventor： Zhigang Fan ,  Hui Cheng ,  Robert J. Rolleston

IPC: G06T1/00 ,  G11B20/00 ,  H04N1/32 ,  G06K9/00

CPC classification number: G06T1/0071 ,  G06T2201/0051 ,  G06T2201/0061 ,  G11B20/00086 ,  H04N1/00005 ,  H04N1/00037 ,  H04N1/32144 ,  H04N1/32213 ,  H04N1/32251 ,  H04N1/32267 ,  H04N1/32288 ,  H04N1/32299 ,  H04N1/32304 ,  H04N1/32309 ,  H04N2201/3242 ,  H04N2201/328

Abstract: A method of editing a digital image having associated embedded data, such as printing hints, includes embedding a first watermark in the original image before the image is edited. The first watermarking scheme associates first watermark information with each pixel and is used to detect which pixels have been edited. A second watermark may be embedded in the original image according to a second watermarking scheme which associates second watermark information with non-overlapping groups of pixels in the original image. The second watermark information may be used to synchronize the first watermark information and to detect editing information which does not change pixel values. After editing, only those edited portions of the image need have their embedded data reapplied.

Abstract translation: 编辑具有相关联的嵌入数据（诸如打印提示）的数字图像的方法包括在图像编辑之前在原始图像中嵌入第一水印。 第一水印方案将第一水印信息与每个像素相关联，并用于检测哪些像素已被编辑。 第二水印可以根据将第二水印信息与原始图像中的非重叠像素组相关联的第二水印方案嵌入到原始图像中。 第二水印信息可以用于同步第一水印信息并且检测不改变像素值的编辑信息。 编辑后，只有图像的编辑部分需要重新应用其嵌入的数据。

公开(公告)号：US20050123194A1

公开(公告)日：2005-06-09

申请号：US11034131

申请日：2005-01-12

Applicant: Zhigang Fan ,  Shen-ge Wang ,  Hui Cheng

Inventor： Zhigang Fan ,  Shen-ge Wang ,  Hui Cheng

IPC: H04N1/387 ,  G06T1/00 ,  H04N1/32 ,  H04N1/46 ,  H04N1/60 ,  G06K9/00 ,  G06K9/40 ,  G06K15/00 ,  G06T5/00 ,  H04N1/407

CPC classification number: H04N1/32309 ,  G06T1/0021 ,  G06T2201/0601 ,  H04N1/32144 ,  H04N1/32341 ,  H04N1/6033 ,  H04N2201/0081 ,  H04N2201/3242 ,  H04N2201/3271 ,  H04N2201/3283

Abstract: A method for enhancing color fidelity in multi-reproduction, includes scanning an image to be reproduced, wherein the image contains an invisible digital watermark including color information; decoding the color information contained in the watermark; comparing the decoded color information with the scanned image; generating a correction table from the differences between the decoded color information and the scanned image; and performing color correction on the scanned image using the correction table. This method confines the color error to one generation, even when copies go through multiple reproduction.

Abstract translation: 一种用于增强多重再现中的色彩保真度的方法，包括扫描要再现的图像，其中图像包含包含颜色信息的不可见数字水印; 对包含在水印中的颜色信息进行解码; 将解码的颜色信息与扫描图像进行比较; 从解码的颜色信息和扫描图像之间的差异产生校正表; 并使用校正表对扫描图像执行颜色校正。 这种方法将颜色误差限制在一代，即使拷贝经过多重再现。

公开(公告)号：US20050018875A1

公开(公告)日：2005-01-27

申请号：US10872963

申请日：2004-06-21

Applicant: Jeffrey Lubin ,  Hui Cheng

Inventor： Jeffrey Lubin ,  Hui Cheng

IPC: G06K9/00 ,  G06T20060101

CPC classification number: G06T1/005 ,  G06T2201/0065 ,  G06T2201/0081

Abstract: A method and apparatus for using a reference in a watermarking application is disclosed. Watermarked content and a reduced resolution reference are registered such that registration parameters are calculated. The watermarked content is processed using the registration parameters. A watermark is recovered using the processed watermarked content and the reduced resolution reference.

