公开(公告)号：US20140355671A1

公开(公告)日：2014-12-04

申请号：US13906031

申请日：2013-05-30

Applicant: Ya-Ti Peng ,  Yi-Jen Chiu ,  Hong Jiang

Inventor： Ya-Ti Peng ,  Yi-Jen Chiu ,  Hong Jiang

IPC: H04N19/167 ,  H04N19/115 ,  H04N19/176

CPC classification number: H04N19/115 ,  H04N19/117 ,  H04N19/124 ,  H04N19/167 ,  H04N19/176

Abstract: Systems, articles, and methods are described including bit-rate control for video coding using object-of-interest data.

Abstract translation: 描述了系统，文章和方法，其包括利用目标数据的视频编码的比特率控制。

公开(公告)号：US20140079134A1

公开(公告)日：2014-03-20

申请号：US13784978

申请日：2013-03-05

Applicant: Yi-Jen Chiu ,  Hong Jiang ,  Lidong Xu ,  Ya-Ti Peng

Inventor： Yi-Jen Chiu ,  Hong Jiang ,  Lidong Xu ,  Ya-Ti Peng

IPC: H04N9/64 ,  H04N7/30

CPC classification number: H04N9/64 ,  H04N1/64 ,  H04N19/186 ,  H04N19/30 ,  H04N19/60

Abstract: Techniques are described that can be used to either compress or expand video. Color compression techniques are described that can be used to compress the wide color gamut content into lower color gamut for inclusion in a baseline layer. Color expansion techniques are described that convert lower color gamut data into wider color gamut format for inclusion in an enhancement layer. Both of the baseline video stream and enhancement layer video streams may be transmitted through a channel or stored in a memory device to be viewed later. Accordingly, both baseline and enhancement video layers are available so that either lower or higher quality displays can be used to display video.

Abstract translation: 描述了可用于压缩或扩展视频的技术。 描述了可用于将宽色域内容压缩成较低色域以包括在基线层中的彩色压缩技术。 描述了将较低色域数据转换成更宽的色域格式以包含在增强层中的颜色展开技术。 基线视频流和增强层视频流都可以通过信道发送或存储在存储设备中，以便稍后观看。 因此，基线和增强视频层都可用，以便可以使用较低或较高质量的显示器来显示视频。

公开(公告)号：US08639031B2

公开(公告)日：2014-01-28

申请号：US13074257

申请日：2011-03-29

Applicant: Ya-Ti Peng ,  Yi-Jen Chiu

Inventor： Ya-Ti Peng ,  Yi-Jen Chiu

IPC: G06K9/00 ,  G06K9/40

CPC classification number: G06T5/40 ,  G06K9/38 ,  G06T2207/10016 ,  G06T2207/10024

Abstract: Techniques are disclosed involving contrast adjustment for images. For example, an input image is classified based on its pixel value characteristics, as expressed in an input brightness histogram. From such a classification, a target histogram distribution for a corresponding output image (i.e., a contrast-adjusted transformation of the input image) may be specified. With the target histogram of the output image specified, a transformation function may be derived that maps input image values to output image values. Moreover, transitions of such transformation functions may be smoothed. Such smoothing may provide advantages, such as a reduction in flickering associated with video data.

Abstract translation: 公开了涉及图像的对比度调整的技术。 例如，输入图像根据输入亮度直方图所表示的像素值特性进行分类。 根据这样的分类，可以规定对应的输出图像的目标直方图分布（即输入图像的对比度调整变换）。 利用指定的输出图像的目标直方图，可以导出将输入图像值映射到输出图像值的变换函数。 此外，这种变换函数的转换可以被平滑化。 这种平滑可以提供诸如减少与视频数据相关联的闪烁的优点。

