臺灣博碩士論文加值系統

一個可靠的系統，必須要能容忍在不同的環境中(如：起霧、下雨、下雪等)也能確實的運作。本研究最主要的目的，不僅僅是想了解光與空氣是如何的作用。更進一步的，希望藉由公式的推導，回復光在受未干擾時的狀態，也就是景物表面最初所散發的光。
恢復景物原本的影像，無可避免的可以分為兩大問題。分別為估計airlight 與估計透射率 。本研究藉由兩種不同的方法分別得到airlight的值與透射率 值，再藉由影像退化模式的公式推估出景物在未受干擾前最原始的亮度。
實驗的場景我們選擇了在台灣常見的天氣型態：起霧和下雨。並且針對各種的天氣型態拍攝了交通影像與非交通影像。再針對交通影像拍攝了一般道路與高速公路兩種類型。本研究所提出的技術對於能見度之改善皆有良好的效果。

The bad weather condition including fog, haze, rain and show make the acquired images contrast being low, which make computer vision application fail to detect or recognize objects. A technique for visibility improvement the bad weather images is presented. In this proposed approach, the polarized images are used to obtain the high contrast images. The input images are assumed composed by the direct light and airlight . The airlight is affected by the bad weather conditions, which makes the acquired image unclear. The key idea of the proposed method is use ICA to estimate and remove the airlight from the input images. The experimental results have demonstrated that the proposed method can effectively remove the bad weather condition and enhance the contrast of the input images

第一章 簡介...........................................1
1.1 研究動機..........................................1
1.2 研究目的..........................................2
1.3 文獻探討..........................................5
第二章　利用偏光鏡回復影像..............................8
2.1 影像退化模式......................................8
2.2 光的偏振性.......................................10
2.3 影像公式.........................................13
2.4 恢復影像.........................................15
2.5 估計p...........................................15
2.6 估計............................................23
第三章　利用偏光鏡回復影像.............................24
3.1 利用偏光鏡回復影像的缺點...........................24
3.2 反射率為常數的影像................................26
3.3 反射率不為常數的影像...............................30
3.4估計Airlight Color A..............................34
3.5 區域圖...........................................35
3.6 雜訊的估計........................................37
第四章 實驗結果.......................................43
4.1偏光鏡為基礎.......................................41
4.2單張影像為基礎.....................................48
4.3交通影像之能見度統計................................54
第五章 結論與未來工作..................................57
5.1 結論.............................................57
5.2 未來方向..........................................58
參考文獻..............................................60

[Bof 01]P. Bofill and M. Zibulevsky. “Underdetermined blind source separation using sparse representations.” Signal Processing, 81:2353–62, 2001.

[ Coz 97]F. Cozman and E. Kroktov. “Depth from scattering.” In Proc.IEEE CVPR, pages 801–806, 1997.

[Cha 88]P. S. Chavez. 1988.” An improved dark-object subtraction technique for atmonspheric scattering correction of multispectral data.” Remote Sensing of Environment 24, 450–479.

[Chu 06] Y. C. Chung, S. L. Chang, J. M. Wang, and S. W. Chen, “An Edge Analysis Based Blur Measure for Image Processing Applications” National Taiwan Normal Universal.

[Fat 07]R. Fattal. 2007. “Image upsampling via imposed edge statistics.” ACM SIGGRAPH 26, 3, 95.

[Fat 08]R. Fattal.” Single image dehazing.” to appear in SIGGRAPH,2008.

[Hyv 00]A. Hyvrinen, and E. Oja. 2000. “Independent component analysis: Algorithms and applications.” Neural Networks 13, 411–430.

[Hec 02]E. Hecht, Optics, pp. 562-628. fourth ed., Addison Wesley, 2002.

[Liu 06]C. Liu, W. T. Freeman, R. Szeliski, and S. B. Kang.2006. “Noise estimation from a single image.” In Proceedings of IEEE CVPR, 901–908.

[Lev 07]A. Levin, R. Fergus, F. Durand, and W. T. Freeman. 2007. “Image and depth from a conventional camera with a coded aperture.” ACM Transaction on Graphics 26, 3, 70.

[Lu 94]J. Lu, and D. M. H. Jr. 1994. “Contrast enhancement via multiscale gradient transformation.” In IEEE International Conference on Image Processing, 482–486.

[Nar 00]S. G. Narasimhan, and S. K. Nayar. 2000. “Chromatic framework for vision in bad weather.” In Proceedings of IEEE CVPR, 598–605.
[Nay 99]S. K. Nayar, and S. G. Narasimhan. 1999. “Vision in bad weather.” In Proceedings of IEEE CVPR, 820.

[Nar 02]S. G. Narasimhan and S. K. Nayar. “Vision and the atmosphere” Int. J. Comp. Vis., 48:233–254, 2002.

[Oak 07]J. P. Oakley, and H. Bu. 2007. “Correction of simple contrast loss in color images.” IEEE Transactions on Image Processing 16, 2, 511–522.

[P´er 98]P. P´e rez. 1998.”Markov random fields and images.” In CWI Quar- terly, vol. 11, 413–437

[Ros 99] M. V. Rossum, and T. Nieuwenhuizen. 1999. “Multiple scattering of classical waves: microscopy, mesoscopy and diffusion.”vol. 71, 313–371.

[Rah 96]Z. Rahman, D. Jobson, and G. Woodell. 1996. “Multiscale retinex for color image enhancement”.

[Sch 07]Y. Y. Schechner, and Y. Averbuch. 2007. “Regularized image recovery in scattering media.” IEEE Transactions on Pattern Analysis and Machine Intelligence 29, 9, 1655–1660.

[Sch 07]Y. Y. Schechner, S. G. Narasimhan, and S. K. Nayar. “Polarization-based vision through haze.” App. Opt., 42:511– 525, 2003.

[Sch 01] Y. Y. Schechner, S. G. Narasimhan, and S. K. Nayar. 2001. “Instant dehazing of images using polarization.” 325–332.

[Shw 06]S. Shwartz, E. Namer, and Y. Y. Schechner. 2006. “Blind haze separation.” In Proceedings of IEEE CVPR, 1984–1991.

[Tan 00]K. Tan, and J. P. Oakley. 2000.” Enhancement of color images in poor visibility conditions.” Proceedings of International Conference on Image Processing 2, 788–791.

[Tan 08]R. T. Tan. 2008. “Visibility in bad weather from a single image.” Proceedings of IEEE CVPR.

[Wik 07]WIKIPEDIA, 2007. Unsharp masking — wikipedia, the free encyclopedia.

[Yua 07]L. Yuan, J. Sun, L. Quan, and H. Y. Shum. 2007. “Image deblurring with blurred/noisy image pairs.” ACMTransactions on Graphics 26, 3, 1.

[Zib 01]M. Zibulevsky and B. A. Pearlmutter. “Blind source separation by sparse decomposition in a signal dictionary.” Neural Computations, 13:863–882, 2001.

[Zha 02]Y. Zhang, B. Guindon, and J. Cihlar. 2002. “An image transform to characterize and compensate for spatial variations in thin cloud contamination of landsat images.” Remote Sensing of Environment 82 (October), 173–187.