本論文提出對於行車記錄器所擷取的影像序列來進行車道線偵測、車輛偵測及人物偵測追蹤的整合型行車輔助系統。經過影像前處理後，偵測車道線，再基於車道線內偵側車輛，最後是對畫面中出現的人物進行偵測。車道線偵測包含直線車道線及彎曲車道線，先用簡單且有效的方法來偵測直線車道線，並加入非直線車道線之判別；在車輛偵測步驟前加入簡單的機制判斷畫面為日間或夜間，再分別針對日間及夜間的車輛偵測使用不同的方法，日間車輛偵測是使用陰影偵測法結合邊緣偵測法實現，而夜間車輛偵測是利用車尾燈進行辨識；最後找出可能為人的區域並採用Histograms of Oriented Gradients(HOG)配合Support Vector Machine(SVM)來偵測畫面中的人物。

In this thesis, we present an integrated driver assistance system with lane detection, vehicle detection, and human detection based on camera image sequences. After image preprocessing, we detect driving lanes, vehicles, and human in the region of interest. First, we propose a simple method to find the traffic lanes. In particular, we identify the traffic lanes of either straight line or curve. Furthermore, before the vehicle detection step, we determine the situation of daytime or nighttime, and then use different methods to detect the front vehicle in the region of traffic lanes. In daytime, we use the shadow detection technique and edge detection to find the regions of cars. In nighttime, pairs of tail lights of vehicles are used to detect vehicles. Finally, we use a popular algorithm, Histograms of Oriented Gradients (HOG), as a feature descriptor combined with Support Vector Machine (SVM) classifier to detect pedestrians.

論文審定書 i
致謝 ii
中文摘要 iv
Abstract v
第 1 章 緒論 1
1.1 本文大鋼 1
1.2 研究動機 1
第 2 章 研究背景與相關知識 2
2.1 行車輔助系統概述 2
2.2 道路線偵測 2
2.3 車輛偵測 3
2.3.1 日間之假定區域產生方法 3
2.3.2 夜間之假定區域產生方法 6
2.3.3 假定區域驗證方法 6
2.4 人物偵測 7
2.5 其他相關研究 9
2.5.1 RGB色彩模型[34] 9
2.5.2 HSV色彩空間[34] 10
2.5.3 灰階化 11
2.5.4 Sobel邊緣偵測 11
2.5.5 連通元件標記 12
第 3 章 道路線偵測 13
3.1 直線道路線偵測 13
3.1.1 道路線特徵點偵測 15
3.1.2 回歸直線 15
3.2 彎曲道路線偵測 16
3.2.1 彎曲方向判斷 16
3.2.2 彎曲道路線特徵點掃描 19
3.2.3 估算消失點 21
3.2.4 彎曲道路之寬度 21
3.2.5 彎曲道路線之描繪 21
第 4 章 車輛偵測 25
4.1 日間車輛偵測 25
4.1.1 陰影門檻值計算 26
4.1.2 陰影偵測 26
4.1.3 陰影排序 27
4.1.4 車輛左右邊緣偵測 27
4.1.5 車輛頂部偵測 28
4.1.6 日間車輛驗證 29
4.2 夜間車輛偵測 30
4.2.1 車尾燈特徵偵測 31
4.2.2 連通物件處理 32
4.2.3 物件排序 34
4.2.4 車尾燈配對與框選 35
4.3 日、夜間偵測模式轉換 36
4.3.1 陰影與搜尋區域之亮度差 36
4.3.2 天空亮度偵測 36
第 5 章 人物偵測 38
5.1 人物假定區域 38
5.1.1 人物左右邊緣偵測 39
5.1.2 人物頭部偵測 41
5.1.3 人物假定區域框選 43
5.2 Histograms of Oriented Gradients 43
5.2.1 梯度計算 43
5.2.2 梯度直方圖統計 43
5.2.3 區塊正規化 44
5.3 支援向量機 45
5.3.1 產生訓練資料 46
5.3.2 特徵萃取 47
5.3.3 SVM訓練 47
5.3.4 SVM預測 47
5.4 人物驗證之改善 48
第 6 章 實驗結果及分析 49
6.1 執行時間分析 49
6.2 道路線偵測結果與分析 51
6.2.1 直線道路線偵測 51
6.2.2 彎曲道路線偵測 53
6.3 車輛偵測結果與分析 56
6.3.1 日間車輛偵測 57
6.3.2 夜間車輛偵測 59
6.4 人物偵測結果與分析 61
第 7 章 結論與未來研究方向 68
7.1 結論 68
7.2 未來研究方向 68
參考文獻 69

[1]. S. Park, T. Kim, S. Kang, and K. Heon, “A Novel Signal Processing Technique for Vehicle Detection Radar,” 2003 IEEE MTT-S Int’l Microwave Symp. Digest, pp. 607-610, 2003.
[2]. C. Wang, C. Thorpe, and A. Suppe, “Ladar-Based Detection and Tracking of Moving Objects from a Ground Vehicle at High Speeds,” Proc. IEEE Intelligent Vehicles Symp., 2003.
