Lidar Based Dynamic Obstacle Detection, Tracking and Recognition Method for Driverless Cars
HUANG Rulin1,2, LIANG Huawei2, CHEN Jiajia2, ZHAO Pan2, DU Mingbo1,2
1. Department of Automation, University of Science and Technology of China, Hefei 230061, China;
2. Institute of Applying Technology, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230088, China
Abstract：Existing methods for dynamic obstacle detection and tracking have lots of shortages, such as the high false detection rate for geometric characteristics based methods, and severe influences of scanning angle and/or distance on features and motion based methods. All these issues make existing methods can't satisfy the requirements of real traffic scenarios. Targeting at aforementioned disadvantages, two methods are proposed: a multi-feature fusion based method for dynamic obstacle detection and tracking, and a spatial-temporal characteristic vector based method for obstacle recognition. Firstly, the echo pulse width of obstacles is considered based on the geometric features of dynamic obstacles to increase the accuracy of detection and tracking results. Secondly, a spatial-temporal feature vector is constructed with considering time dimension and spatial dimension information of obstacles. Thus, the SVM (support vector machine) method is used to identify dynamic obstacles to improve the recognition accuracy. Finally, the accuracy and validity of the proposed methods are verified by an autonomous vehicle in real traffic environments.
[1] Ferguson D, Darms M, Urmson C, et al. Detection, prediction, and avoidance of dynamic obstacles in urban environments[C]//IEEE Intelligent Vehicles Symposium. Piscataway, USA: IEEE, 2008: 1149-1154.
[2] Sun Z H, Bebis G, Miller R. On-road vehicle detection: A review[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(5): 694-711.
[3] Tzomakas C, von Seelen W. Vehicle detection in traffic scenes using shadows[R]. Bochum, Germany: Institut fur Neuroinformatik, Ruhr University, 1998.
[4] Gandhi T, Trivedi M M. Pedestrian protection systems: Issues, survey, and challenges[J]. IEEE Transactions on Intelligent Transportation Systems, 2007, 8(3): 413-430.
[5] Vu T D, Burlet J, Aycard O. Grid-based localization and local mapping with moving object detection and tracking[J]. Information Fusion, 2011, 12(1): 58-69.
[6] Darms M S, Rybski P E, Baker C, et al. Obstacle detection and tracking for the urban challenge[J]. IEEE Transactions on Intelligent Transportation Systems, 2009, 10(3): 475-485.
[7] 辛煜,梁华为,梅涛,等.基于激光传感器的无人驾驶汽车动态障碍物检测及表示方法[J].机器人,2014,36(6):654-661.Xin Y, Liang H W, Mei T, et al. Dynamic obstacle detection and representation approach for unmanned vehicles based on laser sensor[J]. Robot, 2014, 36(6): 654-661.
[8] Urmson C, Anhalt J, Bagnell D, et al. Autonomous driving in urban environments: Boss and the Urban Challenge[J]. Journal of Field Robotics, 2008, 25(8): 425-466.
[9] Montemerlo M, Becker J, Bhat S, et al. Junior: The Stanford entry in the Urban Challenge[J]. Journal of Field Robotics, 2008, 25(9): 569-597.
[10] 吴毅华,梁华为,王智灵,等.基于激光雷达回波信号的自适应阈值车道线检测[J].机器人,2015,37(4):451-458.Wu Y H, Liang H W, Wang Z L, et al. Lane marking detection of adaptive threshold based on echo signal of lidar[J]. Robot, 2015, 37(4): 451-458.
[11] MacLachlan R, Mertz C. Tracking of moving objects from a moving vehicle using a scanning laser rangefinder[C]//IEEE Intelligent Transportation Systems. Piscataway, USA: IEEE, 2006: 301-306.
[12] Fuerstenberg K C, Dietmayer K C J, Eisenlauer S, et al. Multilayer laserscanner for robust object tracking and classification in urban traffic scenes[C]//9th World Congress on Intelligent Transport Systems. 2002.
[13] Arras K O, Mozos O M, Burgard W. Using boosted features for the detection of people in 2D range data[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2007: 3402-3407.
[14] Hu M K. Visual pattern recognition by moment invariants[J]. IRE Transactions on Information Theory, 1962, 8(2): 179-187.
