公开(公告)号：US08553931B2

公开(公告)日：2013-10-08

申请号：US12369664

申请日：2009-02-11

Applicant: Yeong-Taeg Kim ,  Ning Xu

Inventor： Yeong-Taeg Kim ,  Ning Xu

IPC: G06K9/00

CPC classification number: G06K9/00355

Abstract: A system and method for adaptively defining a region of interest for motion analysis in digital video is disclosed. In one embodiment, a method of detecting a gesture is disclosed which comprises receiving a video sequence comprising a plurality of frames, determining a region of interest which excludes a portion of the frame, and detecting the gesture within the region of interest.

Abstract translation: 公开了一种用于在数字视频中自适应地定义运动分析的感兴趣区域的系统和方法。 在一个实施例中，公开了一种检测手势的方法，其包括接收包括多个帧的视频序列，确定排除所述帧的一部分的感兴趣区域，以及检测所述感兴趣区域内的手势。

公开(公告)号：US08483431B2

公开(公告)日：2013-07-09

申请号：US12127738

申请日：2008-05-27

Applicant: Ning Xu ,  Yeong-Taeg Kim

Inventor： Ning Xu ,  Yeong-Taeg Kim

IPC: G06K9/00

CPC classification number: G06K9/00711 ,  G06T7/215 ,  G06T2207/10016 ,  G06T2207/30201

Abstract: Systems and methods for estimating the centers of moving objects in a video sequence are disclose. One embodiment is a method of defining one or more motion centers in a video sequence, the method comprising receiving a video sequence comprising a plurality of frames, receiving a motion history image for each of a subset of the plurality of frames based on the video sequence, identifying, through use of the motion history image, one or more data segments having a first orientation, wherein each data segment having the first orientation has a start location and a length, identifying, one or more data segments having a second orientation, wherein each element of a data segment having the second orientation is associated with a data segment having the first orientation, and defining a corresponding motion center for one or more of the indentified data segments having the second orientation.

Abstract translation: 公开了用于估计视频序列中的移动物体的中心的系统和方法。 一个实施例是一种在视频序列中定义一个或多个运动中心的方法，该方法包括接收包括多个帧的视频序列，基于视频序列接收多个帧的子集中的每一个的运动历史图像 通过使用运动历史图像来识别具有第一取向的一个或多个数据段，其中具有第一取向的每个数据段具有开始位置和长度，识别具有第二取向的一个或多个数据段，其中 具有第二取向的数据段的每个元素与具有第一取向的数据段相关联，并且为具有第二取向的一个或多个识别数据段定义相应的运动中心。

公开(公告)号：US20110283346A1

公开(公告)日：2011-11-17

申请号：US12780013

申请日：2010-05-14

Applicant: Weisheng Li ,  Bin Zhu ,  Ning Xu ,  Jia Liu

Inventor： Weisheng Li ,  Bin Zhu ,  Ning Xu ,  Jia Liu

IPC: G06F21/00 ,  G06K9/34

CPC classification number: G06F9/44 ,  G06F21/36 ,  G06F2221/2133 ,  H04L9/32

Abstract: The overlay human interactive proof system (“OHIPS”) and techniques described herein operate in conjunction with any known or later developed computer-based applications or services to provide secure access to resources by reliably differentiating between human and non-human users. Humans have a generally superior ability to differentiate misaligned characters or objects from correctly aligned ones. As such, the OHIP splits an image including one or more visual objects into two or more partial images to form a HIP. The partial images may also be further split into groups of sub-partial images, and/or the partial images (or the sub-partial images) may be moved, so that at any given alignment position, a user can recognize only some visual objects. A user is instructed to reassemble the partial images at one or more predetermined alignment positions using a GUI, and the user is asked to identify information regarding one or more visible objects.

Abstract translation: 覆盖人​​类交互式证明系统（“OHIPS”）和本文所描述的技术与任何已知或未来开发的基于计算机的应用或服务相结合，通过可靠地区分人和非人类用户来提供对资源的安全访问。 人类具有一般优越的能力来区分不正确的字符或对象与正确对齐的字符或对象。 因此，OHIP将包括一个或多个可视对象的图像分割成两个或更多个部分图像以形成HIP。 部分图像还可以进一步分割成一组子部分图像，和/或部分图像（或子部分图像）可以被移动，使得在任何给定的对准位置，用户只能识别一些视觉对象 。 指示用户使用GUI重新组装在一个或多个预定对准位置处的部分图像，并且要求用户识别关于一个或多个可见对象的信息。

