基于车辆视角数据的行人轨迹预测与风险等级评定

doi:10.19562/j.chinasae.qcgc.2022.05.004

摘要/Abstract

摘要：

常用的基于路基视角数据的行人轨迹和风险预测模型往往无法避免复杂的建模运算和人工判断。为简洁而有效地预测行人轨迹和评定风险等级，本文中采用车辆视角数据建立行人轨迹和风险等级的预测模型，并先后进行车辆视角行人数据的采集、基于长短期记忆神经网络的行人轨迹预测和基于聚类分析-支持向量机方法的风险等级评定。实验结果表明，基于车辆视角数据所建立的数据驱动的模型能捕捉行人与车辆的运动趋势和交互特征，具有预测行人轨迹和评定风险等级的能力。

关键词: 行人轨迹预测, 行人风险等级评定, 车辆视角行人数据, 长短期记忆神经网络, 聚类分析, 支持向量机

Abstract:

The commonly used pedestrian trajectory and risk prediction model based on roadbed-perspective data often cannot avoid complex modeling calculation and manual judgment. For succinctly and effectively predicting pedestrian trajectory and evaluating risk grade， a pedestrian trajectory and risk grade prediction model is created based on vehicle-perspective pedestrian data in this paper. The acquisition of vehicle-perspective pedestrian data， the prediction of pedestrian trajectory based on long-short term memory neural network and the assessment of risk grade based on clustering analysis - support vector machine method are successively conducted. The results of experiments show that the data-driven model built based on vehicle-perspective pedestrian data can capture the movement tendency and interaction characteristics of pedestrian and vehicle and is capable of predicting pedestrian trajectory and assessing risk grade.

Key words: pedestrian trajectory prediction, pedestrian risk grade assessment, vehicle-perspective pedestrian data, long short term memory neural network, clustering analysis, support vector machine

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.

Zheyu Zhang,Lü Chao,Jinghang Li,Guangming Xiong,Shaobin Wu,Jianwei Gong. Pedestrian Trajectory Prediction and Risk Grade Assessment Based on Vehicle-Perspective Pedestrian Data[J]. Automotive Engineering, 2022, 44(5): 675-683.

图/表 11

图1

图2

图3

表1

模型符号与输入输出信息"

模型	输入	输出
$f p$	位置	位置
$f b$	标注框	位置
$f d$	距离（行人到车辆）	位置
$f b d$	标注框 + 距离	位置

表1

表2

测试集预测误差"

地点	样本数	$f p$	$f b$	$f d$	$f b d$
校园	32	0.22	0.70	2.52	0.31
魏公村	46	0.18	1.41	2.06	0.68
模型平均误差/m		0.26	0.96	2.87	0.45

