||Development of a Particle Filter Based Algorithm for Lane Tracking Applied in Vehicle Localization and Autonomous Lane FollowingLane Following
||Department of Aeronautics & Astronautics
An autonomous ground vehicle requires not only a system to reliably locate itself in the global coordinate but also the local estimation with respect to the road boundary. One of the challenges will be detecting the lane which accommodates a variety of severe conditions. Hence, this thesis develops an algorithm to track the lanes by applying a Particle Filter with modified RANSAC curve fitting methods, then propagate the measurement in the next image frame. Also, the lane is modeled as a 3rd-order Bezier spline which can describe a complex geometry. Moreover, the primitive parameter of the attitude of the camera, including the pitch angle and the height, are dynamically adjusted because of the unsmooth road condition. Besides, a comparison to the pure lane detection algorithm is verified, which illustrates the improvement and capabilities of this work. In addition, the vehicle tracking problem is discussed where the lane information is used to update the GPS localization.
List of figures vi
List of Abbreviations ix
Chapter 1 Introduction 1
1.1 Motivation 1
1.2 Related work 1
1.3 Goals 3
1.4 Contribution 4
Chapter 2 Methodology (Algorithm infrastructure) 5
Chapter 3 Lane Mark Detection 10
3.1 Inverse Perspective Mapping (IPM) 10
3.2 Image Filtering and Threshold 19
3.3 Lines Detection 20
3.4 RANSAC Spline Fitting 25
3.5 Post-processing 28
3.6 Results 30
3.7 Summary 31
Chapter 4 Lane Tracking 32
4.1 Lane Evolution Model 32
4.2 Particle Filter 36
4.3 Update 37
4.4 Resampling 39
4.5 Pitch and Height Adjustment 41
4.6 Summary 42
Chapter 5 Vehicle Localization 43
5.1 Odometry Motion Model 44
5.2 Update 45
Chapter 6 Experiments 47
6.1 KITTI Dataset 47
6.2 Results 48
6.3 Validation 50
6.4 Pitch and Height Adjustment 57
6.5 Vehicle Localization 59
Chapter 7 Discussion 61
Chapter 8 Conclusions 63
 R. Risack, N. Mohler, and W. Enkelmann, "A video-based lane keeping assistant," in Proceedings of the IEEE Intelligent Vehicles Symposium 2000 (Cat. No. 00TH8511), 2000: IEEE, pp. 356-361.
 A. Borkar, M. Hayes, and M. T. Smith, "A novel lane detection system with efficient ground truth generation," IEEE Transactions on Intelligent Transportation Systems, vol. 13, no. 1, pp. 365-374, 2011.
 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, 2004.
 A. S. Huang and S. Teller, "Probabilistic lane estimation for autonomous driving using basis curves," Autonomous Robots, vol. 31, no. 2-3, p. 269, 2011.
 W. S. Wijesoma, K. S. Kodagoda, and A. P. Balasuriya, "Road-boundary detection and tracking using ladar sensing," IEEE Transactions on robotics and automation, vol. 20, no. 3, pp. 456-464, 2004.
 T. Weiss, B. Schiele, and K. Dietmayer, "Robust driving path detection in urban and highway scenarios using a laser scanner and online occupancy grids," in 2007 IEEE Intelligent Vehicles Symposium, 2007: IEEE, pp. 184-189.
 J. Canny, "A computational approach to edge detection," in Readings in computer vision: Elsevier, 1987, pp. 184-203.
 J. Illingworth and J. Kittler, "A survey of the Hough transform," Computer vision, graphics, and image processing, vol. 44, no. 1, pp. 87-116, 1988.
 M. Aly, "Real time detection of lane markers in urban streets," in 2008 IEEE Intelligent Vehicles Symposium, 2008: IEEE, pp. 7-12.
 J. Goldbeck and B. Huertgen, "Lane detection and tracking by video sensors," in Proceedings 199 IEEE/IEEJ/JSAI International Conference on Intelligent Transportation Systems (Cat. No. 99TH8383), 1999: IEEE, pp. 74-79.
 R. F. Berriel, E. de Aguiar, V. V. de Souza Filho, and T. Oliveira-Santos, "A particle filter-based lane marker tracking approach using a cubic spline model," in 2015 28th SIBGRAPI Conference on Graphics, Patterns and Images, 2015: IEEE, pp. 149-156.
 W. Lu, E. Seignez, F. S. A. Rodriguez, and R. Reynaud, "Lane marking based vehicle localization using particle filter and multi-kernel estimation," in 2014 13th International Conference on Control Automation Robotics & Vision (ICARCV), 2014: IEEE, pp. 601-606.
 H. Li and F. Nashashibi, "Lane detection (part i): Mono-vision based method," INRIA, 2013.
 M. A. Fischler and R. C. Bolles, "Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography," Communications of the ACM, vol. 24, no. 6, pp. 381-395, 1981.
 M. ALY. (2008) Real time detection of lane markers in urban streets. In: 2008 IEEE Intelligent Vehicles Symposium. IEEE, . p. 7-12.
 P. Sturm, "Pinhole camera model," Computer Vision: A Reference Guide, pp. 610-613, 2014.
 R. Hartley and A. Zisserman, Multiple view geometry in computer vision. Cambridge university press, 2003.
 A. M. Muad, A. Hussain, S. A. Samad, M. M. Mustaffa, and B. Y. Majlis, "Implementation of inverse perspective mapping algorithm for the development of an automatic lane tracking system," in 2004 IEEE Region 10 Conference TENCON 2004., 2004: IEEE, pp. 207-210.
 S. Thrun, W. Burgard, and D. Fox, Probabilistic robotics. MIT press, 2005.
 A. Geiger, P. Lenz, C. Stiller, and R. Urtasun, "Vision meets robotics: The KITTI dataset," The International Journal of Robotics Research, vol. 32, no. 11, pp. 1231-1237, 2013.
 H. Li, F. Nashashibi, and G. Toulminet, "Localization for intelligent vehicle by fusing mono-camera, low-cost GPS and map data," in 13th International IEEE Conference on Intelligent Transportation Systems, 2010: IEEE, pp. 1657-1662.
 A. S. Huang, D. Moore, M. Antone, E. Olson, and S. Teller, "Finding multiple lanes in urban road networks with vision and lidar," Autonomous Robots, vol. 26, no. 2-3, pp. 103-122, 2009.
 A. Mousavian, D. Anguelov, J. Flynn, and J. Kosecka, "3d bounding box estimation using deep learning and geometry," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 7074-7082.
 S. Song and M. Chandraker, "Robust scale estimation in real-time monocular SFM for autonomous driving," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014, pp. 1566-1573.
 N. Fanani, A. Stürck, M. Barnada, and R. Mester, "Multimodal scale estimation for monocular visual odometry," in 2017 IEEE Intelligent Vehicles Symposium (IV), 2017: IEEE, pp. 1714-1721.
 D. G. Lowe, "Distinctive image features from scale-invariant keypoints," International journal of computer vision, vol. 60, no. 2, pp. 91-110, 2004.
 H. Bay, T. Tuytelaars, and L. Van Gool, "Surf: Speeded up robust features," in European conference on computer vision, 2006: Springer, pp. 404-417.
 M. Bloesch, M. Burri, S. Omari, M. Hutter, and R. Siegwart, "Iterated extended Kalman filter based visual-inertial odometry using direct photometric feedback," The International Journal of Robotics Research, vol. 36, no. 10, pp. 1053-1072, 2017.