臺灣博碩士論文加值系統

我們提出一個單張影像輸入為前提的快速且簡單的除霧演算法，以往戶外拍攝容易受到霧天氣或煙霧影響，而使得物體顏色資訊遭受遮蓋，相較於現存的除霧研究中，我們所提出的方法優點在於快速的運行速度以及簡單的運算，經由改善暗通道優先(Dark channel prior)方法，遮罩大小參數的減少可以避免因為選擇不當大小的參數而產生的光環。然而隨之而來的過度除霧問題，我們提出兩種非線性修正函式(Gamma correction function及piecewise linear function)修正深度表並且調整除霧影像之顏色。
另外利用光流法，針對霧影片進行除霧，由光流法找出前後frame之相對關係，利用前一張frame的深度表資估算出下一frame之深度表(transmission map)，進而達到影片除霧。
由於我們所提出的方法運算是簡單且有效率的，可以在有限計算能力的平台上執行(如:智慧型手機、數位相機等等)，達到影像除霧的目的。

We propose a simple and fast algorithm for haze removal in a single input image. During the processing of outdoor images, the presence of haze or smoke reduces the color information of the observed objects. Compare with the existing methods, the proposed method has the advantage of fast processing speed because of the modification of the dark channel prior during the estimation of the transmission. Further, the modification of the parameter reduction of the patch size can avoid the halo effect, which is caused by the improper patch size setting, in the haze-free image. Nevertheless, the restored image is unnatural because of over-dehazing. Two non-linear correction functions are proposed to refine the transmission and adjust the color of the restored image. Because all the operations are simple and efficient, the proposed method is suitable for applications performed on a platform with a limited computing ability, e.g., a digital camera or a smart phone, while simultaneously obtaining the promising dehazing results.

目錄
摘要 ii
誌 謝 iii
目錄 iv
圖目錄 v
表目錄 vii
一.導論 1
1.1研究動機 1
1.2研究貢獻 3
1.3研究架構 4
二.文獻探討 5
2.1多張影像輸入除霧 5
2.2單張影像輸入 7
三.研究方法 9
3.1 Transmission estimation by modified dark channel prior 10
3.2 Transmission refinement using nonlinear correction function 12
3.3 Haze-free image recovery 15
3.4 Video dehaze using optic flow 16
四. 實驗與討論 19
4.1 Evaluation of computational performance 20
4.2 Comparisons on scene and road images 22
4.3 Video defog 27
五. 結論與展望 32
參考文獻 33

[1]V. Abolghasemi and A. Ahmadyfard, “An Edge-based Color-aided Method for License Plate Detection,” Image and Vision Computing, Vol. 27, No. 8, pp. 1134-1142, 2009.
[2]Y. Wen, Y. Lu, J. Yan, Z. Zhou, K.M. von Deneen, and P. Shi, “An Algorithm for License Plate Recognition Applied to Intelligent Transportation System,” IEEE Transactions on Intelligent Transportation Systems, Vol. 12, pp. 830-845, 2011.
[3]Y.Y. Schechner, S.G. Narasimhan, and S.K. Nayar, “Instant Dehazing of Images Using Polarization,” IEEE Conference on Computer Vision and Pattern Recognition, Vol. 1, pp. 325-332, 2001.
[4]S. Shwartz, E. Namer, and Y.Y. Schechner, “Blind Haze Separation,” IEEE Conference on Computer Vision and Pattern Recognition, Vol. 2, pp. 1984-1991, 2006.
[5]S.G. Narasimhan and S.K. Nayar, “Vision and the Atmosphere,” International Journal of Computer Vision, Vol. 48, pp. 233-254, 2002.
[6]S.G. Narasimhan and S.K. Nayar, “Chromatic Framework for Vision in Bad Weather,” IEEE Conference on Computer Vision and Pattern Recognition, Vol. 1, pp. 598-605, 2000.
[7]S.G. Narasimhan and S.K. Nayar, “Contrast Restoration of Weather Degraded Images,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 25, No. 6 pp. 713-724, 2003.
[8]E. Marltin and P. Milanfar, “Removal of Haze and Noise from a Single Image,” SPIE, Vol. 8296, 2012.
[9]S.K. Nayar and S.G. Narasimhan, “Vision in Bad Weather,” IEEE Conference on Computer Vision, Vol. 2, pp. 820-827, 1999.
[10]L. Schaul, C. Fredembach, and S. Susstrunk, “Color Image Dehazing Using the Near-infrared,” IEEE Conference on Image Processing, pp. 1629-1632, 2009.
[11]R. Fattal, “Single Image Dehazing,” SIGGRAPH, 2008.
[12]X. Lv, W. Chen, and I. Shen, “Real-time Dehazing for Image and Video,” IEEE Conference on Computer Graphics and Applications, pp. 62-69, 2010.
[13]J.P. Tarel and N. Hauti´ere, “Fast Visibility Restoration from a Single Color or Gray Level Image,” International Conference on Computer Vision, pp. 2201-2208, 2009.
[14]R. Tan, “Visibility in Bad Weather from a Single Image,” IEEE Conference Computer on Vision and Pattern Recognition, pp. 1-8, 2008.
[15]K. He, J. Sun, and X. Tang, “Single Image Haze Removal Using Dark Channel Prior,” IEEE Conference on Computer Vision and Pattern Recognition, pp. 1956-1963, 2009.
[16]A. Levin, D. Lischinski, and Y. Weiss, “A Closed Form Solution to Natural Image Matting,” IEEE Conference on Computer Vision and Pattern Recognition, Vol. 1, pp. 61-68, 2006.
[17]C. Tomasi and R. Manduchi, “Bilateral Filtering for Gray and Color Images,” International Conference on Computer Vision, pp. 839-846, 1998.
[18] http://opencv.org/