(3.236.214.19) 您好!臺灣時間:2021/05/09 22:11
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:::

: 
twitterline
研究生:李健榕
研究生(外文):Lee, Chienjung
論文名稱:基於小波轉換的超解析視訊影像重建技術
指導教授:賴文能賴文能引用關係李昌明李昌明引用關係
指導教授(外文):Lie, WennungLee, Changming
口試委員:詹寶珠賴文能李昌明葉家宏陳佳妍
口試委員(外文):Chung, PauchooLie, WennungLee, ChangmingYeh, ChiahungChen, Chiayen
口試日期:100/7/29
學位類別:碩士
校院名稱:國立中正大學
系所名稱:電機工程研究所
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:2011
畢業學年度:99
語文別:中文
論文頁數:56
中文關鍵詞:超解析離散小波轉換移動補償影像增強
相關次數:
  • 被引用被引用:0
  • 點閱點閱:331
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:54
  • 收藏至我的研究室書目清單書目收藏:0
隨著數位多媒體科技不斷的創新與進步,人們對於影像品質的要求不斷的提高,從早期的 DVD 演進到現在的 HD 和 Ultra HD ,都顯示出人們對於影像高解析的需求。高解析的視訊或影像具有高品質且豐富的色彩內容以及清晰的細節資訊,對於在數位相機、數位攝影機、醫學影像、衛星影像和監視系統等這些應用上有相當大的助益。經由影像擷取系統所得到的影像內容通常受到成像條件、成像因素與硬體限制等會使得影像遭受到破壞進而轉變成低解析的影像,然而透過超解析的恢復重建技術可以將低解析的影像重建出高解析的影像,因此本論文提出了基於小波轉換的超解析視訊重建技術。
本論文的研究重點主要探討:如何利用小波轉換將低解析的視訊重建出高解析的視訊內容。超解析重建最主要的問題是影像放大後高頻的部分會有所損失使得影像較為模糊,而小波轉換能有效的將視訊內容做頻率切割的處理,在不同的子頻帶上進行超解析的重建程序,比較能保留高頻的特性提高重建的品質。本文方法透過畫面間移動估測所產生的向量,讓每張低解析影像皆能重建出三張高解析影像,最後在小波頻域上進行融合,而形成一張高解析影像。
實驗結果顯示,利用本論文提出之方法所重建的高解析視訊內容的 PSNR相較於傳統的 Bicubic 內插方法高 0.9 ~ 1.2 dB,可有效提升視覺品質,特別是在較靜態視訊內容上,則有達 2.2 dB 的增益表現。

摘要 I
目錄 II
圖目錄 IV
表目錄 V
第一章 緒論 1
1.1 研究背景與動機 1
1.2 文獻回顧 2
1.3 論文架構說明 5
第二章 超解析相關理論 7
2.1 超解析恢復方法的發展 7
2.2 超解析恢復理論基礎 9
2.2.1觀察模型 9
2.2.2數學物理意義 10
2.3 基於學習的超解析恢復 12
2.4 基於重建的超解析恢復 12
第三章 基於重建理論的超解析恢復方法 14
3.1 頻率域的超解析重建 14
3.2 空間域的超解析重建 14
3.3 超解析重建演算法性能比較 20
第四章 基於小波轉換的超解析視訊重建 22
4.1 相關背景 22
4.1.1 內插放大 22
4.1.2 小波轉換 26
4.1.3 移動估測與移動補償 27
4.2 權重式移動補償結合高頻差值 29
4.2.1 權重式移動補償 30
4.2.2 小波差值係數 32
4.3 小波係數融合 34
第五章 實驗結果與分析 37
5.1 權重式移動補償實驗結果 37
5.2 本論文所提超解析視訊重建實驗結果與分析 38
5.2.1 未壓縮原始視訊影像實驗 39
5.2.2 MPEG-2壓縮視訊實驗 48
第六章 結論與未來工作 52
6.1 結論 52
6.2 未來工作 52
參考文獻 53
[1]http://tw.renesas.com/
[2]S.C. Park, M.K. Park, and M.G. Kang, “Super-resolution image reconstruction: a technical overview,” IEEE Signal Processing Magazine, Vol. 20, No. 3, pp. 21-36, May 2003.
