植基於色調與亮度的比例影像，最近一個基於全域式門檻值(GTS)的有效演算法已被提出來偵測彩色航照圖中的陰影。不同於GTS方法中僅使用到全域式門檻值方法來區分陰影像素與非陰影像素，本篇論文提出了一個新穎的連續門檻值(STS)方法來更精確的進行陰影的偵測。在STS方法中，我們透過指數函數來修改色調與亮度的比例影像，大幅的增加陰影像素與非陰影像素之間的差距。根據修改過後的比例影像以及全域式門檻值方法，可將彩色航照圖中的每一個像素區分為候選陰影像素或非陰影像素。為了在候選陰影像素中找出真正的陰影像素，我們先將互相連接的候選陰影像素組成一系列的候選陰影區域。接著，針對各個候選陰影區域，以反覆疊代的方式來執行區域式門檻值方法，以便找出真正的陰影像素。最後，針對剩餘的候選陰影區域，我們利用一個細微的陰影決定機制來進一步檢測這些像素是否為真正的陰影像素。實驗結果顯示，在六張測試航照圖中，我們所提出的STS方法與GTS的方法在前三張測試影像上的表現相當接近。針對其他三張擁有較低亮度物件的測試影像，STS方法與GTS方法相較之下，可達到更好的偵測精確度。

Recently, an efficient algorithm based on global thresholding scheme
(GTS) was presented which uses the ratio value of the hue over the
intensity to construct the ratio map for detecting shadows of color
aerial images. Instead of only using the GTS, this thesis presents a
novel successive thresholding scheme (STS) to detect shadows more
accurately. In the proposed STS, the modified ratio map, which is
obtained by applying the exponential function to the ratio map used
in the GTS-based algorithm, is presented to stretch the gap between
the ratio values of shadow-pixels and non-shadow-pixels. By
performing the global thresholding process on the modified ratio
map, a coarse-shadow map is constructed to classify the input color
aerial image into the candidate shadow-pixels and the
non-shadow-pixels. In order to detect the true shadow-pixels from
the candidate shadow-pixels, the connected component process is
first applied to the candidate shadow-pixels for grouping the
candidate shadow regions. For each candidate shadow region, the
local thresholding process is performed iteratively to extract the
true shadow-pixels from the candidate shadow region. Finally, for
the remaining candidate shadow regions, a fine-shadow determination
process is applied to identify whether each remaining candidate
shadow-pixel is the true shadow-pixel or not. Under six testing
images, experimental results show that for the first three testing
images, the shadow detection accuracy of the proposed STS-based
algorithm is comparable to the GTS-based algorithm. For the other
three testing images which contain some low brightness objects, the
STS-based algorithm has better shadow detection accuracy when
compared to the GTS-based algorithm.

[1] T. M. Lillesand and R. W. Kiefer, Remote Sensing and Image Interpretation, 4th ed.New York: Wiley (2000).
[2] W. R. Philipson, Manual of Photographic Interpretation, 2nd ed. MD: American Society Photogrammetry and remote sensing (1997).
[3] A. Huertas and R. Nevatia, Detecting buildings in aerial images, Computer Vision, Graphics, and Image Processing,, Vol. 41, No. 2, pp. 131–152, Feb (1988).
[4] Y. Liow and T. Pavlidis, Use of shadows for extracting buildings in aerial images, Computer Vision, Graphics, and Image Processing, Vol. 49, No. 2, pp. 242–277, Feb (1990).
[5] S. Watanabe, K. Miyajima, and N. Mukawa, ”Detecting changes of buildings from aerial images using shadow and shading model,” in Proc. 14th Int. Conf. Pattern Recognition, Vol. 2, pp. 1408–1412 (1998).
[6] V. J. D. Tsai, Automatic shadow detection and radiometric restoration on digital aerial images, in Proc. Int. Geoscience and Remote Sensing Symposium, Toulouse, France, Jul. 21–25, pp. 732–733 (2003).
[7] C. Jiang, M. Ward. Shadow identification, in Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 606–612 (1992).
[8] C. Jaynes. Dynamic shadow removal from front projection displays, in Proc. IEEE Conf. Visualization, pp. 175–182 (2001).
[9] G. Finlayson, S. Hordley, M. Drew, Removing shadows from images, in: Proc. European Conf. Computer Vision, pp. 823–836 (2002).
[10] A. M. Polidorio, F. C. Flores, N. N. Imai, A. M. G. Tommaselli, and C. Franco, ”Automatic shadow segmentation in aerial color images,” in Proc. XVI Brazilian Symp. Computer Graphics and Image Processing, Oct. 12–15, pp. 270–277 (2003).
[11] J. Huang, W. Xie, and L. Tang, ”Detection of and compensation for shadows in colored urban aerial images,” in Proc. 5th World Congr. Intelligent Control and Automation, Hangzhou, China, Jun. 15–19, pp. 3098–3100 (2004).
[12] V. J. D. Tsai, ”A Comparative Study on Shadow Compensation of Color Aerial Images in Invariant Color Models,” IEEE Trans. Geoscience And Remote Sensing, Vol. 44, No. 6, pp. 1661–1671, June (2006).
[13] W. K. Pratt, Digital Image Processing, 2nd ed. NewYork:Wiley
[14] N. Otsu, ”A threshold selection method from gray level histograms,” IEEE Trans. Syst., Man, Cybern., Vol. SMC–9, No. 1, pp. 62–69, Mar. (1979).
[15] R. C. Gonzalez and R. E.Woods, Digital Image Processing, 2nd ed. MA: Addison-Wesley, 2002.
[16] D. N. F. G.Z. Yang, P. Burger, S. R. Underwood, Structure adaptive anisotropic image filtering, Image and Vision Computing, Vol. 14, No. 2, pp. 135–145 (1996).
[17] H. H. Oh, K. T. Lim, S. I. Chien, ”An improved binarization algorithm based on a water flowmodel for document image with inhomogeneous backgrounds,” Pattern Recognition Vol. 38, pp. 2612–2625 (2005).
[18] [Online]. Available: http://140.118.175.164/Huang/STS-BasedAlgorithm.zip.
[19] A. Prati, I. Mikic, M. M. Trivedi, and R. Cucchiara, ”Detecting moving shadows:Algorithms and evaluations,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 25, No. 7, pp. 918–923, Jul. (2003).
[20] J. Yao and Z. Zhang, ”Systematic static shadow detection,” in Proc. 17th Int. Conf. Pattern Recognition, Vol. 2, pp. 76–79 (2004).