A Real-Time Warning System for Rear-End Collision Based on Random Forest Classifier

Document Type : Regular Article


Department of Computer Science, Faculty of Mathematics and Computer Science, Amirkabir University of Technology, Tehran, Iran


Rear-end collision warning system has a great role to enhance driving safety. In this system, some measures are used to evaluate the safety and in the case of dangerous, the system warns drivers. This system should be executed in real-time, to remain enough time to avoid collision with the front vehicle. To this end, in this paper, a new system is developed by using a random forest classifier to extract knowledge about warning and safe situations. This knowledge can be extracted from accidents and vehicle trajectory data. Since the data of these situations are imbalanced, a combination of cost-sensitive learning and classification methods was used to improve the sensitivity, specificity, and processing time of classification. To evaluate the performance of this system, vehicle-trajectory-data of 100 cars that have been provided by Virginia tech transportation institute, are used. The comparison results are given in terms of accuracy and processing time. By using TOPSIS multi-criteria selection method, it is shown that the implemented classifier is better than different classifiers including Bayesian network, Naive Bayes, MLP neural network, support vector machine, k-nearest neighbor, rule-based methods and decision tree. The implemented random forest gets 88.4% accuracy for detection of the dangerous situations and 94.7% for detection of the safe situations. Also, the proposed system is more robust compared with the perceptual-based and kinematic-based algorithms.