[3]F. Brandi, R. de Queiroz and D. Mukherjee, “Super-resolution of Video Using Key Frames and Motion Estimation,” Proc. of IEEE Int’l Conf. on Image Processing, (ICIP-2008) , San Diego,CA, USA, Oct. 2008.
[4]K .Simonyan, S. Grishin, D. Vatolin and D. Popov, “Fast video superresolution via classification,” Proc. of IEEE Int’l Conf. on Image Processing, (ICIP-2008) , San Diego,CA, USA, Oct. 2008.
[5]S.V. Basavaraja , A.S. Bopardikar, and S. Velusamy, “Detail warping based video super-resolution using image guides, ” Proc. of IEEE Int. Conf. on Image Processing (ICIP-2010), Hong Kong, China, Sept. 2010.
[6] K.W. Hung and W.C. Siu, “New motion compensation model via frequency classification for fast video super-resolution,” Proc. of IEEE Int’l Conf. on Image Processing (ICIP-2009), Cairo, Egypt, Nov. 2009
[7] A . Temizel, and T. Vlachos, “Wavelet domain image resolution enhancement,” IEE Proceedings Vision, Image and Signal Processing, Vol. 153, No. 1, pp 25-30, Feb. 2006.
[8] H. Zheng, A. Bouzerdoum, and S.L. Phung, “Wavelet base nonlocal-mean super-resolution for video sequences,” Proc. of IEEE Int’l Conf. on Image Processing, (ICIP-2010) , Hong Kong, China, Sept. 2010.
[9] H. Demirel, G. Anbarjafari, and S. Izadpanahi, “improved motion-based localized super resolution Technique using discrete wavelet transform for low resolution video enhancement,” Proc of. Conf .on European Signal Processing., (EUSIPCO-2009), Glasgow, Scotland, Aug. 2009.
[10]G. Anbarjafari and H. Demirel, “Image super resolution based on interpolation of wavelet domain high frequency subbands and the spatial domain input image,” Electronics and Telecommunications Research Institute (ETRI) Journal, Vol. 32, No. 3, pp. 390-394, Jun. 2010.
[11]H. Demirel and G. Anbarjafari, “Image resolution enhancement by using discrete and stationary wavelet decomposition,” IEEE Trans. on Image Processing, Vol. 20, No. 5, pp. 1458-1460, May 2011.
[12]R.Y. Tsai and T.S. Huang, “Multiframe image restoration and registration,” Advances in Computer Vision and Image Processing, Vol. 1, No. 2, pp. 317–339, 1984.
[13]A.K. Katsaggelos, R. Molina, and J. Mateos, Super Resolution of Image and Video , Morgan & Claypool, USA,2007.
[14]K.R. Castleman, Digital Image Processing, Prentice-Hall, Englewood Cliffs, NJ, 1996.
[15]S. Farsiu , M.D. Robinson , M. Elad and P. Milanfar, “Fast and robust multi-frame super resolution,” IEEE Trans. on Image Processing , Vol.13, No. 10, pp. 1327-1344, Oct. 2004.
[16]R.R. Schultz and R.L. Stevenson, “Extraction of High-resolution Frame from Video Sequence,” IEEE Trans. on Image Processing, Vol. 5, No. 6, pp. 996-1011, June 1996.
[17]A. Buades, B. Coll, and J.M. Morel, “A non local algorithm for image denoising, ” Proc. of IEEE Int’l Conf. on Computer Vision and Pattern Recognition (CVPR-2005), San Diego, CA, USA, June 2005.
[18]H.A. Aly and E. Dubois, “Image up-sampling using total-variation regularization with a new observation model, ” IEEE Trans. on Image Process, Vol. 14, No. 10, pp. 1647-1659, Oct. 2005.
[19]S. Farsiu, M. Elad, and P. Milanfar, “Multi-Frame Demosaicing and Super-Resolution of Color Images, ” IEEE Trans. on Image Processing, Vol. 15, No. 1, pp. 141-159, Jan. 2006.
