公开(公告)号：US20090316988A1

公开(公告)日：2009-12-24

申请号：US12141824

申请日：2008-06-18

Applicant: Ning Xu ,  Arunkumar Mohananchettiar

Inventor： Ning Xu ,  Arunkumar Mohananchettiar

IPC: G06K9/34

CPC classification number: G06K9/6297 ,  G06K9/6256 ,  G06K9/6857 ,  G06T7/11 ,  G06T7/162 ,  G06T2207/10016 ,  G06T2207/20016

Abstract: Systems and methods for processing an image to determine whether segments of the image belong to an object class are disclosed. In one embodiment, the method comprises receiving digitized data representing an image, the image data comprising a plurality of pixels, segmenting the pixel data into segments at a plurality of scale levels, determining feature vectors of the segments at the plurality of scale levels, the feature vectors comprising one or more measures of visual perception of the segments, determining one or more similarities, each similarity determined by comparing two or more feature vectors, determining, for each of a first subset of the segments, a first measure of probability that the segments is a member of an object class, determining probability factors based on the determined first measures of probability and similarity factors based on the determined similarities, and performing factor graph analysis to determine a second measure of probability for each of a second subset of the segments based on the probability factors and similarity factors.

Abstract translation: 公开了用于处理图像以确定图像的片段是否属于对象类的系统和方法。 在一个实施例中，所述方法包括接收表示图像的数字化数据，所述图像数据包括多个像素，将所述像素数据分割成多个尺度级别的片段，确定所述多个尺度级别上的片段的特征向量， 特征矢量，包括一段或多段视觉感知测量段，确定一个或多个相似度，通过比较两个或多个特征向量确定每个相似度，为该段的第一子集中的每一个确定第一测量概率， 段是对象类的成员，基于基于所确定的相似度的所确定的概率和相似性因子的第一度量来确定概率因子，并且执行因子图分析以确定段的第二子集中的每一个的概率的第二度量 基于概率因子和相似性因素。

公开(公告)号：US20090290762A1

公开(公告)日：2009-11-26

申请号：US12126688

申请日：2008-05-23

Applicant: Haiying Guan ,  Ning Xu

Inventor： Haiying Guan ,  Ning Xu

IPC: G06K9/46

CPC classification number: G06K9/4652 ,  G06K9/00362 ,  G06K9/6226

Abstract: Systems and methods for motion detection of human skin within temporally adjacent electronic images are provided. Motion detection is accomplished by analyzing the color values of selected pixels within the electronic images represented in CbCr color space. Histogram distributions which represent skin colors and non-skin colors in CbCr color space are modeled in order to provide likelihoods that a selected color value appears within the histogram distributions. Posterior skin probability values, indicating the probability that a selected pixel having a given CbCr color value represents human skin, are calculated from these likelihoods. For each of the selected pixels, an intensity difference of the pixel between the electronic images is compared to an adaptive intensity threshold which is a function of the posterior skin probability in order to determine whether the pixel is in motion.

Abstract translation: 提供了用于在时间上相邻的电子图像内的人皮肤的运动检测的系统和方法。 通过分析CbCr颜色空间中表示的电子图像内的所选像素的颜色值来实现运动检测。 在CbCr颜色空间中表示皮肤颜色和非肤色的直方图分布进行建模，以提供所选颜色值出现在直方图分布中的可能性。 根据这些可能性计算后皮肤概率值，其指示具有给定CbCr颜色值的所选像素表示人皮肤的概率。 对于每个所选择的像素，将电子图像之间的像素的强度差与作为后皮概率的函数的自适应强度阈值进行比较，以便确定像素是否在运动。

公开(公告)号：US07570812B2

公开(公告)日：2009-08-04

申请号：US11264938

申请日：2005-11-01

Applicant: Ning Xu ,  Yeong-Taeg Kim

Inventor： Ning Xu ,  Yeong-Taeg Kim

IPC: G06K9/34

CPC classification number: G06T5/002 ,  G06T5/20 ,  G06T2207/10016

Abstract: A super precision image processing system improves the precision of videos and images and eliminates the stage-like artifacts in the smoothly changing areas. In order to obtain higher precision content, the system segments the input image into connected segments and finds a local support for each pixel based on the segmentation result. The system then applies low-pass filtering to the local support for each pixel and the luminance changes between the filtering result and the original luminance of the pixel are limited to a level such that the output image will have the same higher bits as the input image.

