跳到主要內容

臺灣博碩士論文加值系統

(3.236.124.56) 您好!臺灣時間:2021/07/28 10:03
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:鄭家揚
研究生(外文):Chia-Yang Cheng
論文名稱:開發紅-暗黑頻道與去點擴散方程式從事水下影像修復之研究
論文名稱(外文):Underwater Image Restoration by Red-Dark Channel Prior and Point Spread Function Deconvolution
指導教授:張恆華
口試委員:張瑞益丁肇隆李佳翰
口試日期:2015-07-17
學位類別:碩士
校院名稱:國立臺灣大學
系所名稱:工程科學及海洋工程學研究所
學門:工程學門
學類:綜合工程學類
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:70
中文關鍵詞:水下影像影像修復紅-暗黑頻道去點擴散方程式波長和深度顏色補償
外文關鍵詞:underwater imageimage restorationred-dark channel priorpoint spread function deconvolutionwavelength and depth compensation
相關次數:
  • 被引用被引用:0
  • 點閱點閱:129
  • 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
在水下研究領域裡,無人載具通常都會安裝影像監控系統來記錄海底環境資訊。其拍攝的水下影像擁有些共同特徵:色偏和低能見度。這些因素是由於光進入海水之中,其能量會以指數性衰減;此外,根據波長的性質,衰減的幅度也會有所不同。此篇論文主要以簡化的傑夫-葛萊蒙利(Jaffe-McGlamery)水下光學模型來有效率地修復水下影像。在我們的方法裡,首先利用改良過的暗黑頻道來估算紅光色系的背景光和穿透率。如此一來,其能見度將會以物體與相機之間的相對距離獲得適當的補償。接者,藉由分析點擴散方程式與前向散射的關係,我們推導出一個簡單但實用的低通濾波來對水下影像去捲積。最後,利用整張影像的灰階值與波長吸收係數之間的關係,估測出場景距海平面的平均深度及對各色系做合理地補償色差。實驗的數據指出,在各種水下場景,提出的演算法會比許多現存的方法擁有更高程度的影像品質。因此,我們深信此修復方法能夠延伸出不同的水下影像之應用層面。

In the field of undersea research, underwater vehicles usually carry camera systems for recording. The captured images and videos often have two undesired characteristics: color distortion and low visibility. This is because that the light is exponentially attenuated while penetrating through water. Furthermore, the quantity of attenuation is associated with the wavelength of light spectrum. This thesis simplifies the Jaffe-McGlamery optical model and proposes an effective algorithm to recover underwater images. In our approach, a red-dark channel prior was defined and derived to estimate the background light and the transmission. The visibility of scene was compensated by the object-camera distance to recover the color of the background and objects. Subsequently, by analyzing the physical property of the point spread function, we developed a simple but efficient low-pass filter to deblur the image by deconvolution. Finally, we used the relationship between the radiance above the sea surface and the absorption coefficient to correct the color distortion. A wide variety of underwater images with different scenarios were used for the experiments. The experimental results show that the proposed algorithm effectively recovered underwater images while eliminating the influence of absorption and scattering. Comparing with many existing methods, the proposed framework provided more natural restoration results. We believe that this new restoration algorithm is promising in many underwater image processing applications.

Acknowledgements i
中文摘要 ii
ABSTRACT iii
Contents iv
List of figures vi
List of tables x
List of symbols xi
CHAPTER 1 INTRODUCTION 1
1.1 Background 1
1.2 Motivation 2
1.3 Organization of the thesis 3
CHAPTER 2 RELATED STUDIES 4
2.1 Color model 4
2.1.1 RGB color space 4
2.1.2 HSI color space 5
2.2 Image domain 7
2.2.1 Spatial domain 7
2.2.2 Frequency domain 7
2.3 Edge preserving 8
2.4 Blind deconvolution 9
2.5 Nelder-Mead optimization 10
2.6 Underwater optical model 12
2.6.1 Absorption 13
2.6.2 Scattering 13
2.6.3 Direct light 15
2.6.4 Forward scatter 15
2.6.5 Back scatter 16
2.7 Underwater image processing 16
CHAPTER 3 METHODS 22
3.1 Simplified optical model 22
3.2 Red-dark channel prior 24
3.2.1 Background light estimation 25
3.2.2 Transmission estimation 26
3.3 Point spread function deconvolution 31
3.4 Transmission compensation 33
3.5 Color compensation 34
CHAPTER 4 EXPERIMENTAL RESULTS 36
4.1 Color evaluation 36
4.2 Visibility evaluation 44
4.3 Recovery results 56
4.4 Applications 63
CHAPTER 5 CONCLUSION 67
References 69


