跳到主要內容

臺灣博碩士論文加值系統

(3.236.84.188) 您好!臺灣時間:2021/08/01 19:14
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:張浩軒
研究生(外文):Hao-Hsuan Chang
論文名稱:運用手機加速規之影像去模糊技術
論文名稱(外文):Image Deblurring by Accelerometers of Mobile Phones
指導教授:丁建均丁建均引用關係
口試委員:盧奕璋曾易聰簡鳳村
口試日期:2015-07-24
學位類別:碩士
校院名稱:國立臺灣大學
系所名稱:電信工程學研究所
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:2015
畢業學年度:103
語文別:英文
論文頁數:97
中文關鍵詞:影像去模糊盲反卷積問題點擴散函數/運動模糊函數估計慣性測量感應器
外文關鍵詞:Image DeblurringBlind DeconvolutionPower Spread Function (PSF)/Motion Blur Kernel EstimationInertial Measurement Sensors
相關次數:
  • 被引用被引用:0
  • 點閱點閱:137
  • 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
數位相機與智慧型手機越來越普遍,由於相機技術的進步,它們也相當容易操作,然而模糊的相片依然是一個尚待解決的問題。模糊相片通常發生於使用者拍照時晃動到相機,在長曝光時間或低環境光源的情況下特別容易發生。影像去模糊是一種將模糊影像還原成清晰且視覺上可接受的相片的技術。影像去模糊技術分為相當多種,近年來的技術著重在兩主要步驟:估計模糊函數和影像重建。之前的研究證實在影像邊緣的區域,估計模糊函數的效果會比在影像平滑的區域更佳。
在本篇論文中,我們利用手機加速規(accelerometer)的資訊估計模糊函數,透過手機加速規的資訊輔助,估計模糊函數的精準度可以顯著的增加。這類利用特殊硬體設備在相機上輔助影像去模糊的研究以前也曾出現過,我們和之前的方法最大的不同在於:我們結合手機加速規的資訊和盲反卷積(blind deconvolution)的演算法。我們所提出的新方法介於盲反卷積和非盲反卷積(non-blind deconvolution)方法之間,因此我們稱它為半盲反卷積(semi-blind deconvolution)。我們提出方法的去模糊效果勝過其他當今最先進的盲卷積影像方法或只用加速規資訊的影像去模糊。

Digital cameras and smart phones have become more common than before. They are simpler to operate due to the advance of the camera technology. However, blurring remains an unsolved problem. This often occurs when users sway the camera while taking photos, especially with long exposure time or in a low-light environment. Image deblurring is the method of reconstructing a sharp and visually plausible image from a blurred image. Image deblurring methods have different types, but recent deblurring approaches focus on two main stages: blur kernel estimation and image restoration. Previous studies have proved that blur kernel estimation algorithms perform better on the edge part of an image than on smooth part.
In this thesis, we make use of the accelerometer in the cellphone to estimate the blur kernel. The accuracy of blur kernel estimation is significantly improved with the additional information of the accelerometer. Deblurring with the special hardware on the camera has also shown before. The main difference between our method and previous methods is that we blend the information of the accelerometer into blind deconvolution algorithms. This new method is an intermediate of blind deconvolution and non-blind deconvolution, so we call it semi-blind deconvolution. The deblurring results by our method surpass other state-of-the-art blind deconvolution methods or deblurring by accelerometers in real data.

