臺灣博碩士論文加值系統

對於自動駕駛車輛的發展，車道維持是一個跨入自駕車的開端。本論文提出一可用於車道維持應用之支援彎道及直線的車道偏移警示系統設計，對於此系統開發會面臨許多的挑戰，像是在多變天候下(如：日間、夜間、雨天)須維持良好的偵測品質、車用場景快速變化造成的影像資訊雜亂，以及雨刷所造成的線條誤判，同時，一套完整的車道維持系統，須兼備偵測直線及彎道車道功能。
本論文提出隨著天候狀況自動調整閥值的動態閥值(區域閥值與全域閥值)，以在各天候下，調整出最適合的閥值以萃取車道標線特徵；並採用多張畫面驗證機制，於車速40公里以上時，可濾除背景靜止的景物、地面的路標與雨刷影響。本論文將道路平面分為較近之車道直線偵測區域，與遠方之車道曲線偵測區域，並施予不同的車道線資訊萃取參數與區域平均亮度的計算區塊大小，以得到穩定之直線與曲線車道偵測，並提出一車道曲線模型，除能標記車道曲線位置，更提供道路曲率，以利車道維持應用。本演算法實作於Renesas R-Car M2平台，並且用攝影機為影像輸入，在D1 (720x480)解析度下，效能可以達到每秒29張。在75部日間、夜間以及雨天影片測試中，車道偏移警示可達98%偵測率及97%的精準度，而彎曲車道線偵測可達93.7%的偵測率，並通過車輛測試中心ISO-17361之檢測。

Lane Keeping System (LKS) is the entrance of the autonomous car. This thesis proposes a design of the Lane Departure Warning System (LDWS) supporting curve and straight lane detection for lane keeping application. LKS encounters three challenges: keeping good enough quality in various weather conditions, avoiding from the influence of complicated scenes caused by rapid vehicle speed, and avoiding from the influence of windshield wiper. At mean time, a comprehensive LKS should be equipped with the function of detecting straight and curve lane.
This thesis proposes a Conditional Dynamic Threshold (CDT), which includes local threshold and global threshold. CDT adjusts the suitable threshold value according to weather condition at that moment, and facilitates to generate binarization image for extracting lane feature. Moreover, multiple frame approval is adopted to conquer the some effects of complicated scenes such as static objects, signs appearing temporarily, and interference of the windshield wiper. We distinguish the road surface into two parts, i.e., the near view part for straight lane detection and the far view part for curve lane detection, and apply corresponding parameters and the block size of average intensity calculation. Furthermore, a curve lane model, which not only locates the position of curve lane but also provides the essential information of LKS, i.e., the curvature of roadway, is proposed. This proposed system is implemented on Renesas R-Car M2 embedded platform with a camera, and achieves 29 frame per second at D1 (720x480) resolution. With 75 day, night, and rainy day video testing, the lane departure detection function reaches 98.9% detection rate, 97.8% precision rate, and the curve lane detection function reaches 93.7% detection rate. Besides, our LDWS is approved by ARTC with ISO-17361.

摘要 I
Abstract III
誌謝 V
List of Figures VIII
List of Tables XI
Chapter 1 Introduction 1
1.1 Background 1
1.2 Motivation 4
1.3 Organization of Thesis 5
Chapter 2 Related Works 6
2.1 Lane-mark Generation 7
2.1.1 Edge-based Detection Method 7
2.1.2 Intensity-based Detection Method 8
2.2 Straight Line Detection 10
2.2.1 Hough Transform 10
2.2.2 Inverse Perspective Mapping (IPM) 11
2.3 Curve Lane Model Selection 13
Chapter 3 Proposed Algorithm 17
3.1 Overview of Proposed Algorithm 17
3.2 Global Parameter Setting 18
3.3 Binarization 19
3.3.1 Weather Judgment 20
3.3.2 Conditional Dynamic Threshold (CDT) 21
3.4 Line thinning 24
3.5 Straight Lane Detection 25
3.5.1 Hough Transform 25
3.5.2 Line Collection 27
3.5.3 Finite State Machine (FSM) 28
3.6 Curve Lane Detection 31
3.6.1 Curve Lane Model 31
3.6.2 Curve Lane Fitting 32
3.6.3 Kalman Filter 33
3.7 Lane Keeping System (LKS) 35
3.7.1 Lane Departure Warning 35
3.7.2 Curvature Warning 36
Chapter 4 Experimental Results and Comparison 38
4.1 Implementation 38
4.2 Experimental Results and Comparison 40
4.2.1 LDWS Experiment Results 40
4.2.2 Curve Detection Experiment Results 42
4.2.3 Comparison 43
4.3 LDWS ISO Analysis 44
4.4 Lane Keeping Application Simulation 47
Chapter 5 Conclusion and Future Work 49
5.1 Conclusion 49
5.2 Future Work 50
Reference 51

[1] SAE J3016, “Taxonomy and Definitions for Terms Related to On-Road Motor Vehicle Automated Driving Systems”, 2016
[2] C. Y. Low, H. Zamzuri, S. A. Mazlan, “Simple robust road lane detection algorithm,” Intelligent and Advanced Systems (ICIAS) 2014 5th International Conference on, pp. 1-4, 2014.
