近年來，交通安全的議題已逐漸被重視，其中關於智慧型汽車的相關議題亦愈趨重要。在本論文中，我們設計出一智慧型駕駛輔助系統，系統的功能包括有:直線車道偵測與追蹤、彎曲車道偵測與追蹤、自動偵測前方車輛、自動相機參數校正、提供駕駛者有關前方車輛的參數(距離和高度)、提供車道的彎曲程度。
　　本論文主要的重點分成三個部份:第一個是偵測及追蹤車道，第二個是偵測及追蹤車輛，第三個則是車道以及前車參數的量測。在偵測及追蹤車道部份，我們根據車道的性質將車道分成近端車道和遠端車道，分別用直線方程式和二次曲線方程式來逼近，並將偵測左右車道的問題轉成偵測車道中線的問題以提高車道追蹤準確度。
　　在偵測車輛部份，我們利用上述所找出的車道定義成偵測前方車輛的感興趣區域，並根據車輛邊緣梯度強烈、對稱性以及車輛有特定的寬高比這些特性偵測車輛，定義出車輛的位置。在車輛追蹤的部份，我們則利用以機率密度函數(probability density function)為量測基礎的平均位移追蹤法則(mean shift tracking algorithm)來持續追蹤車輛位置。
　　利用反向透視投影對應，我們可找出二維影像上的某一點在三維世界座標的位置，藉以量測出前車的高度、前車的距離和車道的彎曲程度，以提供駕駛者安全警示。
　　本系統中，我們用來擷取影像的設備相當簡便，僅需一個數位的CCD攝影機和一台筆記型電腦。本系統已被測試在許多真實道路的影像上，藉由車道及車輛參數計算結果的評估，本系統可被證實能夠長時間成功地追蹤車道和車輛且有高準確度的安全資訊。

　　In recent years, much attention has been paid to the researches on traffic safety and intelligent vehicle (IV) system. In this thesis, we proposed an intelligent driver-assistant system which covers straight lane detection/tracking, curved lane detection/tracking, automatic vehicle detection/tracking, automatic calibration for camera parameters, and parameter assessment for front vehicle and lanes.
　　In this thesis, there are mainly three parts: (1) lane detection and tracking, (2) vehicle detection and tracking and (3) parameter assessment. In lane detection and tracking, we adopt the linear and parabolic lane models for lane boundary fitting in near field and in far field, respectively. In addition, we proposed to use a mid-line lane model instead of detecting both sides of lane boundary to improve the accuracy and robustness.
　　In vehicle detection, regions within the detected lane boundaries are first defined as the regions of interest (ROI). Then, ROI is examined to detect the front vehicle based on characteristics such as image gradients, vehicle symmetry and ratio of vehicle size. After detecting the front vehicle, a new mean-shift tracking algorithm using the proposed similarity measure is adopted for further tracking the vehicle in the successive frames. With the tracked lane and front vehicle, parameters of front vehicle and lane are obtained based on the scheme of inverse perspective mapping (IPM) and subsequently used for providing security alarms.
　　In the proposed system, only one single CCD camera is mounted on the vehicle and connected to a laptop for capturing the front view images. The proposed system has been tested with various image sequences under different road environments. According to the experimental results, the proposed system was found capable of tracking the lanes and the front vehicles successfully and accurately for a long period of time.

[1].R. Bishop, “A Survey of Intelligent Vehicle Applications Worldwide,” in Proc. IEEE Intelligent Vehicles Symposium, pp. 25-30, Oct. 2000.
[2].B. Serge and B. Michel, “Road Segmentation and Obstacle Detection by A Fast Watershed Transform,” in Proc. IEEE Intelligent Vehicles Symposium, pp. 296-301, Oct. 1994.
[3].Y. Xuan, B. Serge and B. Michel, “Road Tracking, Lane Segmentation and Obstacle Recognition by Mathematical Morphology,” in Proc. IEEE Intelligent Vehicles Symposium, pp. 166-172, June 1992.
[4].J. C. McCall and M. M. Trivedi, “An Integrated, Robust Approach to Lane Marking Detection and Lane Tracking,” in Proc. IEEE Intelligent Vehicles Symposium, pp. 533-537, June 2004.
[5].K. Y. Chiu and S. F. Lin, “Lane Detection Using Color-Based Segmentation,” in Proc. IEEE Intelligent Vehicles Symposium, pp. 706-711, June 2005.