口試委員會審定書 #
誌謝 i
中文摘要 ii
ABSTRACT iii
CONTENTS iv
LIST OF FIGURES vi
LIST OF TABLES xiii
Chapter 1 Introduction 1
1.1 Motivation 1
1.2 Background 1
1.3 Organization 4
Chapter 2 Non-Blind and Blind Deconvolution 5
2.1 Non-Blind Deconvolution 6
2.1.1 Direct Inverse Filter 6
2.1.2 Wiener Deconvolution 8
2.1.3 Richardson-Lucy Deconvolution 11
2.1.4 MAP Estimation 15
2.1.5 Image Priors 16
2.1.6 Fast Deconvolution using Hyper-Laplacian Priors 18
2.2 Blind Deconvolution 18
2.2.1 MAP Approaches 20
2.2.2 Kernel estimation in different regions 23
Chapter 3 Review of Existing Deblurring Methods using Inertial Sensors 28
3.1 Capturing Multiple Images 29
3.1.1 Multichannel Blind Deconvolution 29
3.1.2 Spatial Resolution and Temporal Resolution trade-off 30
3.2 Recovering Camera Motion by Inertial Sensors 37
3.2.1 Image Deblurring using Inertial Measurement Sensors 37
3.3 Combined Method of Multiple Images and Inertial Sensors 45
3.4 Summary 49
Chapter 4 Proposed Image Deblurring Method 51
4.1 Observation 52
4.2 Framework 54
4.3 The Initial Estimated Blur Kernel by Accelerometers 56
4.4 Image Regions Selected by Assistance of Accelerometers 57
4.5 The First kernel_blind Estimation 61
4.6 The Second kernel_blind Estimation 62
4.7 kernel_final Estimation by RadonMAP 67
4.8 Experimental Results 73
4.9 Comparison with Blind Deconvolution Methods 87
Chapter 5 Conclusion and Future Work 92
5.1 Conclusions 92
5.2 Future work 93
REFERENCE 94

A. Non-Blind Deconvolution
[1]Levin, A., Fergus, R., Durand, F., & Freeman, W. T. "Image and depth from a conventional camera with a coded aperture." ACM Transactions on Graphics (TOG). Vol. 26. No. 3. ACM, 2007. p. 70.
[2]Krishnan, D., & Fergus, R. "Fast image deconvolution using hyper-Laplacian priors." Advances in Neural Information Processing Systems. 2009. p. 1033-1041.

B. Blind Deconvolution
[3]Fergus, R., Singh, B., Hertzmann, A., Roweis, S. T., & Freeman, W. T. "Removing camera shake from a single photograph." ACM Transactions on Graphics (TOG) 25.3 (2006): 787-794.
[4]Levin, A., Weiss, Y., Durand, F., & Freeman, W. T. "Understanding and evaluating blind deconvolution algorithms." Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on. IEEE, 2009. p. 1964-1971.
[5]Joshi, N., Szeliski, R., & Kriegman, D. J. "PSF estimation using sharp edge prediction." Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on. IEEE, 2008. p. 1-8.
[6]Hu, Z., & Yang, M. H. "Good regions to deblur." Computer Vision–ECCV 2012. Springer Berlin Heidelberg, 2012. 59-72.
[7]Levin, A., Weiss, Y., Durand, F., & Freeman, W. T. "Efficient marginal likelihood optimization in blind deconvolution." Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on. IEEE, 2011. p. 2657-2664.
[8]Cho, T. S., Zitnick, C. L., Joshi, N., Kang, S. B., Szeliski, R., & Freeman, W. T. "Image restoration by matching gradient distributions." Pattern Analysis and Machine Intelligence, IEEE Transactions on 34.4 (2012): 683-694.
[9]Xu, L., & Jia, J. "Two-phase kernel estimation for robust motion deblurring." Computer Vision–ECCV 2010. Springer Berlin Heidelberg, 2010. 157-170.
[10]Cho, S., & Lee, S. "Fast motion deblurring." ACM Transactions on Graphics (TOG). Vol. 28. No. 5. ACM, 2009. p. 145.
[11]Krishnan, D., Tay, T., & Fergus, R. "Blind deconvolution using a normalized sparsity measure." Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on. IEEE, 2011. p. 233-240.
[12]Cho, T. S., Paris, S., Horn, B. K., & Freeman, W. T. "Blur kernel estimation using the radon transform." Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on. IEEE, 2011. 241-248.
[13]Shan, Q., Jia, J., & Agarwala, A. "High-quality motion deblurring from a single image." ACM Transactions on Graphics (TOG). Vol. 27. No. 3. ACM, 2008. p. 73.
[14]Goldstein, A., & Fattal, R. "Blur-kernel estimation from spectral irregularities." Computer Vision–ECCV 2012. Springer Berlin Heidelberg, 2012. 622-635.