表2

图4

图5

图6

表3

图7

图8

参考文献 35

1	RASOULI A， TSOTSOS J K. Autonomous vehicles that interact with pedestrians： a survey of theory and practice ［J］. IEEE Transactions on Intelligent Transportation Systems， 2019.
2	GUO J， KURUP U， SHAH M. Is it safe to drive？ an overview of factors， metrics， and datasets for driveability assessment in autonomous driving ［J］. IEEE Transactions on Intelligent Transportation Systems， 2019， 21（8）： 3135-3151.
3	MAURYA S K， CHOUDHARY A. Pedestrian detection and vulnerability decision in videos ［C］. 2019 Second International Conference on Advanced Computational and Communication Paradigms （ICACCP）. IEEE： 1-6.
4	CAMARA F， BELLOTTO N， COSAR S， et al. Pedestrian models for autonomous driving part II： high-level models of human behavior ［J］. IEEE Transactions on Intelligent Transportation Systems， 2020.
5	RUDENKO A， PALMIERI L， HERMAN M， et al. Human motion trajectory prediction： a survey ［J］. The International Journal of Robotics Research， 2020， 39（8）： 895-935.
6	CHEN Z， WU C， LYU N， et al. Pedestrian-vehicular collision avoidance based on vision system ［C］. 17th International IEEE Conference on Intelligent Transportation Systems （ITSC）. IEEE： 11-15.
7	RIDEL D A， DEO N， WOLF D， et al. Understanding pedestrian-vehicle interactions with vehicle mounted vision： an LSTM model and empirical analysis ［C］. 2019 IEEE Intelligent Vehicles Symposium （IV）. IEEE： 913-918.
8	KOOIJ J F P， SCHNEIDER N， FLOHR F， et al. Context-based pedestrian path prediction ［C］. European Conference on Computer Vision. Springer： 618-633.
9	ALAHI A， GOEL K， RAMANATHAN V， et al. Social lstm： human trajectory prediction in crowded spaces ［C］. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition， 2016： 961-971.
10	MA Y， ZHU X， ZHANG S， et al. Trafficpredict： trajectory prediction for heterogeneous traffic-agents ［C］. Proceedings of the AAAI Conference on Artificial Intelligence.33： 6120-6127.
11	QUINTERO R， PARRA I， LLORCA D F， et al. Pedestrian intention and pose prediction through dynamical models and behaviour classification ［C］. 2015 IEEE 18th International Conference on Intelligent Transportation Systems. IEEE： 83-88.
12	ROTH M， FLOHR F， GAVRILA D M. Driver and pedestrian awareness-based collision risk analysis ［C］. 2016 IEEE Intelligent Vehicles Symposium （IV）. IEEE： 454-459.
13	LEFèVRE S， VASQUEZ D， LAUGIER C. A survey on motion prediction and risk assessment for intelligent vehicles ［J］. ROBOMECH journal， 2014， 1（1）： 1-14.
14	CHEN P， ZENG W， YU G， et al. Assessing right-turning vehicle-pedestrian conflicts at intersections using an integrated microscopic simulation model ［J］. Accident Analysis， 2019， 129211-224.
15	FLORES C， MERDRIGNAC P， DE CHARETTE R， et al. A cooperative car-following/emergency braking system with prediction-based pedestrian avoidance capabilities ［J］. IEEE Transactions on Intelligent Transportation Systems， 2018， 20（5）： 1837-1846.
16	MCGILL S G， ROSMAN G， ORT T， et al. Probabilistic risk metrics for navigating occluded intersections ［J］. IEEE Robotics Automation Letters， 2019， 4（4）： 4322-4329.
17	BAO N， CARBALLO A， MIYAJIMA C， et al. Personalized subjective driving risk： analysis and prediction ［J］. Journal of Robotics， 2020， 32（3）： 503-519.
18	GAO H， ZHU J， ZHANG T， et al. Situational assessment for intelligent vehicles based on Stochastic model and Gaussian distributions in typical traffic scenarios ［J］. IEEE Transactions on Systems， Man， Cybernetics： Systems， 2020.
19	FENG J， WANG C， XU C， et al. Active collision avoidance strategy considering motion uncertainty of the pedestrian ［J］. IEEE Transactions on Intelligent Transportation Systems， 2020.
20	KIM J， KUM D. Collision risk assessment algorithm via lane-based probabilistic motion prediction of surrounding vehicles ［J］. IEEE Transactions on Intelligent Transportation Systems， 2017， 19（9）： 2965-2976.
21	CAI Y， DAI L， WANG H， et al. Pedestrian motion trajectory prediction in intelligent driving from far shot first-person perspective video ［J］. IEEE Transactions on Intelligent Transportation Systems， 2021.
22	YAGI T， MANGALAM K， YONETANI R， et al. Future person localization in first-person videos ［C］. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018： 7593-7602.
23	SONG X， CHEN K， LI X， et al. Pedestrian trajectory prediction based on deep convolutional lstm network ［J］. IEEE Transactions on Intelligent Transportation Systems， 2020.
24	XUE H， HUYNH D Q， REYNOLDS M. SS-LSTM： a hierarchical LSTM model for pedestrian trajectory prediction ［C］. 2018 IEEE Winter Conference on Applications of Computer Vision （WACV）. IEEE： 1186-1194.
25	GUTIERREZ-OSORIO C， PEDRAZA C. Modern data sources and techniques for analysis and forecast of road accidents： a review ［J］. Journal of Traffic Transportation Engineering， 2020.
26	LYU N， DUAN Z， MA C， et al. Safety margins–a novel approach from risk homeostasis theory for evaluating the impact of advanced driver assistance systems on driving behavior in near-crash events ［J］. Journal of Intelligent Transportation Systems， 2021， 25（1）： 93-106.
27	WANG X， XU X， PREVENTION. Assessing the relationship between self-reported driving behaviors and driver risk using a naturalistic driving study ［J］. Accident Analysis， 2019， 128（8-16）.
28	LI Z， WANG B， GONG J， et al. Development and evaluation of two learning-based personalized driver models for pure pursuit path-tracking behaviors ［C］. 2018 IEEE Intelligent Vehicles Symposium （IV）. IEEE： 79-84.
29	CLEVELAND W S. Robust locally weighted regression and smoothing scatterplots ［J］. Journal of the American statistical association， 1979， 74（368）： 829-836.
30	ANAYA J J， MERDRIGNAC P， SHAGDAR O， et al. Vehicle to pedestrian communications for protection of vulnerable road users ［C］. 2014 IEEE Intelligent Vehicles Symposium Proceedings. IEEE： 1037-1042.
31	LI Y， ZHANG L， SONG Y. A vehicular collision warning algorithm based on the time-to-collision estimation under connected environment ［C］. 2016 14th International Conference on Control， Automation， Robotics and Vision （ICARCV）. IEEE： 1-4.
32	MULLER K R， MIKA S， RATSCH G， et al. An introduction to kernel-based learning algorithms ［J］. IEEE Transactions on Neural Networks， 2001， 12（2）： 181-201.
33	LIKAS A， VLASSIS N， VERBEEK J J. The global k-means clustering algorithm ［J］. Pattern Recognition， 2003， 36（2）： 451-461.
34	LI J， LU C， XU Y， et al. Manifold Learning for Lane-changing behavior recognition in urban traffic ［C］. 2019 IEEE Intelligent Transportation Systems Conference （ITSC）. IEEE： 3663-3668.
35	TOMAR R S， VERMA S， TOMAR G S. SVM based trajectory predictions of lane changing vehicles ［C］. 2011 International Conference on Computational Intelligence and Communication Networks. IEEE： 716-721.