Google Scholar


Main Subjects

[1]     Yan X, Radwan E, Abdel-Aty M. Characteristics of rear-end accidents at signalized intersections using multiple logistic regression model. Accid Anal Prev 2005;37:983–95. doi:10.1016/j.aap.2005.05.001.
[2]     Liang J, Chen L, Cheng X, Chen X. Multi-agent and driving behavior based rear-end collision alarm modeling and simulating. Simul Model Pract Theory 2010;18:1092–103. doi:10.1016/j.simpat.2010.02.006.
[3]     Jaraš┼źniene A, Jakubauskas G. Improvement of road safety using passive and active intelligent vehicle safety systems. Transport 2007;22:284–9.
[4]     Gietelink O, Ploeg J, De Schutter B, Verhaegen M. Development of advanced driver assistance systems with vehicle hardware-in-the-loop simulations. Veh Syst Dyn 2006;44:569–90. doi:10.1080/00423110600563338.
[5]     NHTSA N. Traffic Safety Facts, 2012 Data: Pedestrians’. Ann Emerg Med 2015;65:452.
[6]     Lee JD, McGehee D V., Brown TL, Reyes ML. Collision Warning Timing, Driver Distraction, and Driver Response to Imminent Rear-End Collisions in a High-Fidelity Driving Simulator. Hum Factors J Hum Factors Ergon Soc 2002;44:314–34. doi:10.1518/0018720024497844.
[7]     Zhao X, Jing S, Hui F, Liu R, Khattak AJ. DSRC-based rear-end collision warning system – An error-component safety distance model and field test. Transp Res Part C Emerg Technol 2019;107:92–104. doi:10.1016/j.trc.2019.08.002.
[8]     Fu Y, Li C, Luan TH, Zhang Y, Yu FR. Graded Warning for Rear-End Collision: An Artificial Intelligence-Aided Algorithm. IEEE Trans Intell Transp Syst 2020;21:565–79. doi:10.1109/TITS.2019.2897687.
[9]     Chen T, Liu K, Wang Z, Deng G, Chen B. Vehicle forward collision warning algorithm based on road friction. Transp Res Part D Transp Environ 2019;66:49–57. doi:10.1016/j.trd.2018.04.017.
[10]    Xiang Y, Huang S, Li M, Li J, Wang W. Rear-End Collision Avoidance-Based on Multi-Channel Detection. IEEE Trans Intell Transp Syst 2019:1–11. doi:10.1109/TITS.2019.2930731.
[11]    McGehee D V, Brown TL, Wilson TB, Burns M. Examination of drivers’ collision avoidance behavior in a lead vehicle stopped scenario using a front-to-rear-end collision warning system. Contract DTNH22-93-C-07326) Washington, DC Natl Highw Traffic Saf Adm 1998.
[12]    Seiler P, Song B, Hedrick JK. Development of a collision avoidance system. SAE Trans 1998:1334–40.
[13]    Brown TL, Lee JD, McGehee D V. Human Performance Models and Rear-End Collision Avoidance Algorithms. Hum Factors J Hum Factors Ergon Soc 2001;43:462–82. doi:10.1518/001872001775898250.
[14]    Tang-Hsien Chang, Chih-Sheng Hsu, Chieh Wang, Li-Kai Yang. Onboard Measurement and Warning Module for Irregular Vehicle Behavior. IEEE Trans Intell Transp Syst 2008;9:501–13. doi:10.1109/TITS.2008.928243.
[15]    Bella F, Russo R. A Collision Warning System for rear-end collision: a driving simulator study. Procedia - Soc Behav Sci 2011;20:676–86. doi:10.1016/j.sbspro.2011.08.075.
[16]    Benedetto F, Calvi A, D’Amico F, Giunta G. Applying telecommunications methodology to road safety for rear-end collision avoidance. Transp Res Part C Emerg Technol 2015;50:150–9. doi:10.1016/j.trc.2014.07.008.
[17]    Vogel K. A comparison of headway and time to collision as safety indicators. Accid Anal Prev 2003;35:427–33. doi:10.1016/S0001-4575(02)00022-2.
[18]    Naranjo JE, Gonzalez C, Garcia R, de Pedro T. Cooperative Throttle and Brake Fuzzy Control for ACC$+$ Stop&Go Maneuvers. IEEE Trans Veh Technol 2007;56:1623–30. doi:10.1109/TVT.2007.897632.
[19]    Fancher P, Bareket Z, Ervin R. Human-Centered Design of an Acc-With-Braking and Forward-Crash-Warning System. Veh Syst Dyn 2001;36:203–23. doi:10.1076/vesd.
[20]    Fujita Y, Akuzawa K, Sato M. Radar brake system. Jsae Rev 1995;1:113.
[21]    Noy YI. Ergonomics and safety of intelligent driver interfaces. CRC Press; 1997.
[22]    Kim S-Y, Kang J-K, Oh S-Y, Ryu Y-W, Kim K, Park S-C, et al. An Intelligent and Integrated Driver Assistance System for Increased Safety and Convenience Based on All-around Sensing. J Intell Robot Syst 2008;51:261–87. doi:10.1007/s10846-007-9187-0.
[23]    Dagan E, Mano O, Stein GP, Shashua A. Forward collision warning with a single camera. IEEE Intell. Veh. Symp. 2004, IEEE; n.d., p. 37–42. doi:10.1109/IVS.2004.1336352.
[24]    Kusano KD, Gabler HC. Safety Benefits of Forward Collision Warning, Brake Assist, and Autonomous Braking Systems in Rear-End Collisions. IEEE Trans Intell Transp Syst 2012;13:1546–55. doi:10.1109/TITS.2012.2191542.
[25]    Oh C, Kim T. Estimation of rear-end crash potential using vehicle trajectory data. Accid Anal Prev 2010;42:1888–93. doi:10.1016/j.aap.2010.05.009.
[26]    Moon S, Moon I, Yi K. Design, tuning, and evaluation of a full-range adaptive cruise control system with collision avoidance. Control Eng Pract 2009;17:442–55. doi:10.1016/j.conengprac.2008.09.006.
[27]    Milanés V, Pérez J, Godoy J, Onieva E. A fuzzy aid rear-end collision warning/avoidance system. Expert Syst Appl 2012;39:9097–107. doi:10.1016/j.eswa.2012.02.054.
[28]    Jamson AH, Lai FCH, Carsten OMJ. Potential benefits of an adaptive forward collision warning system. Transp Res Part C Emerg Technol 2008;16:471–84. doi:10.1016/j.trc.2007.09.003.
[29]    Ararat O, Kural E, Guvenc BA. Development of a Collision Warning System for Adaptive Cruise Control Vehicles Using a Comparison Analysis of Recent Algorithms. 2006 IEEE Intell. Veh. Symp., IEEE; n.d., p. 194–9. doi:10.1109/IVS.2006.1689627.
[30]    Liu J-F, Su Y-F, Ko M-K, Yu P-N. Development of a Vision-Based Driver Assistance System with Lane Departure Warning and Forward Collision Warning Functions. 2008 Digit. Image Comput. Tech. Appl., IEEE; 2008, p. 480–5. doi:10.1109/DICTA.2008.78.
