公开(公告)号：US08712096B2

公开(公告)日：2014-04-29

申请号：US13041092

申请日：2011-03-04

Applicant: Jiangjian Xiao ,  Harpreet Singh Sawhney ,  Hui Cheng

Inventor： Jiangjian Xiao ,  Harpreet Singh Sawhney ,  Hui Cheng

IPC: G06K9/00

CPC classification number: G06K9/6296 ,  G06K9/00624 ,  G06T7/254

Abstract: 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.

Abstract translation: 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。

公开(公告)号：US08634638B2

公开(公告)日：2014-01-21

申请号：US12488911

申请日：2009-06-22

Applicant: Feng Han ,  Hui Cheng ,  Jiangjian Xiao ,  Harpreet Singh Sawhney ,  Sang-Hack Jung ,  Rakesh Kumar ,  Yanlin Guo

Inventor： Feng Han ,  Hui Cheng ,  Jiangjian Xiao ,  Harpreet Singh Sawhney ,  Sang-Hack Jung ,  Rakesh Kumar ,  Yanlin Guo

IPC: G06K9/62

CPC classification number: G06K9/00342

Abstract: 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.

Abstract translation: 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。

公开(公告)号：US08391368B2

公开(公告)日：2013-03-05

申请号：US11401990

申请日：2006-04-10

Applicant: Hui Cheng ,  Michael Anthony Isnardi ,  Arkady Kopansky

Inventor： Hui Cheng ,  Michael Anthony Isnardi ,  Arkady Kopansky

IPC: H04N7/12

CPC classification number: H04N19/59 ,  H04N19/117 ,  H04N19/132 ,  H04N19/139 ,  H04N19/147 ,  H04N19/176 ,  H04N19/196 ,  H04N19/61 ,  H04N19/82 ,  H04N19/86

Abstract: A system and method of compressing a video signal can include the steps of: receiving a video signal, the video signal including frames; analyzing, for each frame, the video signal on a macroblock-by-macroblock level; determining whether to downsample a macroblock residual for each of the macroblocks; selectively downsampling a macroblock residual for some of the macroblocks; and coding the macroblocks. A system and method of decompressing a video signal can include the steps of receiving a compressed video signal, the video signal including frames; analyzing, for each frame, the video signal on a macroblock-by-macroblock level; determining whether to upsample a macroblock residual for each of the macroblocks; selectively upsampling a macroblock residual for some of the macroblocks; and decoding the macroblocks.

Abstract translation: 压缩视频信号的系统和方法可以包括以下步骤：接收视频信号，视频信号包括帧; 对于每个帧分析以宏块为单位的视频信号; 确定是否对每个所述宏块的宏块残差进行下采样; 选择性地对某些宏块的宏块残差进行下采样; 并对宏块进行编码。 解压缩视频信号的系统和方法可以包括以下步骤：接收压缩视频信号，视频信号包括帧; 对于每个帧分析以宏块为单位的视频信号; 确定是否对每个宏块的宏块残差进行上采样; 选择性地对一些宏块的宏块残差进行采样; 并解码宏块。

公开(公告)号：US20120093398A1

公开(公告)日：2012-04-19

申请号：US13336815

申请日：2011-12-23

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

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

IPC: G06K9/62 ,  G06K9/00

CPC classification number: G06F16/70 ,  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：US20120092503A1

公开(公告)日：2012-04-19

申请号：US13336812

申请日：2011-12-23

Applicant: Hui Cheng

Inventor： Hui Cheng

IPC: H04N7/18

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：US20090316983A1

公开(公告)日：2009-12-24

申请号：US12488911

申请日：2009-06-22

Applicant: Feng Han ,  Hui Cheng ,  Jiangjian Xiao ,  Harpreet Singh Sawhney ,  Sang-Hack Jung ,  Rakesh Kumar ,  Yanlin Guo

Inventor： Feng Han ,  Hui Cheng ,  Jiangjian Xiao ,  Harpreet Singh Sawhney ,  Sang-Hack Jung ,  Rakesh Kumar ,  Yanlin Guo

IPC: G06K9/62

CPC classification number: G06K9/00342

Abstract: 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.