[3] T. Y. Sun and W. C. Huang, “Embedded vehicle lane-marking tracking system,” 2009 IEEE 13th International Symposium on Consumer Electronics, pp. 627-631., 2009.
[4] P. Lindner, S. Blokzyl, G. Wanielik, and U. Scheunert, “Applying multi level processing for robust geometric lane feature extraction,” in Proc. 2010 IEEE Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI), pp. 248 –254, 2010.
[5] Q. Lin, Y. Han, and H. Hahn, “Real-time lane detection based on extended edge-linking algorithm,” in Proc. 2010 2nd International Conference on Computer Research and development, pp. 725-730, 2010.
[6] S. Zhow, J. Xi, J. Gong, G. Xiong, and H. Chen, “A novel lane detection based on geometrical model and Gabor filter,” in Proc. IEEE IV Symp., San Diego, CA, USA, pp. 59–64, 2010.
[7] Y. Chen, and M. He, “Sharp curve lane boundaries projective model and detection,” in Proc. 2012 10th IEEE International Conference on Industrial Informatics, pp.1188-1193, 2012.
[8] P. S. Ge, L. Guo, G. K. Xu, R. H. Zhang, and T. Zhang, “A Real-Time Lane Detection Algorithm Based on Intelligent CCD Parameters Regulation,” Discrete Dynamics in Nature and Society, 2012.
[9] C. L. Huo, Y. H. Yu, and T. Y. Sun, “Lane Departure Warning System based on Dynamic Vanishing Point Adjustment,” Proc. of 2012 IEEE 1st Conference on Consumer Electronics, pp. 25-28, 2012.
[10] Y. Dong, J. Xiong, L. Li, and J. Yang, “Robust lane detection and tracking for lane departure warning,” in Proc. 2012 International conference on Computational Problem-Solving, pp. 461-464, 2012.
[11] C. Y. Chang, and C. H. Lin, “An efficient method for lane-mark extraction in complex condition,” in Proc. International Conference on Intelligence and Computing and International Conference on Autonomic and Trusted Computing, pp. 330-336, 2012.
[12] H. Yoo, U. Yang, and K. Sohn, “Gradient-enhancing conversion for illumination-robust lane detection,” IEEE Transactions on Intelligent Transportation systems, Vol. 14, No. 3, pp. 1083-1094, 2013.
[13] W. Li, X. Gong, Y. Wang and P. Liu, “A lane marking detection and tracking algorithm based on sub-regions,” Proceedings 2014 International Conference on Informative and Cybernetics for Computational Social Systems (ICCSS), pp. 68-73 , 2014.
[14] Q. Chen and H. Wang, “A Real-time Lane Detection Algorithm Based on a Hyperbola-Pair Model,” 2006 IEEE Intelligent Vehicles Symposium, pp. 510-515 , 2006.
[15] H. Y. Lin, L. Q. Chen, Y. H. Lin and M. S. Yu, “Lane departure and front collision warning using a single camera,” 2012 International Symposium on Intelligent Signal Processing and Communications Systems, pp. 64-69, 2012.
[16] J. Wang and X. An, “A multi-step curved lane detection algorithm based on hyperbola-pair model,” 2010 IEEE International Conference on Automation and Logistics, pp. 132-137, 2010.
[17] H. J. Jang, S. H. Baek and S. Y. Park, “Curved lane detection using robust feature extraction,” The 2014 2nd International Conference on Systems and Informatics (ICSAI 2014), pp. 109-112, 2014.
[18] H. Tan, Y. Zhou, Y. Zhu, D. Yao and K. Li, “A novel curve lane detection based on Improved River Flow and RANSAC,”17th International IEEE Conference on Intelligent Transportation Systems (ITSC), pp. 133-138, 2014.
[19] M. Aly, "Real time detection of lane markers in urban streets," 2008 IEEE Intelligent Vehicles Symposium, pp. 7-12, 2008.
[20] J. Deng, and Y. Han, “A real-time system of lane detection and tracking based on optimized RANSAC B-spline fitting.” In: Proceedings of the 2013 Research in Adaptive and Convergent Systems, pp. 157-164, 2013.
[21] A. Mammeri, G. Lu and A. Boukerche, “Design of lane keeping assist system for autonomous vehicles,” 2015 7th International Conference on New Technologies, Mobility and Security (NTMS), pp. 1-5, 2015.
[22] W. Zhang, H. Li, X. Yan and Z. Liu, “A Method of Recognizing Curve Direction Based on Hough Transform,” 2016 9th International Symposium on Computational Intelligence and Design (ISCID), pp. 3-6, 2016.
