臺灣博碩士論文加值系統

有霧的影像不僅會降低視覺能見度，也會降低影像處理的能力，因此影像除霧在電腦視覺領域中是相當重要的技術。在這些技術當中較具代表性的方法為He等人提出的暗通道先驗(Dark Channel Prior, DCP)除霧方法，由於在部分情況下DCP方法除霧後容易產生光暈，因此本文為改善DCP除霧後光暈現象提出一個自適應遮罩尺寸的DCP除霧方法(簡稱ADCP)，該方法以有霧影像的梯度反比作為依據並計算出不同的遮罩尺寸，在梯度大的區域使用較小的遮罩尺寸解決光暈現象，而在梯度小的區域則使用較大遮罩尺寸來達到除霧效果，並透過高斯濾波器與函數計算以獲得更好的非線性對應關係，最後使用蟻群最佳化(Ant Colony Optimization, ACO)演算法尋找高斯濾波器與函數的最佳參數，此外本研究也提出一個新的評量指標，並作為ACO演算法的成本評估函數。經實驗結果證實，本研究提出的方法可以有效的改善DCP除霧技術的光暈現象，並且仍然保有良好的除霧性能。

Haze images not only reduce visual visibility, but also affect the effectiveness of image processing. Therefore, image dehazing technology is a very important technology in the field of computer vision. Among them, the representative method is the dark channel prior (DCP) dehazing technology propose by He et al. Since DCP is easy to produce halo after dehazing in some cases, this paper proposes an adaptive mask size DCP dehazing method (ADCP) to improve the halo phenomenon after DCP dehazing. This method based on the inverse of the gradient of the haze image and calculates different mask sizes. In the area with a large gradient, a smaller mask size is used to solve the halo phenomenon, while in the area with a small gradient, a larger mask size is used to achieve the effect of haze removal. And through Gaussian filter and gamma function calculation to obtain better nonlinear correspondence. Finally, the ant colony optimization (ACO) algorithm is used to find the optimal parameters of the Gaussian filter and the gamma function. In addition, we also propose a new dehazing performance index and use it as a cost function for the ACO. Experimental results confirm that the method proposed in this paper can effectively improve the halo phenomenon of haze removal image in DCP, while maintaining good haze removal performance.

目錄
摘要 I
Abstract II
誌謝 III
目錄 V
表目錄 VII
圖目錄 VIII
第一章 簡介 1
1.1. 研究動機 1
1.2. 文獻回顧 3
1.3. 研究目的 7
第二章 背景知識 10
2.1. DCP除霧方法 10
2.2. 除霧性能指標 12
第三章 ADCP的除霧方法 14
3.1. ADCP 14
3.2. 使用ACO估測最佳化參數 18
3.3. 使用ADCP的除霧方法 21
第四章 實驗結果 24
4.1. 評估指標 24
4.2. 固定參數ADCP的除霧結果 25
4.3. 最佳化參數ADCP的除霧結果 29
第五章 結論 33
參考文獻 34
 
表目錄
表4.1. 影像除霧結果的比較 26
表4.2. 影像除霧結果的新可見邊緣比的比較 27
表4.3. 影像除霧結果的飽和像素比的比較 28
表4.4. 影像除霧結果的DPI_h的比較 28
表4.5. 使用ACO估計ADCP的參數結果 29
表4.6. ADCP的除霧結果比較 31
表4.7. 最佳化參數ADCP的影像除霧結果比較 32
 
圖目錄
圖1.1. 有霧影像 1
圖1.2. 有霧影像衰退模型 2
圖1.3. 不同遮罩的DCP除霧結果 8
圖3.1. 不同值的影像梯度對應遮罩尺寸的曲線圖 16
圖3.2. 以一維數據為例子 18
圖3.3. ACO路徑設置 20
圖3.4. 使用ACO獲得除霧參數流程圖 21
圖3.5. ADCP除霧流程 22
圖3.6. 自適應遮罩尺寸的暗通道估計範例 23