Abstract translation: 超精密图像处理系统提高了视频和图像的精度，消除了平滑变化的区域中的舞台状伪像。 为了获得更高精度的内容，系统将输入图像分割为连接的分段，并根据分割结果为每个像素找到本地支持。 然后，系统对每个像素对本地支持应用低通滤波，并且滤波结果和像素的原始亮度之间的亮度变化被限制到使得输出图像将具有与输入图像相同的更高位的电平 。

公开(公告)号：US20080316372A1

公开(公告)日：2008-12-25

申请号：US11765974

申请日：2007-06-20

Applicant: Ning Xu ,  Yeong-Taeg Kim

Inventor： Ning Xu ,  Yeong-Taeg Kim

IPC: H04N5/66

CPC classification number: H04N5/57 ,  G09G3/20 ,  G09G5/00 ,  G09G2320/0233 ,  G09G2320/066 ,  G09G2320/08 ,  G09G2360/144 ,  H04N21/42202 ,  H04N21/4318 ,  H04N21/44218

Abstract: A video display with a display screen adapted to display video images according to adjustable display parameters, for example brightness, contrast, and/or sharpness, and at least one viewer sensor configured to determine at least one variable viewing characteristic and wherein the display is adapted to adjust the display parameters to adjust the displayed video image quality at least partially as a function of the variable viewing characteristic. A method of adjusting displayed image quality of a video display system, including inducing the video display system to determine at least one characteristic of a current viewing situation and adjusting one or more variable display parameters at least partially as a function of the determined characteristics. The viewing characteristics can include viewing time, viewing distance, and other.

Abstract translation: 具有适于根据可调节显示参数（例如亮度，对比度和/或清晰度）显示视频图像的显示屏幕的视频显示器，以及配置成确定至少一个可变观看特征的至少一个观看者传感器，并且其中所述显示器被适配 调整显示参数以至少部分地根据可变观看特征来调整显示的视频图像质量。 一种调整视频显示系统的显示图像质量的方法，包括诱导视频显示系统确定当前观看情况的至少一个特征，并且至少部分地根据所确定的特征来调整一个或多个可变显示参数。 观看特征可以包括观看时间，观看距离等。

公开(公告)号：US20070236610A1

公开(公告)日：2007-10-11

申请号：US11394954

申请日：2006-03-30

Applicant: Zhi Zhou ,  Yeong-Taeg Kim ,  Ning Xu

Inventor： Zhi Zhou ,  Yeong-Taeg Kim ,  Ning Xu

IPC: G06K9/40 ,  H04N5/00

CPC classification number: H04N19/80 ,  H04N19/85

Abstract: An image processing system implements recursive 3D super precision for processing smoothly changing video image areas by performing temporal noise reduction and then 2D super precision. The temporal noise reduction is applied to two frames, one being the current input low precision frame, and the other being the previous higher precision frame from memory. The 2D super precision is applied to the noise reduced frame to output a high precision frame which is also saved into memory for processing the next incoming frame. The input frame has a limited bit depth while the output image has an increased bit depth.

Abstract translation: 图像处理系统通过执行时间噪声降低然后2D超精度实现递归3D超精度，用于处理平滑变化的视频图像区域。 时间噪声降低被应用于两个帧，一个是当前输入低精度帧，另一个是来自存储器的先前较高精度帧。 2D超精度被应用于降噪帧以输出高精度帧，其也被保存到存储器中用于处理下一帧。 输入帧具有有限的位深度，而输出图像具有增加的位深度。

公开(公告)号：US20060221095A1

公开(公告)日：2006-10-05

申请号：US11099710

申请日：2005-04-05

Applicant: Ning Xu ,  Yeong-Taeg Kim

Inventor： Ning Xu ,  Yeong-Taeg Kim

IPC: G09G5/02

CPC classification number: G09G3/2059 ,  G09G3/2051 ,  G09G5/02

Abstract: A color quantization or re-quantization method is provided that combines two dimensional halftoning with luminance preserving quantization (LPQ) for better perception results of high precision color video quantization. A combination of LPQ and error diffusion, and a combination of LPQ and spatial dithering, is provided. To combine LPQ and spatial dithering, the spatial dithering is regarded as a two-step processing, a mapping and a simple rounding. To combine LPQ and dithering together, a rounding step is replaced by the LPQ algorithm in the combination. Further a method is provided for post-processing which is applicable to both cases to reduce the color perception for grayscale image.

Abstract translation: 提供了一种颜色量化或重新量化方法，其组合二维半色调与亮度保持量化（LPQ），以获得更高的高精度彩色视频量化的感知结果。 提供了LPQ和误差扩散的组合以及LPQ和空间抖动的组合。 为了组合LPQ和空间抖动，空间抖动被认为是两步处理，映射和简单舍入。 为了组合LPQ和抖动，组合中的LPQ算法代替了舍入步骤。 此外，提供了用于后处理的方法，其适用于两种情况以减少灰度图像的颜色感知。

公开(公告)号：US09554132B2

公开(公告)日：2017-01-24

申请号：US14119090

申请日：2012-05-24

Applicant: James E. Crenshaw ,  Alfred She ,  Ning Xu ,  Limin Liu ,  Scott Daly ,  Kevin Stec ,  Samir Hulyalkar

Inventor： James E. Crenshaw ,  Alfred She ,  Ning Xu ,  Limin Liu ,  Scott Daly ,  Kevin Stec ,  Samir Hulyalkar

