公开(公告)号：US20150023585A1

公开(公告)日：2015-01-22

申请号：US14054816

申请日：2013-10-15

Applicant: NOVATEK Microelectronics Corp.

Inventor： Lei Zhou ,  Guangzhi Liu ,  Cheng-Wei Chou

IPC: G06F17/30

CPC classification number: G06F17/30244

Abstract: A matching search method is utilized for performing a matching search from a first image block to a second image block in a stereo matching system. The matching search method includes obtaining a global offset of the first image block corresponding to the second image block according to an offset relationship between a first image data of the first image block and a second image data of the second image block; and performing the matching search from the first image block to the second image block according to the global offset and a searching range.

Abstract translation: 一种匹配的搜索方法用于在立体匹配系统中执行从第一图像块到第二图像块的匹配搜索。 匹配搜索方法包括根据第一图像块的第一图像数据和第二图像块的第二图像数据之间的偏移关系获得与第二图像块相对应的第一图像块的全局偏移; 以及根据全局偏移量和搜索范围，从第一图像块到第二图像块执行匹配搜索。

公开(公告)号：US09042638B2

公开(公告)日：2015-05-26

申请号：US14033515

申请日：2013-09-22

Applicant: NOVATEK Microelectronics Corp.

Inventor： Lei Zhou ,  Guangzhi Liu ,  Cheng-Wei Chou

IPC: G06K9/00

CPC classification number: G06K9/00536 ,  G06K9/00201 ,  G06K9/6202 ,  G06T7/593 ,  G06T2207/20021

Abstract: An image matching method is utilized for performing a stereo matching from a first image block to a second image block in a stereo matching system. The image matching method includes performing a matching computation from the first image block to the second image block according to a first matching algorithm to generate a first matching result; performing the matching computation between the first image block and the second image block according to a second matching algorithm to generate a second matching result and a third matching result; obtaining a matching error and a matching similarity of the first image block according to the second matching result and the third matching result; and determining a stereo matching result of the first image block according to the matching error and the matching similarity.