在戶外拍攝的照片時常因為天氣的影響而造成照片品質的降低。在空氣中有大量懸浮微粒的情況下，行進中的光線受到這些懸浮微粒的影響而產生散射的現象。這種光線散射的現象是導致圖片對比度降低，並且看起來霧濛濛的主因。為了解決這個問題，在本篇論文中提出了利用估計局部與全域懸浮散射光(airlight)來實現單張圖片去霧化的方法。在提出的方法中使用了以物理為基礎建立的圖片降階模型，此降階模型為直接衰減(direct attenuation)及懸浮散射光的線性組合。
在提出的方法中，三個色彩通道中的最小值，稱為白圖(white map)，被視為評估霧的濃度的參考。首先利用白圖估計局部的懸浮散射光，並且使用適性暗原色先驗統計(adaptive dark channel prior) 來取得全域的懸浮散射光, 而圖片沒受霧化影響的程度就可藉由前兩項直接推算。在上列步驟後，就可達到霧化圖片的復原。
而為了進一步改善在圖片中受濃霧影響較嚴重的較遠的場景，在提出的方法中利用影像二值化及影像分割建立了再次去霧(redehazing)的程序。實驗的結果顯示，提出的方法能有效的去除圖片中霧化所造成的影響並改善圖片的細節。並且透過與其他目前先進的單張圖片去霧化的方法比較，來探討提出的方法的執行成果。

口試委員會審定書 #
誌謝 i
中文摘要 ii
ABSTRACT iii
CONTENTS iv
LIST OF FIGURES vi
Chapter 1 Introduction 1
1.1 Introduction of Dehazing 1
1.2 Thesis Organization 6
Chapter 2 Related Work 7
2.1 Single Image Dehazing Methods 8
2.1.1 Dark Channel Prior 9
2.1.2 Atmospheric Veil Inference 10
2.2 Mean Shift Segmentation 11
Chapter 3 Single Image Dehazing using Local and Global Airlight Estimation 14
3.1 System Overview 14
3.2 Global Airlight Estimation using adaptive dark channel 17
3.3 Atmospheric Veil Inference for Local Airlight Estimation 22
3.4 Refinement of Local Airlight using Soft Matting 24
3.5 Recovery of the Scene Radiance 30
3.6 Redehazing using Binary Thresholding and Mean Shift Segmentation 31
Chapter 4 Experimental Results 38
4.1 Resultant images 38
4.2 Comparison with other haze removal methods 52
Chapter 5 Conclusion and Future Work 63
5.1 Conclusion 63
5.2 Future work 64
REFERENCE 67

1.Cantor, A., "Optics of the atmosphere--Scattering by molecules and particles," IEEE Journal of Quantum Electronics, 14(9): p. 698-699, 1978
2.Comaniciu, D. and Meer, P., "Mean shift: a robust approach toward feature space analysis," IEEE Conference on Pattern Analysis and Machine Intelligence, 24(5): p. 603-619, 2002
3.Fattal, R., "Single image dehazing," ACM SIGGRAPH 2008 papers, Los Angeles, California, 2008.
4.Kaiming, H., Jian, S., and Xiaoou, T., "Single image haze removal using dark channel prior," IEEE Conference on Computer Vision and Pattern Recognition, 2009
5.Kopf, J., Neubert, B., Chen, B., Cohen, M., Cohen-Or, D., Deussen, O., Uyttendaele, M., and Lischinski, D., "Deep photo: model-based photograph enhancement and viewing," ACM SIGGRAPH Asia 2008 papers, Singapore, 2008.
6.Koschmieder, H., "Theorie der horizontalen sichtweite," Beitr. Phys. freien Atm., 12: p. 33-53,171-181, 1924
7.Levin, A., Lischinski, D., and Weiss, Y., "A Closed Form Solution to Natural Image Matting," IEEE Conference on Computer Vision and Pattern Recognition, 2006
8.Narasimhan, S.G. and Nayar, S.K., "Chromatic framework for vision in bad weather," IEEE Conference on Computer Vision and Pattern Recognition, 2000
9.Narasimhan, S.G. and Nayar, S.K., "Contrast restoration of weather degraded images," IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(6): p. 713-724, 2003
10.Nayar, S.K. and Narasimhan, S.G., "Vision in bad weather," IEEE International Conference on Computer Vision, 1999
11.Porter, T. and Duff, T., "Compositing digital images," International Conference on Computer Graphics and Interactive Techniques, 1984.
12.Schechner, Y.Y., Narasimhan, S.G., and Nayar, S.K., "Instant dehazing of images using polarization," IEEE Conference on Computer Vision and Pattern Recognition. p. I-325-I-332 vol.1, 2001.
13.Shwartz, S., Namer, E., and Schechner, Y.Y., "Blind Haze Separation," IEEE Conference on Computer Vision and Pattern Recognition, 2006
14.Tan, R.T., "Visibility in bad weather from a single image," IEEE Conference on Computer Vision and Pattern Recognition, 2008
15.Tarel, J.-P. and Hauti`ere, N., "Fast visibility restoration from a single color or gray level image," IEEE International Conference on Computer Vision, 2009
16.Yuhui, Z., Bin, F., and Huiqing, Z., "Image De-Weathering for Road Based on Physical Model," International Conference on Information Engineering and Computer Science, 2009