IPC: H04N7/12 ,  H04N7/26 ,  H04N11/02 ,  H04N7/01 ,  H04N11/04 ,  H04B1/66 ,  G06K9/36 ,  H04N19/51 ,  H04N19/176 ,  H04N19/46 ,  H04N19/182 ,  H04N19/33 ,  H04N19/31 ,  H04N19/587 ,  H04N19/59 ,  H04N19/196

CPC classification number: H04N19/573 ,  H04N19/176 ,  H04N19/182 ,  H04N19/198 ,  H04N19/31 ,  H04N19/33 ,  H04N19/46 ,  H04N19/587 ,  H04N19/59

Abstract: Compression transforming video into a compressed representation (which typically can be delivered at a capped pixel rate compatible with conventional video systems), including by generating spatially blended pixels and temporally blended pixels (e.g., temporally and spatially blended pixels) of the video, and determining a subset of the blended pixels for inclusion in the compressed representation including by assessing quality of reconstructed video determined from candidate sets of the blended pixels. Trade-offs may be made between temporal resolution and spatial resolution of regions of reconstructed video determined by the compressed representation to optimize perceived video quality while reducing the data rate. The compressed data may be packed into frames. A reconstruction method generates video from a compressed representation using metadata indicative of at least one reconstruction parameter for spatial regions of the reconstructed video.

Abstract translation: 压缩将视频转换为压缩表示（通常可以以与常规视频系统兼容的上限像素速率传送），包括通过生成视频的空间混合像素和时间上混合的像素（例如，时间和空间上混合的像素），以及确定 用于包含在压缩表示中的混合像素的子集包括通过评估由混合像素的候选集确定的重建视频的质量。 可以在由压缩表示确定的重构视频的区域的时间分辨率和空间分辨率之间进行权衡，以在降低数据速率的同时优化感知视频质量。 压缩数据可以被打包成帧。 重建方法使用表示重建视频的空间区域的至少一个重建参数的元数据从压缩表示生成视频。

公开(公告)号：US08848057B2

公开(公告)日：2014-09-30

申请号：US11448206

申请日：2006-06-06

Applicant: Ning Xu ,  Sangkeun Lee ,  Yeong-Taeg Kim

Inventor： Ning Xu ,  Sangkeun Lee ,  Yeong-Taeg Kim

IPC: H04N7/18 ,  H04N9/47 ,  G08B13/196 ,  G06K9/00

CPC classification number: H04N7/181 ,  G06K9/00221 ,  G08B13/1961 ,  G08B13/19619 ,  G08B13/19636 ,  G08B13/19691 ,  H04N7/188

Abstract: A system and method combine digital television together with a digital video camera and controller unit for using a digital video camera together with a digital television set as a home security system that allows stranger detection, fire detection, motion detection, etc. The detection results are used to make further decisions such as display or record some of the scenes.

Abstract translation: 一种系统和方法将数字电视与数字摄像机和控制器单元结合在一起，使用数字摄像机和数字电视机作为允许陌生人检测，火灾探测，运动检测等的家庭安全系统。检测结果是 用于做出进一步的决定，如显示或记录某些场景。

公开(公告)号：US08707075B2

公开(公告)日：2014-04-22

申请号：US13356987

申请日：2012-01-24

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

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

IPC: G06F1/00 ,  G08C17/00 ,  H04H20/71 ,  H04W4/00 ,  H04L12/28 ,  G08B1/08 ,  G08B13/08 ,  H04Q5/22

CPC classification number: H04W52/0216 ,  G08B25/009 ,  G08B25/10 ,  G08B29/188 ,  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 the proximity of objects. A central computer accumulates the data produced or received and relayed by each module. One of the modules is operable as a leaf node having a sleep mode to conserve energy and an interactive mode. The central computer can send a message to the leaf node commanding it to stay awake in order to receive subsequent communications.

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产生或接收和中继的数据。 其中一个模块可操作为具有睡眠模式以节省能量和交互模式的叶节点。 中央计算机可以向叶节点发送消息，指示它保持清醒，以便接收后续的通信。

公开(公告)号：US08600185B1

公开(公告)日：2013-12-03

申请号：US13981889

申请日：2012-01-30

Applicant: Ning Xu ,  James E. Crenshaw

Inventor： Ning Xu ,  James E. Crenshaw

IPC: G06K9/40 ,  G06K9/00

CPC classification number: G06K9/4652 ,  H04N1/60

Abstract: Methods and systems for restoring image integrity in an image are described. The described methods and systems are particularly applied against an image after determining whether the image has undergone at least one of a color mutation, a non-color mutation, or a combination of a color mutation and a non-color mutation.

Abstract translation: 描述了用于恢复图像中的图像完整性的方法和系统。 在确定图像是否经历了颜色突变，非颜色突变或颜色突变和非颜色突变的组合中的至少一种后，所描述的方法和系统特别应用于图像。