臺灣博碩士論文加值系統

本論文旨在針對立體影像並採用交叉雙邊濾波器進行去霧。在此之前，已經出現大量的去霧演算法。然而這些去霧演算法多是針對單張影像。倘若，直接對立體影像分別進行單張影像去霧，容易導致去霧結果不一致的情況，進而影響使用者觀看立體影像的體驗。
在本論文中，除了對立體影像去霧，同時也預估場景深度。本論文的重點在於根據立體影像產生場景深度，並以此場景深度結合交叉雙邊濾波器進行去霧。此方法可以避免去霧結果不一致的情況。最後，本論文的測試結果顯示，相較以往的方法可以得到更好的結果。

In this thesis, we present a novel dehazing approach for stereo images based on cross bilateral filtering. Numerous dehazing algorithms have been proposed before. Nevertheless, most of the dehazing algorithms are proposed for a single image. This will produce inconsistent results if dehazing stereo images iteratively.
We simultaneously estimate scene depth and dehaze the stereo images. The proposed approach is based on the observation of depth cues in the stereo images. The main idea of using depth cues is to avoid inconsistent results and of using the cross bilateral filter is to preserve shape details. The results show that the proposed approach can get better results compared with the previous methods.

ABSTRACT (in Chinese).………………………………………………………….………………………i
ABSTRACT (in English) ………………….…………………………………………………………….…ii
Acknowledgements iii
Contents iv
List of Tables v
List of Figures vi
Chapter 1 Introduction 1
1.1 Motivation 1
1.2 Thesis Organization 4
Chapter 2 Related Works 5
2.1 Single Image Dehazing 5
2.2 Stereo Image Dehazing 7
Chapter 3 Algorithm 8
3.1 Overview 8
3.2 Stereo Disparity Map 9
3.3 Dark Channel Weighted Transmission 13
3.4 Cross Bilateral Filter 17
3.5 Hazy Image Recovery 19
3.6 Coefficient Estimation 20
Chapter 4 Implementation and Results 22
4.1 Implementation 22
4.2 Results 27
Chapter 5 Conclusions 45
References 46

[1] Carr, P., Hartley, R., "Improved Single Image Dehazing Using Geometry", Digital Image Computing: Techniques and Applications (DICTA), 103–110, 2009.
[2] Cho, H., Lee, H., Kang, H., Lee, S., "Bilateral Texture Filtering", ACM Transactions on Graphics (TOG), 33(4), 1281–1288, 2014.
[3] Fattal, R., "Single Image Dehazing", ACM Transactions on Graphics (TOG), 27(3), 7–23, 2008.
[4] Fattal, R., "Dehazing Using Color-Lines", ACM Transactions on Graphics (TOG), 34(1), 1–14, 2014.
[5] Gibson, K., Nguyen, T., "Fast Single Image Fog Removal Using the Adaptive Wiener Filter", Proceedings of the International Conference on Image Processing (ICIP), 714–718, 2013.
[6] Hartley, R. I., Zisserman, A., Multiple View Geometry in Computer Vision, Cambridge: Cambridge University Press, 2004.
[7] He, K., Sun, J., Tang, X., "Single Image Haze Removal Using Dark Channel Prior", IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 33(12), 2341–2353, 2011.
[8] Kopf, J., et al., "Deep Photo: Model-Based Photograph Enhancement and Viewing", ACM SIGGRAPH Asia, 2008.
[9] Li, Z.W., et al., "Simultaneous Video Defogging and Stereo Reconstruction", Computer Vision and Pattern Recognition (CVPR), 4988–4997, 2015.
[10] Meng, G. , et al., "Efficient Image Dehazing with Boundary Constraint and Contextual Regularization", International Conference on Computer Vision (ICCV), 617–624, 2013.
[11] Middleton, W. E. K, Vision Through the Atmosphere, Toronto: University of Toronto Press, 1952.
[12] Shiau, Y. H., et al., "Weighted Haze Removal Method with Halo Prevention", Journal of Visual Communication and Image Representation, 25(2), 445–453, 2014.
[13] Tan, R.T., "Visibility in Bad Weather from A Single Image", Computer Vision and Pattern Recognition (CVPR), 1–8, 2008.
[14] Tarel, J.P., Hautiere, H., "Fast Visibility Restoration from a Single Color or Gray Level Image", International Conference on Computer Vision (ICCV), 2201–2208, 2009.
[15] Tarel, J.P., Hautiere, H., "Improved Visibility of Road Scene Images under Heterogeneous Fog", Proceedings of IEEE Intelligent Vehicle Symposium (IV), 478–485. 2010.
[16] Tomasi, C., Manduchi, R., "Bilateral Filtering For Gray and Color Images", International Conference on Computer Vision (ICCV), 839–846, 1998.
[17] Wang, J.B., He, N., Lu, K., "A New Single Image Dehazing Method with MSRCR Algorithm", Proceedings of the International Conference on Internet Multimedia Computing and Service (ICIMCS), 2015.
[18] Yang, Q.X., "A Non-Local Cost Aggregation Method For Stereo Matching", Computer Vision and Pattern Recognition (CVPR), 1402–1409, 2012.
[19] Yang, Q.X., Ahuja, N., Tan, K.H., "Constant Time Median and Bilateral Filtering", International Journal of Computer Vision, 112(3), 307–318, 2015.
[20] Zhang, Z., "A Flexible New Technique for Camera Calibration", IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 22(11), 1330–1334, 2000.
[21] Bilateral Filter, Available: http://en.wikipedia.org/wiki/Bilateral_filter.
[22] Ensenso und IDS Imaging Development Systems (2012) Obtaining Depth Information from Stereo Images, Available: http://www.sanxo.eu/content/whitepaper/IDS_Whitepaper_3D_Stereo_Vision.pdf.
[23] Google Cardboard, Available: https://www.google.com/get/cardboard/.
[24] Middlebury Stereo Datasets, Available: http://vision.middlebury.edu/stereo/data/
[25] Structural Similarity , Available: https://en.wikipedia.org/wiki/Structural_similarity.
[26] Single Image Visibility Restoration Comparison, Available: http://perso.lcpc.fr/tarel.jean-philippe/visibility/.ch
[27] Unity - Manual: Global Fog, Available: https://docs.unity3d.com/Manual/script-GlobalFog.html
[28] Unity - Scripting API: FogMode, Available: https://docs.unity3d.com/ScriptReference/FogMode.html