公开(公告)号：US08059207B2

公开(公告)日：2011-11-15

申请号：US11710594

申请日：2007-02-23

Applicant: Ning Xu ,  Yeong-Taeg Kim

Inventor： Ning Xu ,  Yeong-Taeg Kim

IPC: H04N7/18 ,  H04N5/00

CPC classification number: H04N5/144 ,  H04N5/21

Abstract: An adaptive temporal noise reduction method that adaptively combines motion adaptive filtering results and motion compensated results to reduce Gaussian additive noise in video sequences is described herein. The system determines the motion detection and motion compensation results from the current frame and the filtered previous frame. Measurements on the video are used to determine a probabilistic measure of noise that is employed to adaptively combine the motion detection and motion compensation results.

Abstract translation: 本文描述了自适应地组合运动自适应滤波结果和运动补偿结果以减少视频序列中的高斯加性噪声的自适应时间噪声降低方法。 该系统从当前帧和经过滤的前一帧确定运动检测和运动补偿结果。 视频测量用于确定用于自适应地组合运动检测和运动补偿结果的噪声概率测量。

公开(公告)号：US07536059B2

公开(公告)日：2009-05-19

申请号：US10985364

申请日：2004-11-10

Applicant: Ning Xu ,  Yeong-Taeg Kim

Inventor： Ning Xu ,  Yeong-Taeg Kim

IPC: G06K9/36

CPC classification number: H04N1/648 ,  H04N19/124 ,  H04N19/172 ,  H04N19/186

Abstract: A color quantization method in RGB color space which preserves high precision of luminance information in an original high precision RGB image signal which is quantized to a lower precision (lower bit depth) RGB signal. The method can be used to convert the original RGB signal to arbitrary quantization levels in RGB space.

Abstract translation: RGB色彩空间中的颜色量化方法，其保持了以较低精度（较低位深度）RGB信号量化的原始高精度RGB图像信号中的亮度信息的高精度。 该方法可用于将原始RGB信号转换为RGB空间中的任意量化级别。

公开(公告)号：US20070132846A1

公开(公告)日：2007-06-14

申请号：US11433194

申请日：2006-05-11

Applicant: Alan Broad ,  Rahul Kapur ,  Jaidev Prabhu ,  Martin Turon ,  Ning Xu ,  Xin Yang ,  Matt Miller

Inventor： Alan Broad ,  Rahul Kapur ,  Jaidev Prabhu ,  Martin Turon ,  Ning Xu ,  Xin Yang ,  Matt Miller

IPC: H04N7/18 ,  H04N9/47

CPC classification number: G08B25/009 ,  G08B25/10 ,  G08B29/188 ,  H04W52/0216 ,  H04W84/18 ,  Y02D70/22

Abstract: A plurality of modules interact to form an adaptive network in which each module transmits and receives data signals indicative of proximity of objects. A central computer accumulates the data produced or received and relayed by each module for analyzing proximity responses to transmit through the adaptive network control signals to a selectively-addressed module to respond to computer analyses of the data accumulated from modules forming the adaptive network. Interactions of local processors in modules that sense an intrusion determine the location and path of movements of the intruding object and control cameras in the modules to retrieve video images of the intruding object. Multiple operational frequencies in adaptive networks permit expansions by additional networks that each operate at separate radio frequencies to avoid overlapping interaction. Additional modules may be introduced into operating networks without knowing the operating frequency at the time of introduction. Remote modules operating as leaf nodes of the adaptive network actively adapt to changed network conditions upon awaking from power-conserving sleep mode. New programs are distributed to all or selected modules under control of the base station.

Abstract translation: 多个模块交互以形成自适应网络，其中每个模块发送和接收指示对象接近的数据信号。 中央计算机累积由每个模块生成或接收和中继的数据，用于分析接近响应，以通过自适应网络控制信号传送到选择性寻址的模块，以响应从形成自适应网络的模块累积的数据的计算机分析。 感知入侵的模块中的本地处理器的交互决定了模块中入侵物体和控制摄像机的移动的位置和路径，以检索入侵物体的视频图像。 自适应网络中的多个操作频率允许通过附加网络进行扩展，每个网络在不同的射频频率下操作以避免重叠的交互。 在不知道引入时的工作频率的情况下，可以将额外的模块引入到操作网络中。 作为自适应网络的叶节点运行的远程模块在从省电休眠模式唤醒时主动适应变化的网络状况。 新程序分配给基站控制下的所有或所选模块。

公开(公告)号：US20060256129A1

公开(公告)日：2006-11-16

申请号：US11128761

申请日：2005-05-12

Applicant: Ning Xu ,  Yeong-Taeg Kim

Inventor： Ning Xu ,  Yeong-Taeg Kim

IPC: G09G5/02

CPC classification number: H04N9/67 ,  H04N1/603 ,  H04N17/02 ,  H04N17/04

Abstract: A method is presented for realizing standard colors on a display that does not have the standard primaries. The method enables a display with non-standard primaries to show colors as it has standard SMPTE-C primaries. Further, a method is presented to show the same standard colors on different locations of the display. Measurements of the physical parameters of the display's color primaries are obtained and implemented as calibrated display or a display which can be calibrated by user/calibrator with a color measuring tool such as calorimeter or spectroradiometer.

