公开(公告)号：US09542748B2

公开(公告)日：2017-01-10

申请号：US14646656

申请日：2013-04-08

Applicant: LSI Corporation

Inventor： Ivan Leonidovich Mazurenko ,  Pavel Aleksandrovich Aliseitchik ,  Alexander Borisovich Kholodenko ,  Denis Vasilyevich Parfenov ,  Denis Vladimirovich Parkhomenko

IPC: G06K9/56 ,  G06T7/00 ,  G06K9/00 ,  G06F3/01 ,  G06K9/46 ,  G06K9/62

CPC classification number: G06T7/11 ,  G06F3/017 ,  G06K9/00375 ,  G06K9/46 ,  G06K9/6218 ,  G06K2009/4666 ,  G06T7/194 ,  G06T7/50 ,  G06T2207/10028

Abstract: Systems and methods for image processing may perform one or more operations including, but not limited to: receiving raw image data from at least one imaging device; computing at least one image depth distance from the raw image data; computing one or more image validity flags from the raw image data; generating at least one data validity mask from the one or more image validity flags; determining a background imagery estimation from at least one image depth distance; generating at least one foreground mask from the background imagery estimation and the at least one image depth distance; generating at least one region-of-interest mask from the data validity mask and the foreground mask; and generating filtered raw image data from the raw image data and at least one region of interest mask.

Abstract translation: 用于图像处理的系统和方法可以执行一个或多个操作，包括但不限于：从至少一个成像设备接收原始图像数据; 计算与原始图像数据的至少一个图像深度距离; 从原始图像数据计算一个或多个图像有效性标志; 从所述一个或多个图像有效性标志生成至少一个数据有效性掩码; 从至少一个图像深度距离确定背景图像估计; 从所述背景图像估计和所述至少一个图像深度距离中生成至少一个前景蒙版; 从数据有效性掩码和前景掩码生成至少一个感兴趣的区域掩模; 以及从原始图像数据和至少一个感兴趣区域掩模生成滤波后的原始图像数据。

公开(公告)号：US20150242681A1

公开(公告)日：2015-08-27

申请号：US14424953

申请日：2013-04-16

Applicant: LSI Corporation

Inventor： Pavel Aleksandrovich Aliseitchik ,  Denis Vladimirovich Zaytsev ,  Denis Vasilyevich Parfenov ,  Aleksey Alexandrovich Letunovskiy ,  Dmitry Nicolaevich Babin

IPC: G06K9/00 ,  G06T1/60

CPC classification number: G06K9/00335 ,  G06F3/042 ,  G06K9/00973 ,  G06K9/4604 ,  G06K2009/4666 ,  G06T1/60

Abstract: The disclosure is directed to a system and method of image processing. According to various embodiments of the disclosure, a storage module in communication with a plurality of memory banks stores a plurality of pixels of an image in the memory banks and interleaves the memory banks to enable a plurality of image scanners to access the plurality of pixels. A scanning module scans a selection of pixels in at least four directions relative to a first pixel of the plurality of pixels utilizing the plurality of image scanners. A singular points detection module in communication with the scanning module acquires a depth of each pixel of the selection of scanned pixels and determines a singularity value of the first pixel by comparing the depth of the first pixel with the depth of each pixel of the selection of pixels.

Abstract translation: 本公开涉及一种图像处理系统和方法。 根据本公开的各种实施例，与多个存储体通信的存储模块将多个像素的像素存储在存储体中，并交织存储体，以使得多个图像扫描器能够访问多个像素。 扫描模块利用多个图像扫描仪扫描相对于多个像素中的第一像素的至少四个方向的像素选择。 与扫描模块通信的奇点检测模块获取扫描像素的选择的每个像素的深度，并且通过将第一像素的深度与选择的每个像素的深度进行比较来确定第一像素的奇异值 像素。