拋物線偵測在道路辨識應用中是個十分重要的議題。本論文新提出了一個新穎且可偵測拋物線的三階段演算法。在第一階段中，我們採取隨機選取方式，可得到初始拋物線。在第二階段中，我們採用證據加強策略來判斷初始拋物線是否可晉升為候選拋物線。在第三階段中，我們使用所提出的新投票系統來確認候選拋物線是否為真正的拋物線。重複上述之三階段拋物線偵測程序，直到所有拋物線均偵測完畢。此外，我們提出一個機率分析模型來證實此演算法的有效性。根據一些真實的測試影像，實驗結果說明我們所提出的三階段拋物線偵測法與近年來李青等作者所提出的演算法具有相當的競爭性，然而，我們所提出的演算法其執行速度改良率可達57%。

Parabola detection is a fundamental problem in road recognition application. This thesis presents a novel three–phase algorithm for detecting parabolas. In the first phase, based on the randomized approach, an initial parabola is created. In the second phase, based on the evidence–enhancement strategy, the initial parabola may be promoted to the candidate parabola. In the third phase, a new voting scheme is presented to determine whether the candidate parabola is the true parabola or not. We continue the above three–phase parabola detection procedure until all the parabolas are detected. A probability analysis model is given to support the efficiency of our proposed approach. Under some real test images, experimental results demonstrated that the detected parabolas by using our proposed three–phase algorithm is quite competitive to the currently published algorithm by Li et al. while our proposed algorithm has about 57.0% execution–time improvement ratio.

[1] T. C. Chen and K. L. Chung, “An efficient randomized algorithm for detecting circles,” Computer Vision and Image Understanding, vol. 83, no. 2, pp. 172–191, 2001.

[2] H. Y. Cheng, B. S. Jeng, P. T. Tseng, and K. C. Fan, “Lane detection with moving vehicles in the traffic scenes,” IEEE Trans. on Intelligent Transportation Systems, vol. 7, no. 4, pp. 571–582, Dec. 2006.

[3] S. Y. Choi, J. M. Lee, “Applications of moving windows technique to autonomous vehicle navigation,” Image and Vision Computing, vol. 24, no. 2, pp. 120–130, Feb. 2006.

[4] G. H. Golub, Matrix Computations, Hopkins University Press, Baltimore, 1996.

[5] R. C. Gonzalez and R. E. Woods, Digital Image Processing, Prentice Hall, New Jersey, 2002.

[6] K. Hashimoto, “An image-processing architecture and a motion control method for an autonomous vehicle,” in Proc. of lEEE Symp. on Intelligent Vehicles, pp. 120-125, 1992.

[7] D. Hearn and M. P. Baker, Computer Graphics, Prentice Hall, New York, 1997.

[8] P. V. C. Hough, “Method and means for recognizing complex patterns,” U.S. Patent 3,069,654, Dec. 1962. 22

[9] K. Kluge, “Extracting road curvature and orientation from image edge points without perceptual grouping into features,” in Proc. of IEEE Intelligent Vehicles Symposium, pp. 109–114, 1994.

[10] S. Lakshmanan and K. Kluge, “Lane detection for automotive sensors,” in Proc. of International Conference on Acoustics, Speech, and Signal Processing, vol. 5, pp. 2955–2958, 1995.

[11] Q. Li, N. Zheng, and H. Cheng, “Springrobot: a prototype autonomous vehicle and its algorithms for lane detection,” IEEE Trans. on Intelligent Transportation Systems, vol. 5, no. 4, pp. 300–308, Dec. 2004.

[12] T. Liu, N. Zheng, H. Cheng, and Z.Xing, “A novel approach of road recognition based in deformable template and genetic algorithm,” in Proc. of Intelligent Transportation System Conf., vol. 2, pp. 1251–1256, 2003.

[13] B. Yu and A. K. Jain, “A robust and fast skew detection algorithm for generic documents,” Pattern Recognition, vol. 29, no. 10, pp, 1599–1629, 1996.

[14] B. Yu and A. K. Jain, “Lane boundary detection using a multiresolution Hough transform,” in Proc. of International Conference on Image Processing, vol. 2, pp. 748–751, 1997.

[15] http://vasc.ri.cmu.edu/idb/html/road/index.html