公开(公告)号：US20140044375A1

公开(公告)日：2014-02-13

申请号：US13961973

申请日：2013-08-08

Applicant: Samsung Electronics Co., Ltd.

Inventor： Kuanhong XU ,  Qiang WANG ,  Ji-yeun KIM ,  Woo-young JANG

IPC: G06T5/00

CPC classification number: G06T5/00 ,  G06T5/002 ,  G06T2207/10101 ,  G06T2207/20012

Abstract: An image processing method includes configuring a noise reduction filter for each of pixels in an image in accordance with a linear noise model of the image, based on different levels of a noise effect caused to a corresponding pixel, among the pixels, by other pixels, among the pixels and adjacent to the corresponding pixel. The method further includes performing noise reduction filtering on each of the pixels, using the noise reduction filter for each of the pixels, to obtain a noise reduced image.

Abstract translation: 一种图像处理方法包括：根据图像的线性噪声模型，基于由像素之中的相应像素对其他像素引起的噪声效应的不同级别，对其中的每个像素配置降噪滤波器， 并且与相应的像素相邻。 该方法还包括使用每个像素的降噪滤波器对每个像素执行降噪滤波，以获得降噪图像。

公开(公告)号：US20160210502A1

公开(公告)日：2016-07-21

申请号：US14995633

申请日：2016-01-14

Applicant: Samsung Electronics Co., Ltd.

Inventor： Kuanhong XU ,  Ya LU ,  Zhilan HU ,  Hongwei ZHANG ,  Jae-Joon HAN ,  Wonjun KIM

IPC: G06K9/00 ,  G06K9/66 ,  G06K9/52 ,  G06T7/20 ,  H04N19/136

CPC classification number: G06K9/00335

Abstract: A method and corresponding apparatus include extracting a movement trajectory feature of an object from an input video. The method and corresponding apparatus also include coding the extracted movement trajectory feature, and determining a type of a movement of the object based on the coded movement trajectory feature.

Abstract translation: 方法和相应的装置包括从输入视频中提取对象的移动轨迹特征。 所述方法和对应的装置还包括对所提取的运动轨迹特征进行编码，以及基于编码的运动轨迹特征来确定对象的运动的类型。

公开(公告)号：US20140254920A1

公开(公告)日：2014-09-11

申请号：US14199049

申请日：2014-03-06

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Kuanhong XU ,  Qiang WANG ,  Woo-young JANG ,  Ji-yeun KIM

IPC: G06T5/00

CPC classification number: G06T5/002 ,  G06T7/11 ,  G06T2207/20012

Abstract: A method of enhancing a quality of a 3 dimensional (3D) image includes classifying an input 3D image into a plurality of sub-areas based on noise characteristics of the plurality of sub-areas of the input 3D image, denoising each of the plurality of sub-areas of the input 3D image by using different denoising methods according to noise characteristics of each of the classified plurality of sub-areas and obtaining a second 3D image after the denoising, and enhancing a contrast ratio of the second 3D image after the denoising.

Abstract translation: 提高三维（3D）图像的质量的方法包括基于输入3D图像的多个子区域的噪声特性将输入3D图像分类为多个子区域，对多个子图像中的每一个进行去噪 通过使用根据分类的多个子区域中的每一个的区域的噪声特性使用不同的去噪方法并在去噪之后获得第二3D图像并且增强去噪后的第二3D图像的对比度，从而输入3D图像的子区域 。