期刊目錄列表 - 47卷第1期(2002.4) - 【數理與科技類】47(1)
Directory

影像穩定化技術在智慧型運輸系統的應用
作者:梁祐銘(國立臺灣師範大學資訊教育學系)、陳世旺(國立臺灣師範大學資訊工程學系)、廖弘源(中央研究院資訊科學所)

卷期:47卷第1期
日期:2002年4月
頁碼:87-100
DOI:10.6301/JNTNU.2002.47(1).05

摘要:

本論文針對影像視覺在智慧型運輸系統的應用,提出影像穩定化(image stabilization) 的技術。本研究主要目的在補償固定型交通監控系統之攝影器材因晃動而造成不穩的影像序列。在固定型影像穩定化技術中,可以分成三步驟:運動的估算(motion estimation),總體運動的分析(global motion analysis)及影像的補償(image compensation)。我們提出k 階投射比對(k-order projection matching)方法,結合方塊比對(block matching)來作運動的估算,前者可以解決當影像含有小角度旋轉的時候,仍可精確地估測運動速度;在第二步驟中我們利用仿射運動模組(affine motion model)來作整體運動的分析,以解決影像含有位移及旋轉的情形;最後利用運動模組的反轉換來還原不穩的影像序列。利用模擬影像及真實影像的實驗結果皆顯示本文所提的技術之可應用性。

關鍵詞:影像穩定化、運動的估算、總體運動的分析、影像的補償、k階投射比對、方塊比對與仿射運動模組

《詳全文》

中文APA引文格式梁祐銘、陳世旺、廖弘源(2002)。影像穩定化技術在智慧型運輸系統的應用。師大學報:數理與科技類47(1),87-100。doi:10.6301/JNTNU.2002.47(1).05
APA FormatLiang, Y.-M., Chen, S.-W., & Liao, M. H.Y.(2002). Image Stabilization for ITS Applications. Journal of National Taiwan Normal University: Mathematics, Science & Technology, 47(1), 87-100. doi:10.6301/JNTNU.2002.47(1).05

Journal directory listing - Volume 47 Number 1 (2002/April) - Mathematics, Science & Technology【47(1)】
Directory

Image Stabilization for ITS Applications
Author: You-Ming Liang(Department of Information and Computer Education,National Taiwan Normal University),Sei-Wang Chen(Department of Computer Science and Information Engineering,National Taiwan Normal University), H. Y. Mark Liao(Institute of Information,Science Academia)

Vol.&No.:Vol. 47, No. 1
Date:April 2002
Pages:87-100
DOI:10.6301/JNTNU.2002.47(1).05

Abstract:

In this paper, we propose an image stabilization technique for stabilizing image sequences taken from traffic monitoring cameras. The proposed technique includes three steps: motion estimation, global motion analysis, and image compensation. In the motion estimation, a module combining block matching and k-order projection matching is evoked to estimate motions between two successive images. The process will estimate motions accurately even though there exists rotations between images. In the global motion analysis, an affine motion model is utilized to determine the parameters of translation and rotation between images. The determined affine transformation is then exploited to compensate for the unstabilities of input image sequences. The experimental results of using both simulated and real images have revealed the applicability of the proposed technique..

Keywords:Image Stabilization, Motion Estimation, Global Motion Analysis, Image Compensation, K-order projection matching, Block matching and affine motion model