基于优化 DBSCAN算法的激光雷达障碍物检测

在激光雷达障碍物检测中，由于数据密度分布不均匀，传统 DBSCAN聚类算法无法同时对近距离和远距离目标实现良好聚类，容易导致漏检和误检。为了解决这个问题，改进了传统 DBSCAN算法聚类邻域半径 ε参数的选值方法，不同于传统 DBSCAN算法在聚类过程中使用统一的聚类邻域半径，而是调整为根据目标距离变化而变化的自适应聚类邻域半径。首先根据激光雷达扫描线分布求出相邻两条扫描线的间距建立 ε*列表，然后依据每个扫描点的坐标值在列表中查找出对应的列表值，最后通过线性插值法确定对应的邻域半径。福特数据集的实验结果表明，优化之后的 DBSCAN算法无论是对近距离目标还是远距离目标，其聚类效果均得到明显改善。与传统算法相比，障碍物检测正检率提高了 17.52%。

Abstract

In the process of obstacle detection based on LiDAR, the traditional DBSCAN clustering algorithm can’t achieve good clustering for both short-range and long-distance targets because of the uneven distribution of data density, resulting in missed detection or false detection. To solve the problem, this paper proposed an optimized DBSCAN algorithm which improves the adaptability under different distance by optimize the selection method of neighborhood radius. According to the distribution of the lines scanned by LiDAR, the distance between two adjacent scan lines is determined and an improved neighborhood radius list is established. Then the neighborhood radius will be searched in the list based on the coordinated values of each scan point. Finally, linear interpolation method is used to obtain the corresponding neighborhood radius. The experimental results based on Ford dataset prove that compared with the traditional DBSCAN algorithm, the proposed algorithm can effectively improve the accuracy of obstacle detection and adapt to the target clustering operation under different distances. The positive detection rate of obstacle detection is increased by 17.52%.

参考文献

[1] Kostavelis I, Nalpantidis L, Gasteratos A. Supervised traversa-bility learning for robot navigation[C]//Proceedings of the 12th Annual Conference on Towards Autonomous Robotic Systems, 2011: 289–298.

[2] 林川, 宋伟奇, 覃金飞. 基于 V-视差的障碍物检测改进方法 [J].科学技术与工程, 2014, 14(1): 86–90.

Lin C, Song W Q, Qin J F. Improved method of obstacle detec-tion based on V-disparity[J]. Science Technology and Engi-neering, 2014, 14(1): 86–90.

[3] Jazayeri A, Cai H Y, Tuceryan M, et al. Vehicle detection and tracking in car video based on motion model[J]. IEEE Transac-tions on Intelligent Transportation Systems, 2011, 12(2): 583–595.

[4] 曾丽娜. 车载视觉系统中障碍物检测与识别方法研究 [D]. 南京: 南京航空航天大学, 2016.

Zeng L N. Research on obstacle detection and identification for on-board vision systems[D]. Nanjing: Nanjing University of Aeronautics and Astronautics, 2016.

[5] 万忠涛 . 基于激光雷达的道路与障碍检测研究 [D]. 长沙: 国防科学技术大学, 2010.

Wan Z T. Research on LADAR based road and obstacles de-tection[D]. Changsha: National University of Defense Tech-nology, 2010.

[6] Himmelsbach M, Hundelshausen F V, Wuensche H J. Fast segmentation of 3D point clouds for ground ve-hicles[C]//Proceedings of 2010 IEEE Intelligent Vehicles Sym-posium, 2010: 560–565.

[7] Moras J, Cherfaoui V, Bonnifait P. Credibilist occupancy grids for vehicle perception in dynamic environ-ments[C]//Proceedings of 2011 IEEE International Conference on Robotics and Automation, 2011: 84–89.

[8] 吴伟民, 黄焕坤. 基于差分隐私保护的 DP-DBScan聚类算法研究[J].计算机工程与科学, 2015, 37(4): 830–834.

Wu W M, Huang H K. A DP-DBScan clustering algorithm based on differential privacy preserving[J]. Computer Engineering and Science, 2015, 37(4): 830–834.

[9] Azim A, Aycard O. Layer-based supervised classification of moving objects in outdoor dynamic environment using 3D laser scanner[C]//Proceedings of 2014 IEEE Intelligent Vehicles Symposium, 2014: 1408–1414.

[10] 周水庚, 周傲英, 曹晶. 基于数据分区的 DBSCAN算法[J].计算机研究与发展, 2000, 37(10): 1153–1159.