[6].C. R. Jung and C. R. Kelber, “A Robust Linear-Parabolic Model for Lane Following,” in Proc. 17th Brazilian Symp. Computer Graphics and Image Processing, pp. 72-79, Oct. 2004.
[7].Q. Li, N. Zheng and H. Cheng “Springrobot: A Prototype Autonomous Vehicle and Its Algorithm for Lane Detection,” IEEE Trans. Intelligent Transportation Systems, vol. 5, no. 4, pp. 300-308, Dec. 2004.
[8].J. W. Lee, “A Machine Vision System for Lane-Departure Detection,” Computer Vision and Image Understanding, vol. 86, no. 1, pp. 52-78, Apr. 2002.
[9].J. W. Lee, U. K. Yi and K. R. Baek, “A Cumulative Distribution Function of Edge Direction for Road-Lane Detection,” IEICE, vol. E84-D, no. 9, pp. 1206-1216, Sep. 2001.
[10].J. W. Park, J. W. Lee and K. Y. Jhang, “A Lane-Curve Detection Based on An LCF,” Pattern Recognition Letters, vol. 24, no. 14, pp. 2301-2313, Oct. 2003.
[11].A. Watanabe and M. Nishida, “Lane Detection for A Steering Assistance System,” in Proc. IEEE Intelligent Vehicles Symposium, pp. 159-164, June 2005.
[12].Y. Wang, E. K. Teoh and D. Shen, “Lane Detection and Tracking Using B-Snake,” Image and Vision Computing, vol. 22, no. 4, pp. 269-280, Apr. 2004.
[13].Y. Wang, D. Shen and E. K. Teoh, “Lane Detection Using Catmull-Rom Spline,” in Proc. IEEE Intelligent Vehicles Symposium, pp. 51-57, Oct. 1998.
[14].Y. Wang, D. Shen and E. K. Teoh, “Lane Detection Using Spline Model,” Pattern Recognition Letters, vol. 21, no.8, pp. 677-689, June 2000.
[15].Y. He, H. Wang and B. Zhang, “Color-Based Road Detection in Urban Traffic Scenes,” IEEE Trans. Intelligent Transportation Systems, vol. 5, no. 4, Dec. 2004.
[16].D. Pomerleau, “RALPH: Rapidly Adapting Lateral Position Handler,” in Proc. IEEE Intelligent Vehicles Symposium, pp. 506-511, Sep. 1995.
[17].M. Bertozzi and A. Broggi, “Real-Time Lane and Obstacle Detection on The GOLD System,” in Proc. IEEE Intelligent Vehicles Symposium, pp. 213-218, 1996.
[18].M. Bertozzi and A. Broggi, “GOLD: A Parallel Real-Time Stereo Vision System for Generic Obstacle and Lane Detection,” IEEE Trans. Image Processing, vol. 7, no. 1, pp. 62-81, Jan. 1998.
[19].A. Broggi, “Robust Real-Time Lane and Road Detection in Critical Shadow Condition,” in Proc. IEEE Int'l Symp. Computer Vision, pp. 353-358, Nov. 1995.
[20].M. Bertozzi, A. Broggi and A. Fascioli, “Stereo Inverse Perspective Mapping: Theory and Applications,” Image and Vision Computing, vol. 16, no. 8, pp. 585-590, June 1998.
[21].A. Broggi, M. Bertozzi, A. Fascioli, C. G. L. Bianco and A. Piazzi, “Visual Perception of Obstacles and Vehicles for Platooning,” IEEE Trans. Intelligent Transportation Systems, vol. 1, no. 3, pp. 164-176, Sep. 2000.
[22].A. Broggi, P. Cerri and P. C. Antonello, “Multi-Resolution Vehicle Detection Using Artificial Vision,” in Proc. IEEE Intelligent Vehicles Symposium, pp. 310-314, June 2004.
[23].J. V. Leuven, M. B. V. Leeuwen and F. C. A. Groen, “Real-Time Vehicle Tracking in Image Sequences,” in Proc. IEEE Conf. Instrumentation and Measurement Technology, vol. 3, pp. 2049-2054, May 2001.
[24].A. W. K. So, K. Y. K. Wong, R. H. Y. Chung and F. Y. L. Chin, “Shadow Detection for Vehicles by Locating The Object-Shadow Boundary,” in Proc. IASTED Int'l Conf. Signal and Image Processing, pp. 315-319, Aug. 2005.
[25].C. Yang, R. Duraiswami and L. Davis, “Efficient Mean-Shift Tracking via A New Similarity Measure,” in Proc. IEEE Computer Society Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 176-183, June 2005.