公开(公告)号：US08446961B2

公开(公告)日：2013-05-21

申请号：US12283305

申请日：2008-09-11

Applicant: Yi-Jen Chiu ,  Hong Jiang ,  Lidong Xu ,  Ya-Ti Peng

Inventor： Yi-Jen Chiu ,  Hong Jiang ,  Lidong Xu ,  Ya-Ti Peng

IPC: H04N11/06

CPC classification number: H04N9/64 ,  H04N1/64 ,  H04N19/186 ,  H04N19/30 ,  H04N19/60

Abstract: Techniques are described that can be used to either compress or expand video. Color compression techniques are described that can be used to compress the wide color gamut content into lower color gamut for inclusion in a baseline layer. Color expansion techniques are described that convert lower color gamut data into wider color gamut format for inclusion in an enhancement layer. Both of the baseline video stream and enhancement layer video streams may be transmitted through a channel or stored in a memory device to be viewed later. Accordingly, both baseline and enhancement video layers are available so that either lower or higher quality displays can be used to display video.

Abstract translation: 描述了可用于压缩或扩展视频的技术。 描述了可用于将宽色域内容压缩到较低色域以包含在基线层中的色彩压缩技术。 描述了将较低色域数据转换成更宽的色域格式以包含在增强层中的颜色展开技术。 基线视频流和增强层视频流都可以通过信道发送或存储在存储设备中，以便稍后观看。 因此，基线和增强视频层都可用，以便可以使用较低或较高质量的显示器来显示视频。

公开(公告)号：US20120176395A1

公开(公告)日：2012-07-12

申请号：US12985461

申请日：2011-01-06

Applicant: Ya-Ti Peng ,  Yi-Jen Chiu

Inventor： Ya-Ti Peng ,  Yi-Jen Chiu

IPC: G09G5/02

CPC classification number: G06T5/008 ,  H04N1/62

Abstract: Methods and systems to manipulate color processing parameters to allow the detection of an arbitrary color of interest. Such reconfigurations may enable general point-of-interest color processing. Color mapping curves may also be configured, to accomplish the tasks of color correction, enhancement, de-saturation, and color compression.

Abstract translation: 用于操纵颜色处理参数以允许检测感兴趣的任意颜色的方法和系统。 这样的重新配置可以实现一般的兴趣点颜色处理。 也可以配置颜色映射曲线，以完成色彩校正，增强，去饱和和色彩压缩的任务。

公开(公告)号：US20140226865A1

公开(公告)日：2014-08-14

申请号：US13997092

申请日：2011-12-30

Applicant: Qiang Li ,  Jianguo Li ,  Yi-Jen Chiu ,  Ya-Ti Peng ,  Yangzhou Du

Inventor： Qiang Li ,  Jianguo Li ,  Yi-Jen Chiu ,  Ya-Ti Peng ,  Yangzhou Du

IPC: H04N5/14 ,  G06K9/62

CPC classification number: H04N5/145 ,  G06K9/3216 ,  G06K9/3233 ,  G06K9/6267 ,  G06T7/223 ,  G06T7/248

Abstract: Systems and methods of detecting an object using motion estimation may include a processor and motion estimation and object detection logic coupled to the processor. The motion estimation and object detection logic may be configured to include logic to detect an object in a frame of a video based on motion estimation. The video may include a first frame and a second frame. The motion estimation may be performed on a region of the second frame using sum of absolute difference between the region of the second frame and a corresponding region of the first frame.

Abstract translation: 使用运动估计来检测对象的系统和方法可以包括耦合到处理器的处理器和运动估计和对象检测逻辑。 运动估计和对象检测逻辑可以被配置为包括基于运动估计来检测视频帧中的对象的逻辑。 视频可以包括第一帧和第二帧。 可以使用第二帧的区域和第一帧的对应区域之间的绝对差的和来在第二帧的区域上执行运动估计。

公开(公告)号：US20110216985A1

公开(公告)日：2011-09-08

申请号：US12718033

申请日：2010-03-05

Applicant: Ya-Ti Peng ,  Yi-Jen Chiu

Inventor： Ya-Ti Peng ,  Yi-Jen Chiu

IPC: G06K9/32 ,  G06K9/40

CPC classification number: G06T3/40

Abstract: System, method, and computer program product to adaptively blend the interpolation results from an 8-tap Lanczos filter and the interpolation results from a bilinear filter, according to the local transitions of the input content. Artifacts may occur, which may be identified as such and corrected. Pixels that represent artifacts in the blended image may be replaced with the pixel for that location taken from the bilinear interpolation.