Zhou S G, Zhou A Y, Cao J. A data-partitioning-based DBSCAN algorithm[J]. Journal of Computer Research and Development, 2000, 37(10): 1153–1159.

[11] 孔栋, 孙亮, 王建强, 等. 基于 3D激光雷达点云的道路边界识别算法[J].广西大学学报(自然科学版), 2017, 42(3): 855–863.

Kong D, Sun L, Wang J Q, et al. Road boundary identification algorithm based on 3D LIDAR point cloud[J]. Journal of Gua-ngxi University (Natural Science Edition), 2017, 42(3): 855–863.

[12] 关超华, 陈泳丹, 陈慧岩, 等. 基于改进 DBSCAN算法的激光雷达车辆探测方法[J].北京理工大学学报, 2010, 30(6): 732–736.

Guan C H, Chen Y D, Chen H Y, et al. Improved DBSCAN clustering algorithm based vehicle detection using a ve-hicle-mounted laser scanner[J]. Journal of Beijing Institute of Technology, 2010, 30(6): 732–736.

[13] 于亚飞, 周爱武. 一种改进的 DBSCAN密度算法[J].计算机技术与发展, 2011, 21(2): 30–33, 38.

Yu Y F, Zhou A W. An improved algorithm of DBSCAN[J]. Computer Technology and Development, 2011, 21(2): 30–33, 38.

[14] Kaempchen N, Buehler M, Dietmayer K. Feature-level fusion for free-form object tracking using laserscanner and vid-eo[C]//Proceedings of the IEEE Proceedings. Intelligent Ve-hicles Symposium, 2005: 453–458.

[15] Chavez-Garcia R O, Burlet J, Vu T D, et al. Frontal object perception using radar and mono-vision[C]//Proceedings of 2012 IEEE Intelligent Vehicles Symposium, 2012: 159–164.

[16] Birant D, Kut A. ST-DBSCAN: an algorithm for clustering spa-tial-temporal data[J]. Data & Knowledge Engineering, 2007, 60(1): 208–221.

[17] Guo C Z, Sato W, Han L, et al. Graph-based 2D road repre-sentation of 3D point clouds for intelligent ve-hicles[C]//Proceedings of 2011 IEEE Intelligent Vehicles Sym-posium, 2011: 715–721.

[18] Barzohar M, Cooper D B. Automatic finding of main roads in aerial images by using geometric-stochastic models and esti-mation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996, 18(7): 707–721.

[19] 胡顺玺 . 基于三维激光扫描仪的车辆前方行人检测研究 [D]. 长春: 吉林大学, 2011.

Hu S X. Study on the vehicle front pedestrian detection based on 3D laser scanner[D]. Changchun: Jilin University, 2011.

[20] 冯少荣, 肖文俊. DBSCAN聚类算法的研究与改进 [J].中国矿业大学学报, 2008, 37(1): 105–111.

Feng S R, Xiao W J. An Improved DBSCAN clustering algo-rithm[J]. Journal of China University of Mining & Technology, 2008, 37(1): 105–111.

[21] Zhou J, Cheng L, Bischof W F. Online learning with novelty detection in human-guided road tracking[J]. IEEE Transactions on Geoscience and Remote Sensing, 2007, 45(12): 3967–3977.

[22] Yu Z W,Wang D X, You J, et al. Progressive subspace en-semble learning[J]. Pattern Recognition, 2016, 60: 692–705.

[23] 李龙杰. 基于四线激光雷达的道路信息提取技术研究 [D]. 北京: 北京工业大学, 2016.

Li L J. Research on technology of road information extraction based on four-layer laser radar[D]. Beijing: Beijing University of Technology, 2016.

[24] 于春和, 刘济林. 越野环境下基于四线激光雷达的障碍检测 [J]. 南京理工大学学报, 2006, 30(5): 618–621, 625.

Yu C H, Liu J L. Obstacle detection based on a four-layer laser radar in cross-country[J]. Journal of Nanjing University of Science and Technology, 2006, 30(5): 618–621, 625.

蔡怀宇, 陈延真, 卓励然, 陈晓冬. 基于优化 DBSCAN算法的激光雷达障碍物检测[J]. 光电工程, 2019, 46(7): 180514. Cai Huaiyu, Chen Yanzhen, Zhuo Liran, Chen Xiaodong. LiDAR object detection based on optimized DBSCAN algorithm[J]. Opto-Electronic Engineering, 2019, 46(7): 180514.

基于优化 DBSCAN算法的激光雷达障碍物检测

关于本站 Cookie 的使用提示

全站搜索

基于优化 DBSCAN算法的激光雷达障碍物检测

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索