在此篇論文中，提出基於改進之暗原色先驗及霧濃度偵測之單張影像除霧方法，暗原色先驗(dark channel prior)除霧方法在某些單張影像中能達到相當好的除霧效果，但基於我們的觀察中大部分的影像包含了霧較濃的部份及霧較淺的部份，因此霧較淺的部份實際上是不需要進行除霧的，為了解決此問題本論文提出HSV距離(HSV distance)、基於像素之暗原色先驗演算法及基於像素之亮原色先驗演算法計算影像之霧濃度，進一步修正大氣光(atmospheric light)及除霧比重提昇暗原色先驗除霧演算法除霧效果，將大氣光求得後即可藉由有霧影像形成原理及暗原色先驗演算法的假設推測出光的傳遞係數(transmission map)，並且使用雙向過濾器(bilateral filter)改善光傳遞係數使其更加精確，最後重建回除霧後的影像，由結果可觀察出本論文提出之方法可達到高品質之除霧效果及較低的計算量，本論文提出之方法也可延伸應用在視訊影像之除霧。

In this thesis, a single image dehazing method based on modified dark channel prior and haze (fog) density detection is proposed. Dark channel prior dehazing algorithm is achieved good results for some haze images. However, we observed that haze images contain low and high haze density. Thus, the region of low haze density is unnecessary to dehaze. To solve this problem, we first defined the HSV distance, pixel-based dark channel prior and pixel-based bright channel prior to estimate the haze density. Further to enhance the dehazing performance of dark channel prior, the atmospheric light value and dehazing weighting is revised based on the HSV distance. Then the new transmission map is obtained. After that, a bilateral filter is applied to refine the transmission map, which can provide the higher accuracy of transmission map. Finally, the haze-free image is recovered by combining the input image and the refined transmission map. As a result, high-quality haze-free image can be recovered with lower computational complexity, which can be naturally extended to video dehazing.

中文摘要 i
Abstract ii
Contents iii
List of Figures v
List of Tables vi
Chapter 1 Introduction 1
1.1 Overview of Single Image Dehazeing 1
1.2 Motivation 4
1.3 Verifying Applications 5
1.4 Contribution 9
1.5 Organization 10
Chapter 2 Background Review 11
2.1 Haze Imaging Model 11
2.2 Patch-based Dark Channel Prior 13
2.3 Single Image Dehazing Based on Patch-based Dark Channel Prior 15
2.4 Bilateral Filtering 18
Chapter 3 Proposed Single Image-Based Dehazing Framework 20
3.1 Pixel-based Dark Channel Prior 21
3.2 Pixel-based Bright Channel Prior 23
3.3 Haze Density Analysis and Estimation of Atmospheric light 25
3.4 Estimation of Transmission Map and Its Refinement 28
3.5 Recovery of Haze-free Image 29
Chapter 4 Experimental Results 30
4.1 Testing Platform of Experimental Results 30
4.2 Comparison of the Single Image-Based Dehazing Methods 32
4.3 Results of Road Condition 34
4.4 Computation Time 36
Chapter 5 Conclusions and Future Works 37
5.1 Conclusion 37
5.2 Future Work 39
Reference 40