Abstract translation: 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。

公开(公告)号：US07515732B2

公开(公告)日：2009-04-07

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: G06K9/00 ,  G06K9/46 ,  G06K9/40

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：US07366361B2

公开(公告)日：2008-04-29

申请号：US10792073

申请日：2004-03-03

Applicant: Hui Cheng

Inventor： Hui Cheng

IPC: G06K9/32

CPC classification number: H04N17/004 ,  G06T7/35 ,  G06T7/38

Abstract: A processed (e.g., captured) video sequence is temporally, spatially, and/or histogram registered to the corresponding original video sequence by generating, for each set of one or more processed frames, a mapping from a selected set of one or more original frames to the processed set, wherein (1) each selected set depends on the selected set corresponding to a previous processed set, (2) each mapping minimizes a local prediction error between the original set and the corresponding processed set, and (3) the accumulated prediction error for the entire processed video sequence is minimized.

Abstract translation: 经处理的（例如，捕获的）视频序列在时间上，空间上和/或直方图上登记到相应的原始视频序列，对于每一组一个或多个经处理的帧，从所选择的一个或多个原始帧的集合生成映射 其中（1）每个选择的集合取决于对应于先前处理集合的所选集合，（2）每个映射最小化原始集合和对应的处理集合之间的局部预测误差，以及（3）累积 整个处理的视频序列的预测误差最小化。

公开(公告)号：US06975742B2

公开(公告)日：2005-12-13

申请号：US09724330

申请日：2000-11-29

Applicant: Hui Cheng

Inventor： Hui Cheng

IPC: G06T1/20 ,  G06T9/00 ,  H04N1/41 ,  G06K9/36

CPC classification number: G06T9/00

Abstract: A method of image compression includes digitizing an image and segmenting the image in a plurality of different manners to generate a plurality of segmented images. Each of the segmented images is compressed. The method further includes determining a bit rate for each of the compressed images, and determining how much image distortion results from each compression, Finally, the manner of segmentation which results in an optimal compromise between the rate and distortion is selected.

Abstract translation: 图像压缩的方法包括数字化图像并以多种不同的方式分割图像以生成多个分割图像。 每个分割图像被压缩。 该方法还包括确定每个压缩图像的比特率，以及确定每个压缩产生多少图像失真。最后，选择导致速率和失真之间的最佳折中的分割方式。

公开(公告)号：US06973213B2

公开(公告)日：2005-12-06

申请号：US09977186

申请日：2001-10-12

Applicant: Zhigang Fan ,  Hui Cheng

Inventor： Zhigang Fan ,  Hui Cheng

IPC: G06T11/60 ,  G06T5/00 ,  G06T7/40 ,  H04N1/387 ,  G06K9/34

CPC classification number: G06K9/00463 ,  G06K9/00456 ,  G06T7/11 ,  G06T7/155 ,  G06T7/187 ,  G06T2207/10008 ,  G06T2207/20156 ,  G06T2207/30176

Abstract: A method for segmenting an image using a background-based segmentation process is provided. A document image (102) is low-pass filtered and decimated. The decimated image is processed at low resolution by a low-resolution segmentation (104) stage. Segmentation results include identification of a main background and one or more objects. Objects that cannot be classified in text or picture classes are further segmented into a local background and smaller objects. This process is reiterated until all objects are classified in text or picture classes. The results are overlaid on the image (102) during an original-resolution refinement (106) stage to refine the segmentation.

Abstract translation: 提供了一种使用基于背景的分割过程来分割图像的方法。 文档图像（102）被低通滤波和抽取。 抽取的图像通过低分辨率分割（104）阶段以低分辨率处理。 分割结果包括识别主背景和一个或多个对象。 不能分类为文本或图片类的对象进一步分割为本地背景和较小对象。 重复此过程，直到所有对象分类为文本或图片类。 在原始分辨率细化（106）阶段期间，将结果覆盖在图像（102）上，以细化分割。