[3]. J. Hancock, E. Hoffman, R. Sullivan, D. Ingimarson, D. Langer, and M. Hebert, “High-Performance Laser Ranger Scanner,” Proc. SPIE Int’l Conf. Intelligent Transportation Systems, 1997.
[4]. R. Chellappa, G. Qian, and Q. Zheng, “Vehicle Detection and Tracking Using Acoustic and Video Sensors,” Proc. IEEE Int’l Conf. Acoustics, Speech, and Signal Processing, pp. 793-796, 2004.
[5]. Z. Sun, G. Bebis, and R. Miller, “On-Road Vehicle Detection: A Review”, IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, pp. 694-711, 2006.
[6]. A. Kanitkar, B. Bharti, and U. N. Hivarkar, “Vision based Preceding Vehicle Detection Using Self Shadows and Structural Edge Features”, ICIIP, 2011.
[7]. M. Bertozzi, A. Broggi, M. Cellario, A. Fascioli, P. Lombardi, and M. Porta, “Artifical Vision in Road Vehicles,” Proc. IEEE, vol. 90, no. 7, pp. 1258-1271, 2002.
[8]. 張毅，”即時路面標線、車輛偵測與距離估計”，淡江大學資訊工程研究所，碩士論文，2002
[9]. 沈信良，”先進安全車輛的道路線及前車視覺偵測技術”，國立中央大學資訊工程研究所，碩士論文，2007
[10]. 石博宇，”駕駛助理視覺系統之日間高速公路前車及鄰接車輛偵測”，國立中正大學電機工程研究所，碩士論文，2003
[11]. 孫宗瀛，”結合慣性道路線標記與車輛陰影之前車偵測演算法”，國立東華大學電機工程研究所，碩士論文，2011
[12]. 鄭凌軒，”DSP-Based之車路視覺系統之研究”，國立中山大學電機工程研究所，碩士論文，2005
[13]. 林全財，”影像處理與電腦視覺技術應用於駕駛輔助系統之研究”，國立交通大學電機與控制工程研究所，碩士論文，2009
[14]. Q. Chen and H. Wang, “A real-time lane detection algorithm based on a hyperbola-pair model,” Proc. IEEE Intelligent Vehicles Symposium, pp. 510 -515 2006.
[15]. J. Wang, and X. An, “A multi-step curved lane detection algorithm based on hyperbola-pair model,” Automation and Logistics (ICAL), IEEE International Conference on. IEEE, 2010.
[16]. S.-N. Kang, et al, “Multi-lane detection based on accurate geometric lane estimation in highway scenarios, ” Intelligent Vehicles Symposium Proceedings, IEEE. pp. 221-226, 2014.
[17]. D. Scharstein, “View Synthesis Using Stereo Vision”, Dissertation of Cornell University PHD, 1997.
[18]. D. Scharstein, and R. Szeliski, ”A Taxonomy and Evaluation of Dense Two-Frame. Stereo Correspondence Algorithms”, International Journal of Computer Vision 47(1/2/3), pp. 7–42, 2002.
[19]. C.-H. Kim*, H.-K. Lee, and Y.-H. Ha, ”Disparity space image based stereo matching using optimal path searching”, Image and Video Communications and Processing, pp. 752-760, 2003.
[20]. C.-J. Tsai, and A. K. Katsaggelos, “Dense Disparity Estimation with a Divide-and-Conquer Disparity Space Image Technique”, IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 1, NO. 1, MARCH, pp. 18-29, 1999.
[21]. S. Jin, J. Cho, X.-D. Pham, K-M. Lee, S.-K. Park, M. Kim, and J.-W. Jeon, “FPGA Design and Implementation of a Real-Time Stereo Vision System”, IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, VOL. 20, NO. 1, pp. 15-26, 2010.
[22]. K. Jawed, J. M. T. Khan, and G. Gimel’farb, “High Resolution Real-time Stereo photogrammetry”, Lecture Slide of The University of Auckland New Zealand.
[23]. S.-S. Intille, and A.-F. Bobick, “Disparity-space images and large occlusion stereo”, Computer Vision - ECCV 94, pp. 179-186.
[24]. R. Yang, and M. Pollefeys, “Multi-Resolution Real-Time Stereo on Commodity Graphics Hardware”, CVPR, pp. 211, 2003.
[25]. Z. Sun, G. Bebis, and R. Miller, “On-Road Vehicle Detection: A Review”, IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, pp. 694-711, 2006.
[26]. A. Bensrhair, M. Bertozzi, A. Broggi, P. Mich´ e, S. Mousset, and G. Toulminet, “A Cooperative Approach to Vision-based Vehicle Detection“, IEEE Intelligent Transportation Systems Conference Proceedings, pp. 209-214, 2001.
[27]. Z. Sun, G. Bebis and R. Miller, ” Using Symmetry for Detecting and Locating Objects in a Picture“, COMPUTER VISION, GRAPHICS, AND IMAGE PROCESSING, pp.179-195 , 1989.
[28]. A. Kuehnle, “Symmetry-Based Recognition for Vehicle, ” RePattern Recognition Letters, vol. 12, pp. 249-258, 1991.