[26].C. Yang, R. Duraiswami, A. Elgammal and L. Davis, “Real-Time Kernel-Based Tracking in Joint Feature-Spatial Spaces,” Technical Report CS-TR-4567, University of Maryland, 2004.
[27].K. She, G. Bebis, H. Gu and R. Miller, “Vehicle Tracking Using On-Line Fusion of Color and Shape Features,” in Proc. IEEE Int'l Conf. Intelligent Transportation Systems, 2004.
[28].D. Comaniciu, V. Ramesh and P. Meer, “Kernel-Based Object Tracking,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 25, no. 5, pp. 564-577, May 2003.
[29].J. G. Allen, R. Y. D. Xu and J. S. Jin, “Mean Shift Object Tracking for A SIMD Computer,” in Proc. IEEE Int'l Conf. Information Technology and Applications, vol. 1, pp. 692-697, July 2005.
[30].R. T. Collins, “Mean-Shift Blob Tracking through Scale Space,” in Proc. IEEE Computer Society Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 234-240, June 2003.
[31].H. T. Nguyen and A. W. M. Smeulders, “Fast Occluded Object Tracking by A Robust Appearance Filter,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 8, pp. 1099-1104, Aug. 2004.
[32].H. T. Nguyen, M. Worring and R. V. D. Boomgaard, “Occlusion Robust Adaptive Template Tracking,” in Proc. IEEE Int'l Conf. Computer Vision, vol. 1, pp. 678-683, July 2001.
[33].G. D. Hager and P. N. Belhumeur, “Efficient Region Tracking with Parametric Models of Geometry and Illumination,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 10, pp. 1025-1039, Oct. 1998.
[34].J. M. Collado, C. Hilario, A. de la Escalera and J. Armingol, “Model Based Vehicle Detection for Intelligent Vehicles,” in Proc. IEEE Intelligent Vehicles Symposium, pp. 572-577, June 2004.
[35].T. Xiong and C. Debrunner, “Stochastic Car Tracking with Line- and Color-Based Features,” IEEE Trans. Intelligent Transportation Systems, vol. 5, no. 4, pp. 324-328, Dec. 2004.
[36].H. Tao, H. S. Sawhney and R. Kumar, “Object Tracking with Bayesian Estimation of Dynamic Layer Representations,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, no. 1, pp. 75-89, Jan. 2002.
[37].T. Chateau and J. T. Lapreste, “Real Time Tracking with Occlusion and Illumination Variations,” in Proc. IEEE Int'l Conf. Pattern Recognition, vol. 4, pp. 763-766, Aug. 2004.
[38].S. Avidan, “Support Vector Tracking,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 8, pp. 1064-1072, Aug. 2004.
[39].M. J. Black and A. D. Jepson, “Eigentracking: Robust Matching and Tracking of Articulated Objects Using A View-Based Representation,” IJCV, vol. 26, no. 1, pp. 63-84, Jan. 1998.
[40].O. Williams, A. Blake and R. Cipolla, “A Sparse Probabilistic Learning Algorithm for Real-Time Tracking,” in Proc. IEEE Int'l Conf. Computer Vision, pp. 353-360, 2003.
[41].F. and M. B. Clowes, “Finding Picture Edges through Collinearity of Feature Points,” IEEE Trans. Computers, vol. 25, no. 4, pp. 449-456, Apr. 1976.
[42].T. Zielke, M. Brauckmann and W. V. Seelen, “Intensity and Edge-Based Symmetry Detection with An Application to Car-Following,” Image Understanding, vol. 58, no. 2, pp. 177-190, Sep. 1993.
[43].I. T. Jolliffe, Principal Component Analysis, New York: Springer-Verlag, 2002.
[44].G. Welch and G. Bishop, “An Introduction to The Kalman Filter,” TR 95-041, Apr. 2004.
[45].C. Yang, R. Duraiswami, N. A. Gumerov and L. Davis, “Improved Fast Gauss Transform and Efficient Kernel Density Estimation,” in Proc. IEEE Int'l Conf. Computer Vision, vol.1, pp. 464-471, 2003.
[46].C. Yang, R. Duraiswami and N. A. Gumerov, “Improved Fast Gauss Transform,” Technical Report CS-TR-4495, University of Maryland, 2003.
[47].V. C. Raykar, C. Yang, R, Duraiswami and N. A. Gumerov, “Fast Computation of Sums of Gaussians in High Dimensions,” Technical Report CS-TR-4767, University of Maryland, 2005.