基于KDTree树和欧式聚类的越野环境下行人识别的研究*

doi:10.19562/j.chinasae.qcgc.2019.012.009

汽车工程 ›› 2019, Vol. 41 ›› Issue (12): 1410-1415.doi: 10.19562/j.chinasae.qcgc.2019.012.009

基于KDTree树和欧式聚类的越野环境下行人识别的研究^*

范晶晶¹, 王力¹, 褚文博², 罗禹贡³

1.北方工业大学,城市道路交通智能控制技术北京重点实验室,北京 100144;
2.国汽(北京)智能网联汽车研究院有限公司,北京 100176;
3.清华大学,汽车安全与节能国家重点实验室,北京 100084

发布日期:2019-12-25
通讯作者: 范晶晶,高级工程师,E-mail:jjfan@ncut.edu.cn
基金资助:
*北方工业大学新引进教师科研启动费基金(110051360002)资助

Research on Pedestrian Recognition in Cross-country Environment Based on KDTree and Euclidean Clustering

Fan Jingjing¹, Wang Li¹, Chu Wenbo², Luo Yugong³

1.North China University of Technology, Intelligent Transportation Key Laboratory, Beijing 100144;
2.China Intelligent and Connected Vehicles Research Institute Co., Ltd., Beijing 100176;
3.Tsinghua University, State Key Laboratory of Automotive Safety and Energy, Beijing 100084

Published:2019-12-25

摘要/Abstract

摘要： 越野环境下行人的识别是班组伴随自动驾驶车辆的基础要求。本文中针对激光雷达点云数据中的行人识别问题,特别是越野环境下的特殊问题,提出基于聚类思想的解决方案。在理论分析的基础上,结合人的几何物理特征,设计了基于KDTree和欧式聚类的行人识别算法,并在越野环境下履带式车辆上进行试验。结果表明,所设计的激光雷达行人识别算法能准确识别激光雷达点云数据中的行人,在越野环境下有良好的识别率。

关键词: 行人识别, 激光雷达, 聚类

Abstract: Pedestrian recognition in cross-country environment is a fundamental requirement of group accompanied automatic driving vehicle. Aiming at the problem of pedestrian recognition in lidar point cloud data, especially under cross-country environment, a clustering-based solution is proposed in this paper. On the basis of theoretical analysis, combined with the geometric and physical features of human being, a pedestrian recognition algorithm based on KDTree and Euclidean clustering is designed and a corresponding test is carried out on tracked vehicle under corss-country environment. The results show that the lidar-based pedestrian recognition algorithm designed can accurately identify the pedestrians in lidar point cloud data, with a good recognition rate in cross-country environment.

Key words: pedestrian recognition, lidar, clustering

范晶晶, 王力, 褚文博, 罗禹贡. 基于KDTree树和欧式聚类的越野环境下行人识别的研究^*[J]. 汽车工程, 2019, 41(12): 1410-1415.

Fan Jingjing, Wang Li, Chu Wenbo, Luo Yugong. Research on Pedestrian Recognition in Cross-country Environment Based on KDTree and Euclidean Clustering[J]. Automotive Engineering, 2019, 41(12): 1410-1415.

参考文献

[1] 程健.基于三维激光雷达的实时目标检测[D].杭州:浙江大学,2014.
[2] KIDONO K, MIYASAKA T, WATANABE A, et al. Pedestrian recognition using high-definition LIDAR[C]. IEEE Intelligent Vehicles Symposium,2011:405-410.
[3] 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.
[4] NAGASHIMA T, NAGASAKI T, MATSUBARA H, et al. Object classification integrating estimation of each scan line with LiDAR[C]. IEEE Global Conference on Consumer Electronics,2017:1-4.
[5] SATO S, HASHIMOTO M, TAKITA M, et al. Multilayer lidar-based pedestrian tracking in urban environments[C]. IEEE Intelligent Vehicles Symposium,2010:849-854.
[6] YAMAMOTO T, KAWANISHI Y, IDE I, et al. Efficient pedestrian scanning by active scan LIDAR[C]. IEEE International Workshop on Advanced Image Technology,2018:1-4.
[7] LI K Q, WANG X, XU Y C, et al. Density enhancement-based long-range pedestrian detection using 3-D range data[J]. IEEE Transactions on Intelligent Transportation Systems,2016,17(5):1368-1380.
[8] MOKNI H E, GOVAERS F. Coupled laser inertial navigation system for pedestrian tracking[C]. Workshop on Positioning Navigation and Communication,2011:176-179.
[9] TANG H, CHIEN S, CHENG W, et al. Multi-cue pedestrian detection from 3D point cloud data[C]. International Conference on Multimedia and Expo,2017:1279-1284.
[10] OGAWA T, SAKAI H, SUZUKI Y, et al. Pedestrian detection and tracking using in-vehicle lidar for automotive application[C]. IEEE Intelligent Vehicles Symposium,2011:734-739.
[11] PREMEBIDA C, LUDWIG O, NUNES U, et al. Exploiting LIDAR-based features on pedestrian detection in urban scenarios[C]. International Conference on Intelligent Transportation Systems,2009:1-6.
[12] OLIVEIRA L, NUNES U. Pedestrian detection based on LIDAR-driven sliding window and relational parts-based detection[C]. IEEE Intelligent Vehicles Symposium,2013:328-333.
[13] SZARVAS M, SAKAI U, OGATA J, et al. Real-time pedestrian detection using LIDAR and convolutional neural networks[C]. IEEE Intelligent Vehicles Symposium,2006:213-218.
[14] BENEDEK C. 3D people surveillance on range data sequences of a rotating lidar[J]. Pattern Recognition Letters,2014:149-158.