[20]W.T. Freeman, T.R. Jones, and E.C. Pasztor, “Example-Based Super-Resolution”, Proc. of IEEE Int’l Conf. on Computer Graphics and Applications (PG-2002), Beijing, China, Oct. 2002.
[21]K. Watanabe, Y. Iwai, T. Haga, and M. Yachida, “A fast algorithm of video super-resolution using dimensionality reduction by DCT and example selection,” Proc. of IEEE Int’l. Conf. on Pattern Recognition (ICPR-2008), Tampa, FL , USA, Dec. 2008.
[22]S. Baker and T. Kanade , “Limits on super-resolution and how to break them , ” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 24, No. 9, pp. 1167-1183,Sept. 2002.
[23]S.P. Kim, N.K. Bose and H.M. Valenzuela, “Recursive reconstruction of high resolution image from noisy undersampled multiframes,” IEEE Trans. on Acoustics, Speech, and Signal Processing, Vol. 38, No. 6, pp. 1013-1027, June 1990.
[24]H. Ur and D. Gross, “Improved resolution from sub-pixel shifted pictures,”CVGIP: Graphical Models and Image Processing, Vol. 54, pp. 181-186, Mar.1992.
[25]B.K. Wan, L. Meng, D. Ming, H.Z Qi, Y. Hu and K. Luk, “Video Image Super-resolution Restoration Based on Iterative Back-Projection Algorithm,” Proc of. Conf . on Computational Intelligence for Measurement Systems and Applications (CIMSA-2009), Hong Kong, China, May. 2009.
[26]A.J. Patti, M.I. Sezan, and A.M. Tekalp, “Superresolution video reconstruction with arbitrary sampling lattices and nonzero aperture time,” IEEE Trans. on Image Processing, Vol. 6, No. 8, pp. 1064-1076, Aug. 1997.
[27]W. Zhang and W.K. Cham, “High Quality Artifact-Free Super-Resolution,” Proc. of IEEE Int’l Conf. on Image Processing (ICIP-2010), Hong Kong, China, Sept. 2010.
[28]S.P. Belekos, N.P. Galatsanos, and A.K. Katsaggelos, “Maximum a Posteriori Video Super-Resolution Using a New Multichannel Image Prior,” IEEE Trans. on Image Processing, Vol. 19,No.6, pp.1451-1464, June 2010.
[29]R.R. Schultz and R.L. Stevenson, “A Bayesian approach to image expansion for improved definition,” IEEE Trans. on Image Processing, Vol. 3, No. 3, pp. 233-242, May. 1994.
[30]X.L. Zhang, K.M. Lam and L.S. Shen, “Image magnification based on a blockwise adaptive Markov random field model,” Image and Vision Computing, Vol. 26, No. 9, pp. 1277-1284, Sept. 2008.
[31]M. Elad and A. Feuer, “Superresolution restoration of an image sequence: Adaptive filtering approach,” IEEE Tran.on Image Processing, Vol. 6, No. 12. pp. 1646-1658. March. 1999.
[32]R Hardie, “A Fast Image Super-Resolution Algorithm Using an Adaptive Wiener Filter,” IEEE Tran.on Image Processing,Vol. 16, No. 12, pp. 2953-2964. DEC. 2007.
[33]B.B. Ready, C.N. Taylor and R.W. Beard, “A Kalman-filter Based Method for Creation of Super-resolved Mosaicks,” Proc. of IEEE Int’l Conf. on Robotics and Automation (ICRA-2006), Orlando, FA, USA. May. 2006.
[34]R. Keys,“Cubic convolution interpolation for digital image processing,” IEEE Tran. on Signal Processing, Acoustics, Speech, and Signal Processing, Vo.29, No.6 , pp.1153–1160, Dec 1981.
[35]C.E. Duchon, “Lanczos Filtering in One and Two Dimensions,” Journal of Applied Meteorology, Vol. 18, No. 8, pp.1016-1022, Aug. 1979.
[36]謝東成,保留邊緣特性之影像放大方法,國立臺灣科技大學電機工程學系碩士論文,中華民國九十五年七月
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