Development of Evaluation Methodology for Rear Collision Situation Using Vehicle Sensor Data

Jaehong Park; Gunwoo Lee; Cheol Oh; Jae Hun Kim; Dukgeun Yun

doi:10.7470/jkst.2021.39.6.826

All Issue

2021 Vol.39, Issue 6 Preview Page Next Page

Article

Development of Evaluation Methodology for Rear Collision Situation Using Vehicle Sensor Data Vehicle Sensor 자료를 이용한 후미 추돌사고의 주행 안전성 평가 방법론 개발

31 December 2021. pp. 826-837

PDF XML

Abstract

Surrogate Safety Measure (SSM) is safety evaluation frameworks designed to evaluate the driving safety of a subject vehicle that is constantly interacting with other adjacent vehicles. To apply these approaches, the trajectory data of all adjacent vehicles, as well as the subject vehicle, must be obtained. Because it is nearly impossible to obtain the trajectory data from all adjacent vehicles in the real world, it is required to develop a novel approach for evaluating the driving safety that does not rely on data from adjacent vehicles. The purpose of this study is to develop a methodology to evaluate driving safety using only the subject vehicle’s trajectory data. To evaluate the driving safety of the subject vehicle, the speed, acceleration, and jerk of the subject vehicle were utilized as driving information, and the Stopping Distance Index (SDI) was employed as a SSM. Furthermore, for the development of the driving safety evaluation algorithm, Support Vector Machine (SVM), a machine learning technique, was utilized as a classifier. As a result, the derived accuracy of the classifier was at 80.1%, and therefore, it was concluded that the validity of the proposed methodology was satisfied.

Keywords

jerk

machine learning

stopping distance index (SDI)

support vector machine (SVM)

surrogate safety measure (SSM)

도로를 주행하는 차량은 인접 차량과의 끊임없는 상호 작용을 통해 차량의 주행 안전성을 확보하고자 한다. 차량의 주행 안전성은 교통안전대체지표를 사용하여 평가 할 수 있으나, 교통안전대체지표를 사용하기 위해서는 상호 작용을 형성하고 있는 주체 차량 및 선행 차량의 모든 주행 정보를 취득해야 한다. 그러나 실도로의 주행 환경에서는 주체 차량을 선행하거나 인접하고 있는 모든 차량의 주행 정보를 수집할 수 없으므로, 주체 차량의 주행 안전성을 평가하는데 한계가 존재한다. 본 연구에서는 이러한 한계점을 보완하기 위하여, 주체 차량의 주행 정보만을 이용하여 차량의 주행 안전성을 평가 할 수 있는 방법론을 개발하였다. 주체 차량의 주행 정보는 속도, 가속도, Jerk를 사용하였으며, 교통안전대체지표에는 선행 차량과 후행 차량의 정지 거리를 비교하여 주행 안전성을 평가하는 Stopping Distance Index(SDI)를 사용하였다. 또한, 주행 안전성을 평가하는 분류기로써 Support Vector Machine(SVM)을 사용했으며, 차량의 주행 정보와 SDI를 입 ‧ 출력 변수로써 사용하였다. 또한, 오차 행렬에서 산출된 분류 정확도, 특이도, 정밀도, 재현율을 기준으로 분류기의 성능을 검증하였다. 분석 결과, 주행 안전성 평가 분류기의 분류 정확도는 80.1%로 나타났으며, 본 연구에서 개발한 주행 안전성 평가 방법론에 대한 타당성을 확보했다는 결론을 제시하였다.

키워드

jerk

분류기

SDI

서포트벡터머신

교통안전대체지표

References

Aycin M. F., Benekohal R. F. (2001), Stability and Performance of Car-following Models in Congested Traffic, Journal of Transportation Engineering, 127(1), 2-12. 10.1061/(ASCE)0733-947X(2001)127:1(2)

Bagdadi O. (2013), Assessing Safety Critical Braking Events in Naturalistic Driving Studies, Transportation Research Part F: Traffic Psychology and Behaviour, 16, 117-126. 10.1016/j.trf.2012.08.006

Bagdadi O., Varhelyi A. (2011), Jerky Driving-an Indicator of Accident Proneness?, Accident Analysis and Prevention, 43, 1359-1363. 10.1016/j.aap.2011.02.00921545866

Bellem H., Schonenberg T., Krems J. F., Schrauf M. (2016), Objective Metrics of Comfort: Developing a Driving Style for Highly Automated Vehicles, Transportation Research Part F, 41, 45-54. 10.1016/j.trf.2016.05.005

Cunto F., Duong D., Saccomanno F. F. (2009), Comparison of Simulated Freeway Safety Performance to Observed Crashes, Transportation Research Record: Journal of the Transportation Research Board, 88-97. 10.3141/2103-11

Cunto F., Saccomanno F. F. (2008), Calibration and Validation of Simulated Vehicle Safety Performance at Signalized Intersections, Accident Analysis and Prevention, 40(3), 1171-1179. 10.1016/j.aap.2008.01.00318460386

Hayward J. (1971), Near Misses as a Measure of Safety at Urban Intersections, Ph.D thesis, Department of Civil Engineering, Pennsylvania State University, University Park, PA, USA.

