| Two new approaches for image registration based onspatial-temporal relationship |
| |
| 引用本文： | Deng Zhipeng,Yang Jie & Liu XiaojunInstitute of Image Processing & Pattern Recognition,Shanghai Jiaotong University,Shanghai 200030,P. R. China. Two new approaches for image registration based onspatial-temporal relationship[J]. 系统工程与电子技术(英文版), 2005, 16(2) |
| |
| 作者姓名： | Deng Zhipeng Yang Jie & Liu XiaojunInstitute of Image Processing & Pattern Recognition Shanghai Jiaotong University Shanghai 200030 P. R. China |
| |
| 作者单位： | Deng Zhipeng，Yang Jie & Liu XiaojunInstitute of Image Processing & Pattern Recognition，Shanghai Jiaotong University，Shanghai 200030，P. R. China |
| |
| 基金项目： | ThisprojectwassupportedbytheNationalNaturalScienceFoundationofChina(30170274). |
| |
| 摘 要： | 1.INTRODUCTION Registrationisafundamentaltaskinimageprocessing usedtomatchtwoormorepicturestaken,forexam ple,atdifferenttimes,fromdifferentsensors,and becauseofthese,thepicturesmaybedistorted,de formed,andsoon.Overtheyears,manymethods havebeendevelopedforthevarioustypesofdataand problems;theregistrationmethodscanbelooselydi videdintothreegroups.(1)Normalizedcross correlation:Itisthebasic statisticalapproachtoregistrationbasedontheinten sitiesofpixels[1],andisusedfortemplatematching.(2)Pha…
|
Two new approaches for image registration based on spatial-temporal relationship |
| |
| Deng Zhipeng,Yang Jie,Liu Xiaojun. Two new approaches for image registration based on spatial-temporal relationship[J]. Journal of Systems Engineering and Electronics, 2005, 16(2) |
| |
| Authors: | Deng Zhipeng Yang Jie Liu Xiaojun |
| |
| Affiliation: | Institute of Image Processing & Pattern Recognition, Shanghai Jiaotong University, Shanghai 200030, P. R. China |
| |
| Abstract: | How to improve the probability of registration and precision of localization is a hard problem, which is desiderated to solve. The two basic approaches (normalized cross-correlation and phase correlation) for image registration are analysed, two improved approaches based on spatial-temporal relationship are presented. This method adds the correlation matrix according to the displacements in x- cirection and y- directions, and the registration pose is searched in the added matrix. The method overcomes the shortcoming that the probability of registration decreasing with area increasing owing to geometric distortion, improves the probability and the robustness of registration. |
| |
| Keywords: | image registration phase correlation normalized cross-correlation spatial-temporal relationship. |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
