跳到主要內容

臺灣博碩士論文加值系統

(3.95.131.146) 您好!臺灣時間:2021/07/26 04:26
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:高健祐
研究生(外文):Chien-Yu Kao
論文名稱:動態視訊接圖系統
論文名稱(外文):A Dynamic Scene Registration System
指導教授:林啟芳
學位類別:碩士
校院名稱:元智大學
系所名稱:資訊工程學系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2009
畢業學年度:97
語文別:中文
論文頁數:52
中文關鍵詞:影像接圖視訊接圖全景影像
外文關鍵詞:Image RegistrationVideo MosaicPanorama Image
相關次數:
  • 被引用被引用:1
  • 點閱點閱:211
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
本論文提出一個動態視訊接圖方法,可針對具有移動物體之動態視訊影像進行接合。所提方法主要分為兩階段,分別為校正階段及操作階段。校正階段針對攝影機進行校正,首先我們以平均值(mean)模擬中位數值(median)的方法分別建立左、右視訊畫面穩定背景,並利用Powell方向集方法在穩定背景上找出左、右視訊重疊區域與旋轉角度後校正右攝影機的角度(本論文固定左攝影機,而對右攝影機進行校正)。右旋轉角度若過大(我們限定在 之內),使用者必須以手動方式調整右攝影機擺放角度。若旋轉角度在容忍範圍內,則針對重疊區域找出特徵點,以特徵點的對應關係換算出左、右視訊的轉換矩陣,並經由反轉換矩陣(inverse matrix)對全景圖之接縫處右邊的每一點像素建立出接合遮罩(mask),於操作階段快速接合使用。操作階段時,同樣對左、右視訊分別取得穩定背景後,先進行前、背景的分離處理(在本論文中所要分離出的前景是針對有跨越接縫線的前景)。之後將左、右視訊完整畫面,透過前一階段所建立之接合遮罩進行快速接合。至於前景部分,在左、右視訊畫面接合後將其重新置入,最後輸出完整之全景圖。實驗結果顯示本論文所提方法可解決動態視訊接圖問題。
A dynamic scene registration system is presented in this paper, which can be utilized to register two sequences of video images with moving objects. Firstly, calibration stage focus on the adjustment in view of the camera and find the register mask. Secondly, in operation stage, we use register mask to register two video images rapidly. After registering two images, we use post-processing to deal with the foreground which is across register line. Finally, we output the panorama image as result. Experiments are arranged for demonstrating the feasibility of the proposed approach.
中文摘要 ii
英文摘要 iii
致謝 iv
目錄 v
圖目錄 vii
第一章 序論 1
1.1 研究動機 1
1.2 相關研究瀏覽 1
1.3 所提方法概述 4
1.4 論文架構 5
第二章 接圖方法基本觀念 6
2.1 基本接圖概念 6
2.2 正規化相關匹配法(Normalized Cross Correlation;NCC) 8
2.3 Powell方向集(Powell direction set) 9
2.4 Harris角落檢測(Harris corner detector) 10
2.5 一致性隨機取樣(RANdom SAmple Consensus;RANSAC) 12
2.6 穩定背景擷取方法 13
2.7接圖系統流程介紹 14
第三章 所提方法詳述 17
3.1校正階段 17
3.1.1亮度正規化 18
3.1.2建立左、右視訊之穩定背景 18
3.1.3校正右攝影機之旋轉角度 21
3.1.4計算接合參數 21
3.1.5 建立接合遮罩 23
3.2操做階段 24
3.2.1 建立左、右視訊之穩定背景 25
3.2.2修正轉換矩陣 25
3.2.3 前景分離處理 26
3.2.4利用接合遮罩快速接合 27
3.2.5前景重新置入處理 27
第四章 實驗結果 31
4.1 實驗設備與環境 31
4.2 實驗結果 31
第五章 結論與未來研究 50
5.1 結論 50
5.2 未來研究方向 50
參考文獻 51
[1]R. Szeliski, “Image Mosaicing for Tele-Reality Applications,” Proceeding of the Second IEEE Workshop on Applications of Computer Vision, pp. 44-53, 1994.
[2]R. C. Gonzales, and R. E. Woods, Digital Image Processing, Addison-Wisley, 1992.
[3]B. Hu, C. Brown, and A. Choi, “Acquiring an environment map through image mosaicking,” tech. rep., Computer Science Department, University of Rochester, 2001.
[4]B. Srinivasa Reddy and B. N. Chatterji, “An FFT-Based Technique for Translation, Rotation, and Sacle-Invariant Image Registration”, IEEE Trans. Image Processing, Vol. 5, No. 8, pp. 1271-1276, 1996.
[5]Q. Zheng and R. Chellapa, “A computational vision approach to image registration”, IEEE Trans. Image Processing, Vol. 2, No. 3, pp. 311-326, 1993.
[6]P. Bao and D. Xu, “Complex wavalet-based image mosaics using edge-preserving visual perception modeling,” Computer & Graphics, Vol. 23, pp. 309-321, 1999.
[7]Z. P. Liang, H. Pan, R. L. Magin, N. Ahuja and T. S. Huang. “Automated Image Registration by Maximization of a Region Similarity Metric,” Image Processing, 1997. Proceedings, International Conference, Vol. 3, pp. 272-275, 1997.
[8]Z. Zhu, G. Xu, E. M. Riseman, and A. R. Hanson “Fast Generation of Dynamic and Multi-Resolution Panorama from Video Sequence,” IEEE Multimedia System, Vol. 1,pp. 400-406, 1999.
[9]C. F. Lin and S. C. Sung, “A featureless image registration method with high accuracy,” Thesis of the institute of Electrical Engineering and Computer Engineering and Science, Yuan-Ze University, 2000.
[10]R. Szeliski, “Video mosaics for virtual environments,” IEEE Computer Graphic and Application, pp. 22-30, 1996.
[11]W. K. Tang, T. T. Wong, and P. A. Heng, “A system for real-time panorama generation and display in tele-immersive applications,” IEEE Trans. Multimedia, Vol. 7, No. 2, pp. 208-292, 2005.
[12]C. Dai, Y. Zheng, and X. Li, “Accurate video alignment using phase correlation” IEEE Signal Processing Letters, Vol. 13, No.12, 737-740, 2006.
[13]H. Nicolas, “New methods for dynamic mosaicking,” IEEE Trans. Image Processing, Vol. 10, No. 8, pp. 1239-1251, 2001.
[14]S. J. Ha, S. H. Lee, N. I. Cho, S. K. Kim, and B. Son, “Embedded panoramic mosaic system using auto-shot interface,” IEEE Trans. Consumer Electronics, Vol. 54, No. 1, 16-24, 2008.
[15] Pratt, W.K, Digital Image Processing, 2nd, Wiley, New York, 1991.
[16] Moravec, and H.P, “Towards Automatic Visual Obstacle Avoidance,” International Joint Conference of Artificial Intelligence, Vol. 1, Tokyo, 1977.
[17] Harris C, and M. Stephens, “A combined corner and edge detector,” Proceedings of the 4th Alvey vision conference, pp. 147-151, 1988.
[18] M. Fischler, and R. Bolles, “Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography,” Communications of the ACM, 24:381-385, 1981.
[19] R. C. Bolles and M. A. Fischler, “A ransac-based approach to model fitting and its application to finding cylinders in range data,” Proc. 6th International Joint Conf. on Artificial Intelligence, pages 637–643, Canada, August 1981.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top