A New Framework of Vehicle Collision Prediction by Combining SVM and HMM

This paper presents a framework of accident prediction with a new perspective. First, the new framework of Chain of Road Traffic Incident (CRTI) is proposed, in which the observed vehicle movement features are viewed as road traffic system’s external “performance” that, in essence, reflect the internal “health states” (safety states) of the system at a specific time. A two-stage modeling procedure of CRTI is then proposed using scenario-based strategy: 1) a support vector machine is utilized to classify leaving lane scene versus remaining in lane scene and 2) Gaussian-mixture-based hidden Markov models are developed to recognize accident versus non-accident pattern CRTI given the classified scene. Moreover, the application procedure of the CRTI framework to online collision prediction is proposed. Finally, a simulation test of a typical vehicle collision scene based on PreScan platform is designed and carried out for model training and validation, and has shown promising results in accident prediction using the proposed framework. The CRTI framework could provide a new foundation for developing early warning/intervention strategies in driver assistance system under complex traffic environments.

[1]  Evangelia Portouli,et al.  Combined Effect on Accident Risk of a Dual Task and Higher Driving Speed: A Simulator Study , 2013, HCI.

[2]  Y. Kishimoto,et al.  A modeling method for predicting driving behavior concerning with driver’s past movements , 2008, 2008 IEEE International Conference on Vehicular Electronics and Safety.

[3]  G R Preziotti,et al.  ALERT ALGORITHM DEVELOPMENT PROGRAM: NHTSA REAR-END COLLISION ALERT ALGORITHM , 2002 .

[4]  Frank D. Wood,et al.  Inference in Hidden Markov Models with Explicit State Duration Distributions , 2012, IEEE Signal Processing Letters.

[5]  Urban Kjellen,et al.  Prevention of accidents through experience feedback , 2000 .

[6]  Weihua Sheng,et al.  A Hidden Markov Model based driver intention prediction system , 2015, 2015 IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (CYBER).

[7]  Tieniu Tan,et al.  Traffic accident prediction using vehicle tracking and trajectory analysis , 2003, Proceedings of the 2003 IEEE International Conference on Intelligent Transportation Systems.

[8]  S. Glaser,et al.  Time-to-line crossing and vehicle dynamics for lane departure avoidance , 2004, Proceedings. The 7th International IEEE Conference on Intelligent Transportation Systems (IEEE Cat. No.04TH8749).

[9]  Qingfeng Huang,et al.  An adaptive peer-to-peer collision warning system , 2002, Vehicular Technology Conference. IEEE 55th Vehicular Technology Conference. VTC Spring 2002 (Cat. No.02CH37367).

[10]  Keqiang Li,et al.  Driving safety field theory modeling and its application in pre-collision warning system , 2016 .

[11]  W. V. Winsum.  THE HUMAN ELEMENT IN CAR FOLLOWING MODELS , 1999 .

[12]  A Touran,et al.  A collision model for safety evaluation of autonomous intelligent cruise control. , 1999, Accident; analysis and prevention.

[13]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[14]  Yunpeng Wang,et al.  A Car-Following Model Based on Quantified Homeostatic Risk Perception , 2013 .

[15]  Jianqiang Wang,et al.  Driving risk assessment using cluster analysis based on naturalistic driving data , 2014, 17th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[16]  Yang Li,et al.  The Driving Safety Field Based on Driver–Vehicle–Road Interactions , 2015, IEEE Transactions on Intelligent Transportation Systems.

[17]  Samer H. Hamdar,et al.  Modeling Driver Behavior as Sequential Risk-Taking Task , 2008 .

[18]  Tomasz Stańczyk,et al.  Driver reaction time to lateral entering pedestrian in a simulated crash traffic situation , 2014 .

[19]  Dario D. Salvucci.  Inferring Driver Intent: A Case Study in Lane-Change Detection , 2004 .

[20]  Gautam B. Singh,et al.  Intelligent Algorithms for Early Detection of Automotive Crashes , 2002 .

[21]  H. Mandalia,et al.  Pattern Recognition Techniques to Infer Driver Intentions , 2004 .

[22]  Francesco Bella,et al.  Combined Effect of Traffic and Geometrics on Rear-End Collision Risk , 2010 .

[23]  Kevin P. Murphy,et al.  Machine learning - a probabilistic perspective , 2012, Adaptive computation and machine learning series.

[24]  Gautam B. Singh,et al.  Using Hidden Markov Models in Vehicular Crash Detection , 2009, IEEE Transactions on Vehicular Technology.

[25]  Kalle Parkkari,et al.  SafetyNet Deliverable 5.8; In-depth accident causation database and analysis report , 2008 .

[26]  Nils Borchers,et al.  A balanced active and passive safety concept for new vehicle generations , 2003 .

[27]  Guangquan Lu,et al.  Quantitative indicator of homeostatic risk perception in car following , 2012 .

[28]  Huang Shilin.  Algorithm for airbag actuation based on artificial neural network , 1999 .

[29]  J. Hillenbrand,et al.  Situation assessment algorithm for a collision prevention assistant , 2005, IEEE Proceedings. Intelligent Vehicles Symposium, 2005..

[30]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[31]  Thomas Breitling,et al.  Enhancement of Active & Passive Safety by Future PRE-SAFE® Systems , 2005 .

[32]  Dinesh Mohan,et al.  Transport Planning and Traffic Safety : Making Cities, Roads, and Vehicles Safer , 2016 .

[33]  Wilfried Enkelmann,et al.  A video-based lane keeping assistant , 2000, Proceedings of the IEEE Intelligent Vehicles Symposium 2000 (Cat. No.00TH8511).

[34]  Alex Bateman,et al.  An introduction to hidden Markov models. , 2007, Current protocols in bioinformatics.

[35]  Uwe Franke,et al.  Towards a closer fusion of active and passive safety: Optical flow-based detection of vehicle side collisions , 2011, 2011 IEEE Intelligent Vehicles Symposium (IV).