Some content of this application is unavailable at the moment.
If this situation persist, please contact us atFeedback&Contact
1. (CN101527040) Method and system for processing images

Office : China
Application Number: 200810082736.2 Application Date: 05.03.2008
Publication Number: 101527040 Publication Date: 09.09.2009
Grant Number: 101527040 Grant Date: 19.12.2012
Publication Kind : B
IPC:
G06T 7/00
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
T
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
7
Image analysis, e.g. from bit-mapped to non bit-mapped
CPC:
G06T 7/0002
G06T2207/10016
G06T2207/20224
H04N 17/002
Applicants: Shenzhen Huawei Communication Technology Co., Ltd.
华为终端有限公司
Inventors: Li Kai
李凯
Liu Yuan
刘源
Agents: liu fang
北京同立钧成知识产权代理有限公司 11205
Priority Data:
Title: (EN) Method and system for processing images
(ZH) 图像处理方法及系统
Abstract: front page image
(EN) The embodiments of the invention relate to a method and a system for processing systems, wherein the method comprises the following steps: acquiring video images or capturing a series of frame images in real time; detecting the difference between front and back frame images, and retaining one of the frame images when the difference between the two frame images is smaller than a preset threshold value; performing characteristic information detection on the acquired frame images; and processing the frame images with characteristic information after the detection corresponding to definition, and retaining clear images according to a preset definition standard. The embodiments of the invention can solve the problems that a camera calibration method in the prior art cannot select proper clear images automatically, is inconvenient to use, needs a plurality of persons to finish, and the like, achieves automatic and real-time selection of effective images which have obvious characteristic information and can be used for calibration in the video images, and achieves the automation of a series of steps for processing the images.
(ZH)

本发明各实施例涉及一种图像处理方法及系统,其中,该方法包括:获取视频图像或实时捕获一系列帧图像;对前后两帧图像之间的差异进行检测,在两帧图像之间的差异小于预设阈值时,保留其中一帧图像;对获取的帧图像进行特征信息检测;对检测后具有特征信息的帧图像进行与清晰度相应的处理,并与预设的清晰度标准,保留清晰的图像。本发明各实施例可以解决现有技术中的摄像机标定方法不能自动选取合适清晰的图像、使用不便、需要多人完成等问题,实现自动、实时选取视频图像中有明显特征信息的、能参与标定的有效图像,实现图像处理的一系列步骤的自动化。