[29]. A. Bensrhair, M. Bertozzi, A. Broggi, P. Mich´ e, S. Mousset, and G. Toulminet, “A Cooperative Approach to Vision-based Vehicle Detection“, IEEE Intelligent Transportation Systems Conference Proceedings, pp. 209-214, 2001.
[30]. Z. Sun, R. Miller, G. Bebis, and D. DiMeo, “A Real-time Precrash Vehicle Detection System”, IEEE Workshop of CV, pp.171-176, 2002.
[31]. P. Parodi, and G. Piccioli, “A Feature-Based Recognition Scheme for Traffic Scenes,” Proc. IEEE Intelligent Vehicles Symp., pp. 229-234, 1995.
[32]. U. Handmann, T. Kalinke, C. Tzomakas, M. Werner, and W. Seelen, “An Image Processing System for Driver Assistance,” Image and Vision Computing, vol. 18, no. 5, 2000.
[33]. N. Dalal, and B. Triggs, “Histograms of oriented gradients for human detection. ” Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on. Vol. 1. IEEE, 2005.
[34]. 維基百科，http://zh.wikipedia.org/wiki/Wikipedia:首页
[35]. 陳傑琪，“基於車道線辨識之前車偵測及加速”，國立中山大學資訊工程研究所，碩士論文，2012
[36]. 呂柏漢，“基於車道線辨識之日間和夜間前車偵測辨識強化系統”，國立中山大學資訊工程研究所，碩士論文，2014
[37]. 葉冠甫，“基於單一影像之車輛偵測系統軟硬體設計”，國立中山大學資訊工程研究所，碩士論文，2012
[38]. Y.-L. Chen, C.-T. Lin, C.-J. Fan, C.-M. Hsieh, and B.-F. Wu, “Vision-based Nighttime Vehicle Detection and Range Estimation for Driver Assistance,” in Proc. IEEE Int’l Conf. on Systems, Man and Cybernetics, pp. 2988-2993, 2008.
[39]. C.-C. Wang, S.-S. Huang, and L.-C. Fu, “Driver Assistance System for Lane Detection and Vehicle Recognition with Night Vision,” in Proc. IEEE Int’l Conf. on Intelligent Robots and Systems, pp. 3530-3535, Aug. 2005.
[40]. Y. Chen, and M. He, “Sharp curve lane boundaries projective model and detection,” Iustrial Informatics (INDIN), 2012 10th IEEE International Conference, 2012.
[41]. N. Cristianini, and J. Shawe-Taylor, “An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods.” Cambridge, U.K.: Cambridge Univ. Press, 2000.
[42]. C. Cortes, and V. N. Vapnik, “Support Vector Networks,” Mach. Learn.,vol. 20, no. 3, pp. 273–297, Sep. 1995.
[43]. C.-C. Chang, and C.-J. Lin, “LIBSVM -- A Library for Support Vector Machines,” http://www.csie.ntu.edu.tw/~cjlin/libsvm/.
[44]. Daimler pedestrian dataset. [Online]. Available: http://www.gavrila.net/Research/Pedestrian_Detection/Daimler_Pedestrian_Benchmark_D/Daimler_Mono_Ped__Detection_Be/daimler_mono_ped__detection_be.html.
[45]. R. O’Malley, E. Jones, and M. Glavin, “Rear-lamp vehicle detection and tracking in low-exposure color video for night conditions,” IEEE Trans. Intell. Transp. Syst., vol. 11, no. 2, pp. 453–462, Jun. 2010.
[46]. G. Xu, et al. “Real-time pedestrian detection based on edge factor and Histogram of Oriented Gradient.” Information and Automation (ICIA), 2011 IEEE International Conference on. IEEE, 2011.
[47]. R. Varga, and N. Sergiu. “Gradient-based region of interest selection for faster pedestrian detection.” Intelligent Computer Communication and Processing (ICCP), 2013 IEEE International Conference on. IEEE, 2013.
[48]. G. J. Chen, “Monocular-vision pedestrian detection for medical vehicles.” National Central University, 2012.
[49]. G. Ma, et al. “Vision-based pedestrian detection-reliable pedestrian candidate detection by combining IPM and a 1D profile.” IEEE Intelligent Transportation Systems Conference, 2007.
[50]. R. Benenson, R. Timofte, and L. V. Gool, “Stixels estimation without depth map computation.” Computer Vision Workshops (ICCV Workshops), 2011 IEEE International Conference on. IEEE, 2011.
[51]. C.-F. Lin, et al. “Real-time pedestrian detection system with novel thermal features at night.” Instrumentation and Measurement Technology Conference (I2MTC) Proceedings, 2014 IEEE International. IEEE, 2014.
[52]. J. Hur, S.-N. Kang, and S.-W. Seo, “Multi-lane detection in urban driving environments using conditional random fields.” Intelligent Vehicles Symposium (IV), IEEE, 2013.
[53]. H.-J. Jang, S-H. Baek, and S.-Y. Park, “Curved lane detection using robust feature extraction.” Systems and Informatics (ICSAI), 2014 2nd International Conference on. IEEE, 2014.