Abstract translation: 系统，方法和计算机程序产品，根据输入内容的本地转换，自适应地从8抽头Lanczos滤波器和双线性滤波器的插值结果混合插值结果。 可能发生人工错误，可能会被识别和纠正。 在混合图像中表示伪像的像素可以被从双线性插值中取出的该位置的像素代替。

公开(公告)号：US08108332B2

公开(公告)日：2012-01-31

申请号：US12106843

申请日：2008-04-21

Applicant: Archan Misra ,  Ya-Ti Peng ,  Daby Mousse Sow

Inventor： Archan Misra ,  Ya-Ti Peng ,  Daby Mousse Sow

IPC: G06F9/44 ,  G06N7/02 ,  G06N7/06

CPC classification number: G06K9/623 ,  G06N99/005

Abstract: A method is provided for performing a classification. The method includes ranking a plurality of features of a training set according to how closely they are correlated to their corresponding classifications, extracting a plurality of features of from input data, selecting a subset of the plurality of features such that a computational resource cost of the subset is less than a predefined computational resource maximum and a degree of utility achieved by a classification of the subset by a selected classifier is optimized and exceeds a predefined utility minimum, predicting one of the features of the sensor data that is not selected for the subset of features from a predefined number of past samples of the feature and adding the predicted feature to the subset of features, and classifying, by a processor, using the selected classifier and the resulting subset of features.

Abstract translation: 提供了一种执行分类的方法。 该方法包括根据它们与其对应分类相关的密切程度对训练集合的多个特征进行排序，从输入数据中提取多个特征，选择多个特征的子集，使得计算资源成本 子集小于预定义的计算资源最大值，并且通过所选择的分类器对子集的分类实现的效用程度被优化并且超过预定义的效用最小值，预测未被选择用于子集的传感器数据的特征之一 来自特征的预定数量的过去采样的特征并将预测特征添加到特征子集，并且由处理器使用所选择的分类器和所得到的特征子集进行分类。

公开(公告)号：US20090265297A1

公开(公告)日：2009-10-22

申请号：US12106843

申请日：2008-04-21

Applicant: Archan Misra ,  Ya-Ti Peng ,  Daby Mousse Sow

Inventor： Archan Misra ,  Ya-Ti Peng ,  Daby Mousse Sow

IPC: G06N7/02

CPC classification number: G06K9/623 ,  G06N99/005

Abstract: A method is provided for selecting features for classification that trades classification efficiency for computational resources. The method includes ranking a plurality of features of a training set according to how closely they are correlated to their corresponding classifications, receiving sensor data including a plurality of features, and selecting a subset of the features of the sensor data, according to the ranking of the features of the training data such that a computational resource cost of the subset is less than a predefined computational resource maximum and the degree of utility achieved by a classification of the subset of features by a selected classifier is optimized and exceeds a predefined utility minimum.

Abstract translation: 提供了一种用于选择用于计算资源的分类效率的用于分类的特征的方法。 该方法包括根据它们与其对应分类的相关程度如何接近地对训练集合的多个特征进行排序，接收包括多个特征的传感器数据以及根据传感器数据的特征的选择来选择传感器数据的特征的子集 所述训练数据的特征使得所述子集的计算资源成本小于预定义的计算资源最大值，并且通过所选择的分类器对所述特征子集进行分类而实现的效用程度被优化并且超过预定义的效用最小值。