臺灣博碩士論文加值系統

夜間的影像品質是智慧型監控系統中的一大問題，相較於日間影像，夜間的影像通常具有低亮度、低對比度以及高雜訊的特性。這些特性除了造成人眼視覺觀察極為困難之外，也使得系統後續做偵測或追蹤的演算法的準確率降低。因此我們針對夜間影像進行強化，結合對比強化與去雜訊演算法以此解決上述的三個特性。實驗先以模擬夜間影像驗證本論文方法的架構與對比強化、去雜訊之效果，再應用於真實夜間影像比較其它演算法。實驗結果在量化分析上大幅的提高夜間影像的亮度與對比的指標，而質化上影像整體亮度較高，尤其在影像暗區部份，且相對於其它演算法雜訊較少且弱，因而得到品質較好的夜間影像。

Night image quality in the intelligent surveillance system is a problem. Compared to daytime images, there are always three characteristics in the night, lower brightness, lower contrast and higher noise. These features not only cause human eyes difficult to observe but also make the accuracy decreasing of the system such as object detection or tracking. Therefore, we enhance the night images by combining with contrast enhancement and denoise to solve the above three characteristics. In experiments, we simulate night image to verify that architecture, contrast enhancement and denoise are useful first. Then we applied it on the real night image and compare with other algorithms. There is a strong improvement on the indicators of brightness and contrast of the night image. As the quality, overall image brightness is higher, especially in the dark region of the image, with less and weak noise than other algorithms, which means it get a better quality images at night.

摘要 i
英文摘要 ii
誌謝 iii
表目錄 vii
圖目錄 viii
第1章 前言 1
1.1 研究背景 1
1.2 研究動機、目的 2
1.3 方法與架構 4
1.4 論文結構 5
第2章 文獻探討 6
2.1 夜間影像強化 6
2.2 對比強化 8
2.2.1 Denight 8
2.2.2 Histogram Smoothing 9
2.2.3 Contrast Pair 13
2.2.4 Retinex 16
2.2.5 Retinex Based Adaptive Filter 17
2.3 去雜訊 19
2.3.1 Gaussian Filter 19
2.3.2 Bilateral Filter 20
第3章 夜間影像強化 21
第4章 模擬影像實驗 31
4.1 夜間影像 31
4.2 夜間影像模擬 33
4.2.1 雜訊模擬 34
4.2.2 對比模擬 34
4.3 對比強化分析 39
4.4 去雜訊分析 41
4.5 演算法順序分析 44
第5章 真實影像實驗 48
5.1 對比強化分析 48
5.2 對比強化及去雜訊分析 68
第6章 結論 81
參考文獻 82

1.S. W. Lee, V. Maik, J. Jang, et al., "Noise-adaptive spatio-temporal filter for real-time noise removal in low light level images," IEEE Transactions on Consumer Electronics, vol. 51, no. 2, pp. 648-653, 2005.
2.Y. Rao and L. Chen, "A survey of video enhancement techniques," Journal of Information Hiding and Multimedia Signal Processing, vol. 3, no. 1, pp. 71-99, 2012.
3.A. Date and P. V. Ingole, "Low light video enhancement: a survey," in Proc. International Journal of Computer Applications, Proceedings on National Conference on Recent Trends in Computer Science and Engineering, pp. 4-6. 2015.
4.M. Pallavi, H. Yawalkar and M. P. Pusdekar, "A review on low light video enhancement using image processing technique," International Journal of Advanced Research in Computer and Communication Engineering, vol. 4, no. 1, 2015.
5.A. Yamasaki, H. Takauji, S. Kaneko, et al., "Denighting: enhancement of nighttime images for a surveillance camera," in Proc. International Conference on Pattern Recognition, 2008.
6.H. Malm, M. Oskarsson, E. Warrant, et al., "Adaptive enhancement and noise reduction in very low light-level video," in Proc. IEEE 11th. International Conference on Computer Vision, 2007.
7.X. Qing, J. Hailin, R. Scopigno, et al., "A new approach for very dark video denoising and enhancement," in Proc. 17th IEEE International Conference on Image Processing, 2010.
8.A. R. Rivera, R. Byungyong and C. Oksam, "Content-aware dark image enhancement through channel division," IEEE Transactions on Image Processing, vol. 21, no. 9, pp. 3967-3980, 2012.
9.Z. Xiangdong, S. Peiyi, L. Lingli, et al., "Enhancement and noise reduction of very low light level images," in Proc. 21st International Conference on Pattern Recognition, 2012.
10.F. Xueyang, Z. Delu, H. Yue, et al., "A variational framework for single low light image enhancement using bright channel prior," in Proc. IEEE Global Conference on Signal and Information Processing, 2013.
11.D. Xuan, W. Guan, P. Yi, et al., "Fast efficient algorithm for enhancement of low lighting video," in Proc. IEEE International Conference on Multimedia and Expo, 2011.
12.W. Dongsheng, N. Xin and D. Yong., "A piecewise-based contrast enhancement framework for low lighting video," in Proc. International Conference on Security, Pattern Analysis, and Cybernetics ,2014.
13.黃紋彬，「一個平行化Retinex演算法之實現與分析」，碩士論文，輔仁大學，新北市，2011。
14.K. Minjae, P. Dubok, D. Han, et al., "A novel approach for denoising and enhancement of extremely low-light video," IEEE Transactions on Consumer Electronics, vol. 61, no. 1, pp. 72-80, 2015.
15.H. Malm and E. Warrant, "Motion dependent spatiotemporal smoothing for noise reduction in very dim light image sequences," in Proc. 18th International Conference on Pattern Recognition, 2006.
16.T. Arici, S. Dikbas and Y. Altunbasak, "A histogram modification framework and its application for image contrast enhancement," IEEE Transactions on Image Processing, vol. 18, no. 9, pp. 1921-1935, 2009.
17.J. T. Cheng, B. Hsieh and S. J. Wang, "Image contrast enhancement based on intensity-pair distribution," in Proc. IEEE International Conference on Image Processing, 2005.
18.E. H. Land and J. J. Mccann, "Lightness and retinex theory," Journal of the Optical Society of America, vol. 61, no. 1, pp. 1-11, 1971.
19.L. Meylan and S. Susstrunk, "High dynamic range image rendering with a retinex-based adaptive filter," IEEE Transactions on Image Processing, vol. 15, no. 9, pp. 2820-2830, 2006.
20.繆紹綱，數位影像處理，高立圖書，2003。
21.C. Tomasi and R. Manduchi, "Bilateral filtering for gray and color images," in Proc. 6th International Conference on Computer Vision, 1998.
22.G. Buchsbaum and A. Gottschalk, "Trichromacy, opponent colours coding and optimum colour information transmission in the retina," Proceedings of the Royal Society of London B: Biological Sciences, vol. 220, no. 1218, pp. 89-113, 1983.
23.N. Ponomarenko, V. Lukin, A. Zelensky, et al., "TID2008-a database for evaluation of full-reference visual quality assessment metrics," Advances of Modern Radioelectronics, vol. 10, no. 4, pp. 30-45, 2009.
24.S. J. In, J. K. Wang, T. H. Lee, et al., "Local contrast enhancement based on adaptive multiscale retinex using intensity distribution of input image," Journal of Imaging Science and Technology, vol. 55, no. 4, pp. 40502-1-40502-14, 2011.