[23] J. Guo, Z. Wei and D. Miao, “Lane Detection Method Based on Improved RANSAC Algorithm,”2015 IEEE Twelfth International Symposium on Autonomous Decentralized Systems, pp. 285-288, 2015.
[24] Y. C. Lin, C. C. Lin, L. T. Chen and C. K. Chen, “Adaptive IPM-based lane filtering for night forward vehicle detection,” 2011 6th IEEE Conference on Industrial Electronics and Applications, pp. 1568-1573, 2011.
[25] G. Stein and A. Shashua, “Generating a model of the path of a roadway from an image recorded by a camera” U.S. Patent 20030040864, 2003.
[26] P. Y. Hsiao, C. W. Yeh, S. S. Huang and L. C. Fu, “A Portable Vision-Based Real-Time Lane Departure Warning System: Day and Night,” in IEEE Transactions on Vehicular Technology, vol. 58, no. 4, pp. 2089-2094, 2009.
[27] D.O. Cualain, C. Hughes, M. Glavin and E. Jones, “Automotive standards-grade lane departure warning system.” IET Intelligent Transport Systems, vol. 6 no. 1 pp. 44-57, 2012.
[28] H. Li and F. Nashashibi, “Robust real-time lane detection based on lane mark segment features and general a priori knowledge,” 2011 IEEE International Conference on Robotics and Biomimetics, Karon Beach, pp. 812-817, 2011.
[29] J. Shin, E. Lee, K. Kwon and S. Lee, “Lane detection algorithm based on top-view image using random sample consensus algorithm and curve road model,” 2014 Sixth International Conference on Ubiquitous and Future Networks (ICUFN), pp. 1-2, 2014.
[30] K. H. Lim, K. P. Seng and L. M. Ang, “River Flow Lane Detection and Kalman Filtering-Based B-Spline Lane Tracking,” International Journal of Vehicular Technology, vol. 2012, 2012.
[31] Q. Li, L. Chen, M. Li, S. L. Shaw and A. Nüchter, “A Sensor-Fusion Drivable-Region and Lane-Detection System for Autonomous Vehicle Navigation in Challenging Road Scenarios,” in IEEE Transactions on Vehicular Technology, vol. 63, no. 2, pp. 540-555, 2014.
[32] R. K. Satzoda and M. M. Trivedi, “Drive Analysis Using Vehicle Dynamics and Vision-Based Lane Semantics,” in IEEE Transactions on Intelligent Transportation Systems, vol. 16, no. 1, pp. 9-18, 2015.
[33] Y. Zhou, G. Wang, G. Xu and G. Fu, “Safety driving assistance system design in intelligent vehicles,” 2014 IEEE International Conference on Robotics and Biomimetics (ROBIO 2014), pp. 2637-2642, 2014.
[34] R. F. Berriel, E. de Aguiar, V. V. d. S. Filho and T. Oliveira-Santos, “A Particle Filter-Based Lane Marker Tracking Approach Using a Cubic Spline Model,” 2015 28th SIBGRAPI Conference on Graphics, Patterns and Images, pp. 149-156, 2015.
[35] U. Ozgunalp and N. Dahnoun, “Lane detection based on improved feature map and efficient region of interest extraction,” 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP), pp. 923-927, 2015.
[36] D. C. Hernández, D. Seo and K. H. Jo, “Robust lane marking detection based on multi-feature fusion,” 2016 9th International Conference on Human System Interactions (HSI), pp. 423-428, 2016.
[37] S. Suzuki, “Lane-keeping assistive method based on the BS modification effect induced by weak electrical stimulus,” IECON 2016 - 42nd Annual Conference of the IEEE Industrial Electronics Society, pp. 5921-5928, 2016.
[38] T. Johnson, R. Sherony and H. C. Gabler, “Driver lane keeping behavior in normal driving using 100-car naturalistic driving study data,” 2016 IEEE Intelligent Vehicles Symposium (IV), pp. 227-232, 2016.
[39] D. Hoehener, G. Huang and D. Del Vecchio, “Design of a lane departure driver-assist system under safety specifications,” 2016 IEEE 55th Conference on Decision and Control (CDC), pp. 2468-2474, 2016.
[40] P. Ghimire and S. Kadagad, “Efficient location selection for computations of expensive Log-Gabor features using directional enhancement: For robust localization of lane markings in cluttered scenes,” 2016 IEEE Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER), pp. 269-276, 2016.
[41] K. Osman, J. Ghommam and M. Saad, “Combined road following control and automatic lane keeping for automated guided vehicles,” 2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV), pp. 1-6, 2016.
[42] J. H. Cho, Y. M. Jang and S. B. Cho, “Lane recognition algorithm using the Hough transform with applied accumulator cells in multi-channel ROI,” The 18th IEEE International Symposium on Consumer Electronics (ISCE 2014), pp. 1-3, 2014.
[43] ISO 17361: 2007, Intelligent transport systems – Lane departure warning systems – Performance requirements and test procedures (2007)