[1] S. G. Narasimhan and S. K. Nayar, “Vision and the atmosphere,” Int. J. Comput. Vis., vol. 48, pp. 233-254, 2002.
[2] K. Garg and S. K. Nayar, “Vision and rain,” Int. J. Comput. Vis., vol. 75, no. 1, pp. 3–27, 2007.
[3] M. S. Shehata et al., “Video-based automatic incident detection for smart roads: the outdoor environmental challenges regarding false alarms,” IEEE Trans. Intell. Transportation Syst., vol. 9, no. 2, pp. 349–360, June 2008.
[4] S.G. Narasimhan and S. K. Nayar, “Removing weather effects from monochrome images,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., vol. 2, pp. 186-193, 2001.
[5] Y. Y. Schechner, S. G. Narasimhan, and S. K. Nayar, “Instant dehazing of images using polarization,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., vol. 1, pp. 325-332, 2001.
[6] S. Shwartz, E. Namer, and Y. Y. Schechner, “Blind haze separation,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., vol. 2, 2006.
[7] S. K. Nayar and S.G. Narasimhan, “Vision in bad weather,” in Proc. IEEE Int. Conf. Comput. Vis., vol. 2, pp. 820-827, 1999.
[8] S. G. Narasimhan and S. K. Nayar, “Chromatic framework for vision in bad weather,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., vol. 1, pp. 598-605, June 2000.
[9] S. G. Narasimhan and S. K. Nayar, “Contrast restoration of weather degraded images,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 25, no. 6, pp. 713-724, June 2003.
[10] J. Kopf, B. Neubert, B. Chen, M. Cohen, D. Cohen-Or, O. Deussen, M. Uyttendaele, and D. Lischinski, “Deep photo: model-based photograph enhancement and viewing,” ACM Trans. Graphics, vol. 27, no. 5, pp. 116:1-116:10, 2008.
[11] S.G. Narasimhan and S.K. Nayar, “Interactive deweathering of an image using physical models,” in Proc. IEEE Workshop Color and Photometric Methods in Comput. Vis., Oct. 2003.
[12] R. Tan, “Visibility in bad weather from a single image,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., June 2008.
[13] R. Fattal, “Single image dehazing,” ACM Trans. on Graphics, vol. 27, no. 3, Aug. 2008.
[14] J. Zhang, L. Li, G. Yang, Y. Zhang, and J. Sun, “Local albedo-insensitive single image dehazing,” Vis. Comput., vol. 26, Nov. 2010.
[15] K. He, J. Sun, and X. Tang, “Single image haze removal using dark channel Prior,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 33, no. 12, pp. 2341-2353, Dec. 2011.
[16] C. T. Chu and M. S. Lee, “A content-adaptive method for single image dehazing,” Lecture Notes in Computer Science, vol. 6298, 2010.
[17] J. Yu and Q. Liao, “Fast single image fog removal using edge-preserving smoothing,” in Proc. IEEE Int. Conf. Acoust., Speech Signal Process., Prague, Czech Republic, May 2011, pp. 1245-1248.
[18] J. Zhang, L. Li, Y. Zhang, G. Yang, X. Cao, and J. Sun, “Video dehazing with spatial and temporal coherence,” Vis Comput, vol. 27, pp. 749–757, 2011.
[19] L. W. Kang, C. W. Lin, and Y. H. Fu, “Automatic single-image-based rain streaks removal via image decomposition,” IEEE Trans. Image Process., vol. 21, no. 4, pp. 1742-1755, Apr. 2012.
[20] L. W. Kang, C. W. Lin, C. T. Lin, and Y. C. Lin, “Self-learning-based rain streak removal for image/video,” in Proc. IEEE Int. Sym. Cir. Sys., Seoul, Korea, May 2012, pp. 1871-1874.
[21] P. C. Barnum, S. Narasimhan, and T. Kanade, “Analysis of rain and snow in frequency space,” Int. J. Comput. Vis., vol. 86, no. 2–3, pp. 256–274, 2010.
[22] C. Tomasi and R. Manduchi, “Bilateral filtering for gray and color images,” in Proc. IEEE Int. Conf. Comput. Vis., Jan. 1998, pp. 839–846.
[23] A. Levin, D. Lischinski, and Y. Weiss, “A closed form solution to natural image matting,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., vol. 1, pp. 61-68, 2006.
[24] M. Jahangiri and M. Petrou, “An attention model for extracting components that merit identification,” in Proc. IEEE Int. Conf. Image Processing, Nov. 2009, pp. 965-968
[25] S. Maji, A. C. Berg, and J. Malik, “Classification using intersection kernel support vector machines is efficient,” in Proc. IEEE Conf. Comput. Vis. June 2008, pp. 1-8.
[26] J. Harel, A Saliency Implementation in MATLAB: http://www.klab.caltech.edu/~harel/share/gbvs.php
[27] V. Aurich and J. Weule, “Non-linear Gaussian filters performing edge preserving diffusion”, in Proc. 17 DAGM-Symp., pp. 538-545, 1995.