C. Deblurring with Inertial Measurement Sensors
[15]Nayar, S. K., & Ben-Ezra, M. "Motion-based motion deblurring." Pattern Analysis and Machine Intelligence, IEEE Transactions on 26.6 (2004): 689-698.
[16]Tai, Y. W., Du, H., Brown, M. S., & Lin, S. "Correction of spatially varying image and video motion blur using a hybrid camera." Pattern Analysis and Machine Intelligence, IEEE Transactions on 32.6 (2010): 1012-1028.
[17]Tai, Y. W., Tan, P., & Brown, M. S. "Richardson-lucy deblurring for scenes under a projective motion path." Pattern Analysis and Machine Intelligence, IEEE Transactions on 33.8 (2011): 1603-1618.
[18]Yuan, L., Sun, J., Quan, L., & Shum, H. Y. "Image deblurring with blurred/noisy image pairs." ACM Transactions on Graphics (TOG) 26.3 (2007): 1.
[19]Joshi, N., Kang, S. B., Zitnick, C. L., & Szeliski, R. "Image deblurring using inertial measurement sensors." ACM Transactions on Graphics (TOG). Vol. 29. No. 4. ACM, 2010. p. 30.
[20]Şroubek, F., & Flusser, J. "Multichannel blind deconvolution of spatially misaligned images." Image Processing, IEEE Transactions on 14.7 (2005): 874-883.
[21]Park, S. H., & Levoy, M. "Gyro-based multi-image deconvolution for removing handshake blur." Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on. IEEE, 2014. p. 3366-3373.

D. Theorems and Mathematics
[22]Dempster, A. P., Laird, N. M., & Rubin, D. B. "Maximum likelihood from incomplete data via the EM algorithm." Journal of the royal statistical society. Series B (methodological) (1977): 1-38.
[23]R. C. Gonzalez, R. E. Woods, Digital Image Processing second edition, Prentice Hall, 2002.
[24]Hasinoff, S. W., Durand, F., & Freeman, W. T. "Noise-optimal capture for high dynamic range photography." Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on. IEEE, 2010. p. 553-560.
[25]Kalman, R. E. "A new approach to linear filtering and prediction problems." Journal of Fluids Engineering 82.1 (1960): 35-45.
[26]Deans, S. R. The Radon transform and some of its applications. Courier Corporation, 2007.


QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
1. 1. 方嘉麟,利害關係人交易問題探討~兼論信託財產運用之限制,月旦法學雜誌第90期,頁8-33,2002年11月。
2. 2. 王進祥,不動產證券化法制與信託登記機制之研析(一),現代地政271期.人與地240期,頁35-42,2004年1月。
3. 3. 王進祥,不動產證券化法制與信託登記機制之研析(二),現代地政272期.人與地241期,頁20-24,2004年2月。
4. 4. 王志誠,不動產受益證券之發行與投資人保護機制~信用評等、信用增強及避險計畫,律師雜誌295期,頁54-79,2004年4月。
5. 7. 宋良政,建築經理公司在不動產證券化業務中的角色與任務,建築經理季刊第21期,頁26-29,2005年9月。
6. 8. 林永汀,「鬮分」的協議分割與信託性質研究,司法周刊第1196期2版、3版,2004年8月5日。
7. 10.林中森,不動產證券化之交易安全機制及交易安全年推動策略,現代地政304期.人與地273期,頁3-7,2006年10月。
8. 11.林娟宇,不動產證券化與行銷管理,現代地政276期.人與地245期,頁13-26,2004年6月。
9. 12.卓文乾、陳寶貴,台灣不動產不良債權證券化及其行銷組合之研究(一),現代地政288期.人與地257期,頁12-18,2005年6月。
10. 14.殷章甫,美、日、台之不動產證券化概況(一),現代地政267期.人與地236期,頁3~11,2003年9月。
11. 16.莊孟翰,不動產證券化對台灣房地產市場之影響(一),現代地政272期.人與地241期,頁28-31,2004年2月。
12. 17.梁榮輝、廖振盛,台灣地區不動產證券化推行現況與未來發展,建華金融季刊第28期,頁71-93,2005年3月。
13. 18.陳金令,「不動產證券化」的現況趨勢與課題,建築師雜誌,頁114-117,2005年8月。
14. 19.陳石進,略談不動產貸款的風險與防範,建築經理季刊第21期,頁9-13,2005年9月。
15. 20.黃志偉,不動產證券化條例立法背景暨影響分析(一),現代地政271期.人與地240期,頁25-28,2004年1月。
 
無相關點閱論文