Abstract translation: 公开了一种在水印应用中使用参考的方法和装置。 注册水印内容和降低的分辨率参考，使得计算注册参数。 使用注册参数处理加水印的内容。 使用经处理的水印内容和降低的分辨率参考来恢复水印。

公开(公告)号：US09854147B2

公开(公告)日：2017-12-26

申请号：US13336812

申请日：2011-12-23

Applicant: Hui Cheng

Inventor： Hui Cheng

IPC: H04N7/18 ,  H04N5/232 ,  G06K9/00 ,  G06T1/00 ,  G08B13/196 ,  H04N5/222 ,  G06T7/33 ,  G06K9/20

CPC classification number: H04N5/232 ,  G06K9/0063 ,  G06K2009/2045 ,  G06T1/0007 ,  G06T7/33 ,  G06T2200/32 ,  G06T2207/20228 ,  G06T2207/30181 ,  G08B13/19643 ,  G08B13/1965 ,  H04N5/2224 ,  H04N7/185

Abstract: An adaptive image acquisition system and method that generates virtual view of a surveillance scene to a user (operator), in which, the user operates the system. Through viewing the virtual view, the user controls sensors that create the virtual view. The sensors comprise at least one first sensor having a higher resolution than at least one second sensor. Images from the second sensor are processed to create an image mosaic that is overlaid with images from the higher resolution first sensor. In one embodiment of the invention, the first sensor is moved using Saccade motion. In another embodiment of the invention, a user's intent is used to control the Saccade motion.

公开(公告)号：US09569531B2

公开(公告)日：2017-02-14

申请号：US12489667

申请日：2009-06-23

Applicant: Hui Cheng ,  Changjiang Yan ,  Harpreet Singh Sawhney ,  Feng Han

Inventor： Hui Cheng ,  Changjiang Yan ,  Harpreet Singh Sawhney ,  Feng Han

IPC: G06F17/30 ,  G06K9/00 ,  G06K9/46 ,  G06K9/62

CPC classification number: G06F17/30781 ,  G06K9/00771 ,  G06K9/4642 ,  G06K9/6292

Abstract: A method and system for creating a histogram of oriented occurrences (HO2) is disclosed. A plurality of entities in at least one image are detected and tracked. One of the plurality of entities is designated as a reference entity. A local 2-dimensional ground plane coordinate system centered on and oriented with respect to the reference entity is defined. The 2-dimensional ground plane is partitioned into a plurality of non-overlapping bins, the bins forming a histogram, a bin tracking a number of occurrences of an entity class. An occurrence of at least one other entity of the plurality of entities located in the at least one image may be associated with one of the plurality of non-overlapping bins. A number of occurrences of entities of at least one entity class in at least one bin may be into a vector to define an HO2 feature.

Abstract translation: 公开了一种用于创建定向事件直方图（HO2）的方法和系统。 检测并跟踪至少一个图像中的多个实体。 多个实体之一被指定为参照实体。 定义以参考实体为中心并定向的局部二维地面坐标系。 二维接地平面被划分成多个不重叠的箱体，该箱体形成一个直方图，一个箱子跟踪一个实体类的出现次数。 位于所述至少一个图像中的所述多个实体中的至少一个其他实体的出现可以与所述多个非重叠区域中的一个相关联。 在至少一个箱中的至少一个实体类的实体的多个出现可以被转换为向量以定义HO2特征。

公开(公告)号：US09053194B2

公开(公告)日：2015-06-09

申请号：US13484520

申请日：2012-05-31

Applicant: Harpreet Singh Sawhney ,  Jayakrishnan Eledath ,  Ajay Divakaran ,  Mayank Bansal ,  Hui Cheng

Inventor： Harpreet Singh Sawhney ,  Jayakrishnan Eledath ,  Ajay Divakaran ,  Mayank Bansal ,  Hui Cheng

IPC: G06F17/30

CPC classification number: G06F17/2785 ,  G06F17/30047 ,  G06F17/30867 ,  G06F17/3087

Abstract: A computer-implemented method comprising collecting data from a plurality of information sources, identifying a geographic location associated with the data and forming a corresponding event according to the geographic location, correlating the data and the event with one or more topics based at least partly on the identified geographic location and storing the correlated data and event and inferring the associated geographic location if the data does not comprise explicit location information, including matching the data against a database of geo-referenced data.

Abstract translation: 一种计算机实现的方法，包括从多个信息源收集数据，识别与所述数据相关联的地理位置并根据所述地理位置形成对应的事件，至少部分地基于所述数据和所述事件与一个或多个主题相关联 所识别的地理位置并存储相关数据和事件，并且如果数据不包括显式位置信息，则推断相关联的地理位置，包括将数据与地理参考数据的数据库进行匹配。