Abstract translation: 提出了一种在不具有标准原色的显示器上实现标准颜色的方法。 该方法使具有非标准原色的显示器显示颜色，因为它具有标准的SMPTE-C原色。 此外，呈现了在显示器的不同位置显示相同的标准颜色的方法。 显示器颜色原色的物理参数的测量被获得并被实现为校准显示器或显示器，其可以由用户/校准器用诸如量热计或分光光度计的颜色测量工具进行校准。

公开(公告)号：US20060176313A1

公开(公告)日：2006-08-10

申请号：US11056372

申请日：2005-02-10

Applicant: Ning Xu ,  Yeong-Taeg Kim

Inventor： Ning Xu ,  Yeong-Taeg Kim

IPC: G09G5/02

CPC classification number: H04N9/67

Abstract: This invention presents a YUV to RGB conversion method which preserves high precision of luminance information in an original YUV image signal when converting it to RGB signal. The method can be used to convert the original YUV signal to arbitrary quantization levels in RGB space. In addition, this invention presents methods of pre-quantization and re-quantization as to compensate conventional YUV to RGB color conversion.

Abstract translation: 本发明提出了一种YUV至RGB转换方法，当将其转换为RGB信号时，其保持原始YUV图像信号中的亮度信息的高精度。 该方法可用于将原始YUV信号转换为RGB空间中的任意量化级别。 此外，本发明提出了用于补偿常规YUV到RGB颜色转换的预量化和重新量化的方法。

公开(公告)号：US20200074653A1

公开(公告)日：2020-03-05

申请号：US16120105

申请日：2018-08-31

Applicant: Kun Duan ,  Daniel Ron ,  Chongyang Ma ,  Ning Xu ,  Shenlong Wang ,  Sumant Milind Hanumante ,  Dhritiman Sagar

Inventor： Kun Duan ,  Daniel Ron ,  Chongyang Ma ,  Ning Xu ,  Shenlong Wang ,  Sumant Milind Hanumante ,  Dhritiman Sagar

IPC: G06T7/536 ,  G06T11/60

Abstract: An active depth detection system can generate a depth map from an image and user interaction data, such as a pair of clicks. The active depth detection system can be implemented as a recurrent neural network that can receive the user interaction data as runtime inputs after training. The active depth detection system can store the generated depth map for further processing, such as image manipulation or real-world object detection.

公开(公告)号：US20170374341A1

公开(公告)日：2017-12-28

申请号：US15190085

申请日：2016-06-22

Applicant: Ashraf Ayman Michail ,  Georg Klein ,  Andrew Martin Pearson ,  Zsolt Mathe ,  Mark S. Grossman ,  Ning Xu

Inventor： Ashraf Ayman Michail ,  Georg Klein ,  Andrew Martin Pearson ,  Zsolt Mathe ,  Mark S. Grossman ,  Ning Xu

IPC: H04N13/00 ,  G06T19/00 ,  G06T19/20 ,  H04N13/04 ,  G06T3/60

CPC classification number: H04N13/128 ,  G06F3/012 ,  G06T3/60 ,  G06T15/06 ,  G06T19/00 ,  G06T19/006 ,  G06T19/20 ,  G06T2219/2016 ,  H04N13/111 ,  H04N13/324 ,  H04N13/332 ,  H04N13/366

Abstract: Examples are disclosed that relate to depth-aware late-stage reprojection. One example provides a computing system configured to receive and store image data, receive a depth map for the image data, processing the depth map to obtain a blurred depth map, and based upon motion data, determine a translation to be made to the image data. Further, for each pixel, the computing system is configured to translate an original ray extending from an original virtual camera location to an original frame buffer location to a reprojected ray extending from a translated camera location to a reprojected frame buffer location, determine a location at which the reprojected ray intersects the blurred depth map, and sample a color of a pixel for display based upon a color corresponding to the location at which the reprojected ray intersects the blurred depth map.