[1]G. Griffiths, Technology and applications of autonomous underwater vehicles vol. 2: CRC Press, 2002.
[2]K. Iqbal, R. Abdul Salam, M. Osman, and A. Z. Talib, "Underwater Image Enhancement Using An Integrated Colour Model," IAENG International Journal of Computer Science, vol. 32, pp. 239-244, 2007.
[3]A. S. A. Ghani and N. A. M. Isa, "Underwater image quality enhancement through integrated color model with Rayleigh distribution," Applied Soft Computing, vol. 27, pp. 219-230, 2015.
[4]J. Y. Chiang and Y.-C. Chen, "Underwater image enhancement by wavelength compensation and dehazing," Image Processing, IEEE Transactions on, vol. 21, pp. 1756-1769, 2012.
[5]A. Galdran, D. Pardo, A. Picón, and A. Alvarez-Gila, "Automatic Red-Channel underwater image restoration," Journal of Visual Communication and Image Representation, vol. 26, pp. 132-145, 2015.
[6]台灣大學工程科學及海洋工程系ROV "海影一號". Available: http://www.tuaa2009.org.tw/tuai.php?ITEM1=00000009&ITEM2=A06&nowpage=1
[7]台灣大學工程科學及海洋工程系AUV "海敏一號". Available: http://www.tuaa2009.org.tw/tuai.php?ITEM1=00000009&ITEM2=A06&nowpage=1
[8]The real underwater image. Available: https://www.flickr.com/photos/101166233@N04/15478119092
[9]Department of Computer Science. Available: http://homepages.inf.ed.ac.uk/rbf/CVonline/LOCAL_COPIES/OWENS/LECT14/lecture12.html#fig:spect
[10]RGB color model. Available: http://www3.villanova.edu/latfs/research/res04.html
[11]R. C. Gonzalez and R. E. Woods, "Digital image processing 3rd edition," ed: Prentice Hall, 2007.
[12]Ths HSI color space model. Available: http://www.noldus.com/events/mb2000/program/abstracts/spink.html
[13]K. He, J. Sun, and X. Tang, "Guided image filtering," in Computer Vision–ECCV 2010, ed: Springer, 2010, pp. 1-14.
[14]G. Ayers and J. C. Dainty, "Iterative blind deconvolution method and its applications," Optics letters, vol. 13, pp. 547-549, 1988.
[15]J. C. Lagarias, J. A. Reeds, M. H. Wright, and P. E. Wright, "Convergence properties of the Nelder--Mead simplex method in low dimensions," SIAM Journal on optimization, vol. 9, pp. 112-147, 1998.
[16]Unconstrained nonlinear programming: Nelder-Mead Simplex algorithm. Available: http://www.jakubkonka.com/2013/10/22/nelder-mead-simplex.html
[17]J. S. Jaffe and C. Dunn, "A model-based comparison of underwater imaging systems," in 1988 Orlando Technical Symposium, 1988, pp. 344-350.
[18]B. McGlamery, "A computer model for underwater camera systems," in Ocean Optics VI, 1980, pp. 221-231.
[19]Y. Wang and B. Wu, "Fast Clear Single Underwater Image," 2010 International Conference on Computational Intelligence and Software Engineering, pp. 1-4, 2010.
[20]K. He, J. Sun, and X. Tang, "Single image haze removal using dark channel prior," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 33, pp. 2341-2353, 2011.
[21]E. Trucco and A. T. Olmos-Antillon, "Self-tuning underwater image restoration," Oceanic Engineering, IEEE Journal of, vol. 31, pp. 511-519, 2006.
[22]Y. Y. Schechner and N. Karpel, "Clear underwater vision," in Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on, 2004, pp. I-536-I-543 Vol. 1.
[23]H. Wen, Y. Tian, T. Huang, and W. Gao, "Single underwater image enhancement with a new optical model," in Circuits and Systems (ISCAS), 2013 IEEE International Symposium on, 2013, pp. 753-756.
[24]Y. Yu and F. Liu, "System of remote-operated-vehicle-based underwater blurred image restoration," Optical Engineering, vol. 46, pp. 116002-116002-5, 2007.
[25]Y. Miao, "Underwater image adaptive restoration and analysis by turbulence model," in Information and Communication Technologies (WICT), 2012 World Congress on, 2012, pp. 1182-1187.
[26]J.-K. Guo, C.-C. Sung, and H.-H. Chang, "Restoration of underwater vision using a two-phase regularization mechanism," in Image and Signal Processing (CISP), 2014 7th International Congress on, 2014, pp. 243-247.
[27]Color board. Available: http://www.candelaprinting.com/services/
[28]C. Harris and M. Stephens, "A combined corner and edge detector," in Alvey vision conference, 1988, p. 50.
[29]Kenting coral ecology shows loss of biodiversity. Available: http://taiwantoday.tw/ct.asp?xItem=196052&ctNode=413
[30]My trip to the Great Barrier Reef. Available: http://kimscollaborations.blogspot.tw/2011/08/is-bigger-better-my-trip-to-great.html
[31]International Centre for Underwater Archaeology in Zadar Available: http://icua.hr/hr/ocentru
[32]Ocean view diving. Available: http://www.oceanviewdive.com/gallery-2/
[33](2014). Sue Baker on transect. Available: http://reeflifesurvey.com/2014/08/01/reef-dragon-port-hedland-to-exmouth/sue-diver-barrow-island-nws143gje6m261013-varanus-port-limit-red/
[34]Grooved Brain Coral. Available: http://www.eastiron.org/staffweb/jdejohn/science/Ecosystem/CoralReef/Building%20A%20Background/Types%20of/grooved%20brain%20coral.jpg
[35](2013). Low under water visibility during the period of warm southernly winds. Available: http://www.zmt-bremen.de/Aqaba_Jordanien_9.1.13_-_25.4.13.html


QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top