[31]    Akhlaq M, Sheltami TR, Helgeson B, Shakshuki EM. Designing an integrated driver assistance system using image sensors. J Intell Manuf 2012;23:2109–32. doi:10.1007/s10845-011-0618-1.
[32]    Oh C, Park S, Ritchie SG. A method for identifying rear-end collision risks using inductive loop detectors. Accid Anal Prev 2006;38:295–301. doi:10.1016/j.aap.2005.09.009.
[33]    González S, García S, Li S-T, Herrera F. Chain based sampling for monotonic imbalanced classification. Inf Sci (Ny) 2019;474:187–204. doi:10.1016/j.ins.2018.09.062.
[34]    Jia X, Li W, Shang L. A multiphase cost-sensitive learning method based on the multiclass three-way decision-theoretic rough set model. Inf Sci (Ny) 2019;485:248–62. doi:10.1016/j.ins.2019.01.067.
[35]    Min F, Liu F-L, Wen L-Y, Zhang Z-H. Tri-partition cost-sensitive active learning through kNN. Soft Comput 2019;23:1557–72. doi:10.1007/s00500-017-2879-x.
[36]    Han J, Pei J, Kamber M. Data mining: concepts and techniques. Elsevier; 2011.
[37]    Custer K. 100-Car Data. VTTI, 15-Oct-2019 n.d.
[38]    Japkowicz N, Stephen S. The class imbalance problem: A systematic study1. Intell Data Anal 2002;6:429–49. doi:10.3233/IDA-2002-6504.
[39]    Ling CX, Sheng VS. Class Imbalance Problem. 2010.
[40]    Rodriguez-Galiano VF, Ghimire B, Rogan J, Chica-Olmo M, Rigol-Sanchez JP. An assessment of the effectiveness of a random forest classifier for land-cover classification. ISPRS J Photogramm Remote Sens 2012;67:93–104. doi:10.1016/j.isprsjprs.2011.11.002.
[41]    Dutta RK, Rao TG, Sharma A. Application of Random Forest Regression in the Prediction of Ultimate Bearing Capacity of Strip Footing Resting on Dense Sand Overlying Loose Sand Deposit. J Soft Comput Civ Eng 2019;3:28–40.
[42]    Dogru N, Subasi A. Traffic accident detection using random forest classifier. 2018 15th Learn. Technol. Conf., IEEE; 2018, p. 40–5. doi:10.1109/LT.2018.8368509.
[43]    Hossain M, Muromachi Y. A Bayesian network based framework for real-time crash prediction on the basic freeway segments of urban expressways. Accid Anal Prev 2012;45:373–81. doi:10.1016/j.aap.2011.08.004.
[44]    Farid DM, Zhang L, Rahman CM, Hossain MA, Strachan R. Hybrid decision tree and naïve Bayes classifiers for multi-class classification tasks. Expert Syst Appl 2014;41:1937–46. doi:10.1016/j.eswa.2013.08.089.
[45]    Wefky A, Espinosa F, Prieto A, Garcia JJ, Barrios C. Comparison of neural classifiers for vehicles gear estimation. Appl Soft Comput 2011;11:3580–99. doi:10.1016/j.asoc.2011.01.030.
[46]    Chandanshive V, Kambekar AR. Estimation of building construction cost using artificial neural networks. J Soft Comput Civ Eng 2019;3:91–107.
[47]    Cao LJ, Keerthi SS, Ong CJ, Zhang JQ, Periyathamby U, Fu XJ, et al. Parallel sequential minimal optimization for the training of support vector machines. IEEE Trans Neural Networks 2006;17:1039–49.
[48]    Aci M, ─░nan C, Avci M. A hybrid classification method of k nearest neighbor, Bayesian methods and genetic algorithm. Expert Syst Appl 2010;37:5061–7. doi:10.1016/j.eswa.2009.12.004.
[49]    Cohen WW. Fast Effective Rule Induction. Mach. Learn. Proc. 1995, Elsevier; 1995, p. 115–23. doi:10.1016/B978-1-55860-377-6.50023-2.
[50]    Quinlan JR. C4. 5: programs for machine learning. Elsevier; 2014.
[51]    Ruggieri S. Efficient C4.5 [classification algorithm]. IEEE Trans Knowl Data Eng 2002;14:438–44. doi:10.1109/69.991727.
[52]    Dingus TA, Klauer SG, Neale VL, Petersen A, Lee SE, Sudweeks J, et al. The 100-car naturalistic driving study, Phase II-results of the 100-car field experiment. United States. Department of Transportation. National Highway Traffic Safety …; 2006.
[53]    Tzeng G-H, Huang J-J. Multiple attribute decision making: methods and applications. CRC press; 2011.
[54]    Hornik K. Approximation capabilities of multilayer feedforward networks. Neural Networks 1991;4:251–7. doi:10.1016/0893-6080(91)90009-T.
[55]    Hogema JH, Janssen WH. Effects of intelligent cruise control on driving behaviour: a simulator study. TNO; 1996.
[56]    Horst RVD. Time-to-collision as a cue for decision-making in braking. Vis Veh 1991.
[57]    Saffarzadeh M, Nadimi N, Naseralavi S, Mamdoohi AR. A general formulation for time-to-collision safety indicator. Proc Inst Civ Eng - Transp 2013;166:294–304. doi:10.1680/tran.11.00031.
[58]    Lin T-W, Hwang S-L, Green PA. Effects of time-gap settings of adaptive cruise control (ACC) on driving performance and subjective acceptance in a bus driving simulator. Saf Sci 2009;47:620–5. doi:10.1016/j.ssci.2008.08.004.
[59]    Trnros J, Nilsson L, Ostlund J, Kircher A. Effects of ACC on driver behaviour, workload and acceptance in relation to minimum time headway. 9th World Congr. Intell. Transp. Syst. Am. ITS Japan, ERTICO (Intelligent Transp. Syst. Serv., 2002.
[60]    Zheng P, McDonald M. Manual vs. adaptive cruise control – Can driver’s expectation be matched? Transp Res Part C Emerg Technol 2005;13:421–31. doi:10.1016/j.trc.2005.05.001.
[61]    Fancher P. Intelligent cruise control field operational test. Final report. Volume II: appendices A-F. 1998.
[62]    Reichart G, Haller R, Naab K. Driver assistance: BMW solutions for the future of individual mobility. Intell. Transp. Realiz. Futur. Abstr. Third World Congr. Intell. Transp. Syst. Am., 1996.
[63]    Noori AM, Mikaeil R, Mokhtarian M, Haghshenas SS, Foroughi M. Feasibility of Intelligent Models for Prediction of Utilization Factor of TBM. Geotech Geol Eng 2020. doi:10.1007/s10706-020-01213-9.