Kim J. H., Song T. J., O C., Sung N. M. (2008), Methodology for Evaluating Collision Risks Using Vehicle Trajectory Data, J. Korean Soc. Transp., 26(5), Korean Society of Transportation, 51-62.

Kuhn M., Johnson K. (2018), Applied Predictive Modeling, Springer.

Minderhoud M. M., Bovym P. H. L. (2011), Extended Time-to-Collision Measures for Road Traffic Safety Assessment, Accident Analysis and Prevention, 33(1), 89-97. 10.1016/S0001-4575(00)00019-1

Ministry of Land, Infrastructure and Transport (2013), The User’s Manual for Digital Tachograph Analysis System.

MLTM (Ministry of Land, Infrastructure and Transport) (2020), Rules about the Road Structure and Facilities Standards Explanation.

Murphey Y. L., Milton R., Kiliaris L. (2009), Driver’s Style Classification using Jerk Analysis, In Proceedings of 2009 IEEE Symposium on Computational Intelligence in Vehicles and Vehicular Systems, 23-28. 10.1109/CIVVS.2009.4938719

Nygard M. (1999), A Method for Analysing Traffic Safety with Help of Speed Profiles, M. Sc., Tampere University of Technology, Espoo.

Oh C., Oh J., Min J. (2009), Real-Time Detection of Hazardous Traffic Events on Freeways, Transportation Research Record: Journal of the Transportation Research Board, 2129, 35-44. 10.3141/2129-05

Oh C., Park S., Ritchie S. (2006), A Method for Identifying Rear-End Collision Risks using Inductive Loop Detectors, Accident Analysis and Prevention, 38, 295-301. 10.1016/j.aap.2005.09.00916246286

Othman M. R., Zhong Z., Imamura T., Tetsuo M. (2008), A Study of Analysis Method for Driver Features Extraction, 2008 IEEE International Conference on Systems, Man and Cybernetics. 10.1109/ICSMC.2008.4811498

Park S., Lee C., Kho S. Y., Lee Y. G. (2015), Methodology for Calculating Surrogate Safety Measure by Using Vehicular Trajectory and Its Application, J. Korean Soc. Transp., 33(4), Korean Society of Transportation, 323-336. 10.7470/jkst.2015.33.4.323

Tak S., Kim S., Yeo H. (2015), Development of a Deceleration-Based Surrogate Safety Measure for Rear-End Collision Risk, IEEE Transaction on Intelligent Transportation Systems, 16(5), 2435-2445. 10.1109/TITS.2015.2409374

Talebpour A., Mahmassani H., Mete F., Hamdar S. (2014), Near-Crash Identification in a Connected Vehicle Environment, Transportation Research Record: Journal of the Transportation Research Board, 2424, 20-28. 10.3141/2424-03

Vapnik V. N. (1995), The Nature of Statistical Learning Theory, Springer-Verlag, New York. 10.1007/978-1-4757-2440-08555380

Vogel K. (2003), A Comparison of Headway and Time to Collision as Safety Indicators, Accident Analysis and Prevention, 50, 427-433. 10.1016/S0001-4575(02)00022-2

Wahlberg A. (2000), The Relation of Acceleration Force to Traffic Accident Frequency: A Pilot Study, Transportation Research Part F, 3(1), 29-38. 10.1016/S1369-8478(00)00012-7

Wu K. F., Aguero-V. J., Jovanis P. P. (2014), Using Naturalistic Driving Data to Explore the Association between Traffic Safety-Related Events and Crash Risk at Driver Level, Accident Analysis and Prevention, 72, 210-218. 10.1016/j.aap.2014.07.00525086439

Xiao J. Liu Y. (2012), Traffic Incident Detection Using Multiple-Kernel Support Vector Machine, Transportation Research Record: Journal of the Transportation Research Board, 2324, 44-52. 10.3141/2324-06

Zaki M. H., Sayed T., Shaaban K. (2014), Use of Drivers’ Jerk Profiles in Computer Vision-based Traffic Safety Evaluations, Transportation Research Record: Journal of the Transportation Research Board, 2434, 103-112. 10.3141/2434-13

Information

Publisher :Korean Society of Transportation
Publisher(Ko) :대한교통학회
Journal Title :Journal of Korean Society of Transportation
Journal Title(Ko) :대한교통학회지
Volume : 39
No :6
Pages :826-837
Received Date : 2021-07-23
Revised Date : 2021-08-13
Accepted Date : 2021-08-26
DOI :https://doi.org/10.7470/jkst.2021.39.6.826

Journal of Korean Society of Transportation ISSN:1229-1366(Print) 2234-4217(Online) 대한교통학회지

All Issue