核类别	校园数据集		城区数据集
核类别	分类准确率 / %	分类速度 / s^-1	分类准确率 / %	分类速度/ s^-1
线性核	95.3	~6 900	97.7	~5 500
二次核	98.2	~8 000	97.9	~7 000
立方核	95.7	~5 000	98.6	~7 900
高斯核	96.5	~7 700	98.8	~8 500

[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]	韩勇,林旭洁,黄红武,蔡鸿瑜,罗金镕,李燕婷. 典型汽车碰撞事故场景中行人运动轨迹预测方法[J]. 汽车工程, 2023, 45(6): 1022-1030.
[3]	孙道明, 俞小莉. 随机放电工况下锂离子电池容量预测方法[J]. 汽车工程, 2020, 42(9): 1189-1196.
[4]	鲍伟, 葛建军. 基于稀疏采样数据的电动公交车电池SOC预测方法研究^*[J]. 汽车工程, 2020, 42(3): 367-374.
[5]	王岩, 梁冠群, 危银涛. 基于支持向量机的智能轮胎路面辨识算法^*[J]. 汽车工程, 2020, 42(12): 1671-1678.
[6]	朱冰, 张培兴, 赵健. 面向多维度逻辑场景的自动驾驶安全性聚类评价方法^*[J]. 汽车工程, 2020, 42(11): 1458-1463.
[7]	刘兴涛, 李坤, 武骥, 何耀, 刘新天. 基于EKF-SVM算法的动力电池SOC估计^*[J]. 汽车工程, 2020, 42(11): 1522-1528.
[8]	熊晓夏, 陈龙, 梁军, 蔡英凤, 江浩斌. 基于驾驶员避撞行为的行车风险判别方法的仿真研究^*[J]. 汽车工程, 2019, 41(2): 153-160.
[9]	刘志强，吴雪刚，倪捷，张腾. 基于HMM和SVM级联算法的驾驶意图识别[J]. 汽车工程, 2018, 40(7): 858-.
[10]	胡林, 易平, 黄晶, 张新, 雷正保. 基于真实事故案例的自动紧急制动系统两轮车测试场景研究^*[J]. 汽车工程, 2018, 40(12): 1435-1446.