[1]E. J. McCartney, “Optics of the Atmosphere: Scattering by Molecules and Particles,” Physics Today, Vol.30(5), 1977, pp. 76-77.
[2]R. T. Tan, “Visibility in Bad Weather from a Single Image,” IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, Alaska, Jun 24-26, 2008, pp. 1-8.
[3]Y. Y. Schechner, S. G. Narasimhan and S. K. Nayar, “Instant dehazing of images using polarization,” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Kauai, HI, USA Vol.1,Dec 8-14, 2001, pp. I325-I332.
[4]Y. H. Shiau, P. Y. Chen, H. Y. Yang, C. H. Chen and S. S. Wang, “Weighted haze removal method with halo prevention,” Journal of Visual Communication and Image Representation, Vol.25(2), 2014, pp. 445-453.
[5]Q. Zhu, J. Mai and L. Shao, “A Fast Single Image Haze Removal Algorithm Using Color Attenuation Prior,” IEEE Transactions on Image Processing, Vol.24(11), 2015, pp. 3522-3533.
[6]D. Berman, T. Treibitz and S. Avidan, “Non-local Image Dehazing,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, Jun 26-Jul 1, 2016, pp. 1674-1682.
[7]B. Cai, X. Xu, K. Jia, C. Qing and D. Tao, “DehazeNet: An End-to-End System for Single Image Haze Removal,” IEEE Transactions on Image Processing, Vol.25(11), 2016, pp. 5187-5198.
[8]K. He, J. Sun and X. Tang, “Single Image Haze Removal Using Dark Channel Prior,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.33(12), 2011, pp. 2341-2353.
[9]K. He, J. Sun and X. Tang, “Guided Image Filtering,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.35(6), 2013, pp. 1397-1409.
[10]H. Yang, P. Chen, C. Huang, Y. Zhuang and Y. Shiau, “Low Complexity Underwater Image Enhancement Based on Dark Channel Prior,” Second International Conference on Innovations in Bio-inspired Computing and Applications, Shenzhen, China, Dec 21-23, 2011, pp. 17-20.
[11]B. Li, S. Wang, J. Zheng and L. Zheng, “Single image haze removal using content-adaptive dark channel and post enhancement,” IET Computer Vision, Vol.8(2), 2014, pp. 131-140.
[12]C. Hsieh, C. Chen and Y. Lin, “Adaptive Fast Image Dehazing Algorithm,” IEEE International Symposium on Independent Computing (ISIC), 2014, pp. 1-6.
[13]Z. Shi, J. Long, W. Tang and C. Zhang, “Single image dehazing in inhomogeneous atmosphere,” Optik - International Journal for Light and Electron Optics, Vol.125(15), 2014, pp. 3868-3875.
[14]G. Bi, J. Ren, T. Fu, T. Nie, C. Chen and N. Zhang, “Image Dehazing Based on Accurate Estimation of Transmission in the Atmospheric Scattering Model,” IEEE Photonics Journal, Vol.9(4), 2017, pp. 1-18.
[15]Y. Chen, Z. Li, B. Bhanu, D. Tang, Q. Peng and Q. Zhang, “Improve Transmission by Designing Filters for Image Dehazing,” IEEE 3rd International Conference on Image, Vision and Computing (ICIVC), Chongqing, China, Jun 27-29, 2018, pp. 374-378.
[16]N. Ma, J. Xu and H. Li, “A Fast Video Haze Removal Algorithm Via Dark Channel Prior,” Procedia Computer Science, Vol.131, 2018, pp. 213-219.
[17]T. Yu, I. Riaz, H. Shin and J. Piao, “Real-time single image dehazing using block-to-pixel interpolation and adaptive dark channel prior,” IET Image Processing, Vol.9(9), 2015, pp. 725-734.
[18]C. Chengtao, Z. Qiuyu and L. Yanhua, “Improved dark channel prior dehazing approach using adaptive factor,” IEEE International Conference on Mechatronics and Automation (ICMA), Beijing, China, Aug 2-5, 2015, pp. 1703-1707.
[19]Y. Li, Q. Miao, J. Song, Y. Quan and W. Li, “Single image haze removal based on haze physical characteristics and adaptive sky region detection,” Neurocomputing, Vol.182, 2016, pp. 221-234.
[20]N. Hautière, J. Tarel, D. Aubert and E. Dumont, “Blind Contrast Enhancement Assessment by Gradient Rationing at Visible Edges,” Image Analysis & Stereology, Vol.27(2), 2008, pp. 87-95.
[21]C. Hsieh, S. Horng, Z. Huang and Q. Zhao, “Objective Haze Removal Assessment Based on Two-objective Optimization,” IEEE 8th International Conference on Awareness Science and Technology (iCAST), Taichung, Taiwan, Nov 8-10, 2017, pp. 279-283.
[22]B. Zhao, “An Ant Colony Clustering Algorithm,” International Conference on Machine Learning and Cybernetics, Hong Kong, China, Vol.7, Aug 19-22, 2007, pp. 3933-3938.