[1]	胡林,李根,王方,林淼,巫宁. 基于CIDAS事故数据的路口乘用车-两轮车测试场景研究[J]. 汽车工程, 2023, 45(8): 1417-1427.
[2]	江浩斌, 路保松, 李傲雪. 汽车行驶轨迹数据密度峰值聚类算法研究[J]. 汽车工程, 2023, 45(7): 1153-1162.
[3]	武志斐,李守彪. 基于实例分割的车道线检测算法[J]. 汽车工程, 2023, 45(2): 263-272.
[4]	伍文广,田双岳,张志勇,金斌,邱增华. 凸凹不平道路几何参数识别和模型重构方法研究[J]. 汽车工程, 2023, 45(2): 273-284.
[5]	姜俊昭,杨文豪,彭彬,郭婷,徐业凯,王国卓. 基于能耗加权策略的燃料电池汽车续驶里程预测[J]. 汽车工程, 2023, 45(12): 2357-2365.
[6]	金立生,贺阳,王欢欢,霍震,谢宪毅,郭柏苍. 基于自适应阈值DBSCAN的路侧点云分割算法[J]. 汽车工程, 2022, 44(7): 987-996.
[7]	张哲雨,吕超,李景行,熊光明,吴绍斌,龚建伟. 基于车辆视角数据的行人轨迹预测与风险等级评定[J]. 汽车工程, 2022, 44(5): 675-683.
[8]	黄鹤,李文龙,杨澜,王会峰,王飚,茹锋. DHSSA优化的K均值互补迭代车型信息数据聚类[J]. 汽车工程, 2022, 44(5): 691-700.
[9]	张晓龙,江昆,孙恺,刘茂林,邵振雷,肖鹏川,杨殿阁. 激光雷达的内参建模与点云修正方法[J]. 汽车工程, 2021, 43(8): 1228-1237.
[10]	王海,李洋,蔡英凤,孙恺,陈龙. 基于激光雷达的3D实时车辆跟踪[J]. 汽车工程, 2021, 43(7): 1013-1021.
[11]	龚章鹏,王国业,于是. 基于体素网络的道路场景多类目标识别算法[J]. 汽车工程, 2021, 43(4): 469-477.
[12]	罗玉涛,秦瀚. 基于稀疏彩色点云的自动驾驶汽车3D目标检测方法[J]. 汽车工程, 2021, 43(4): 492-500.
[13]	姜武华,周松林,王其东,陈无畏,陈佳佳. 基于自适应多特征融合的路沿检测与跟踪方法研究[J]. 汽车工程, 2021, 43(12): 1762-1770.
[14]	马雷,刘泽宾,曹彪,王文举,邱泉源. 基于粗糙性度量的道路可行驶区域识别方法[J]. 汽车工程, 2021, 43(11): 1594-1601.
[15]	赵治国,王鹏,陈晓蓉,梁凯冲. 转向避撞工况下装载激光雷达车辆的障碍物跟踪[J]. 汽车工程, 2021, 43(11): 1611-1619.

基于KDTree树和欧式聚类的越野环境下行人识别的研究^*

Research on Pedestrian Recognition in Cross-country Environment Based on KDTree and Euclidean Clustering

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 10