Highway crash detection and risk estimation using deep learning.

Crash Detection is essential in providing timely information to traffic management centers and the public to reduce its adverse effects. Prediction of crash risk is vital for avoiding secondary crashes and safeguarding highway traffic. For many years, researchers have explored several techniques for early and precise detection of crashes to aid in traffic incident management. With recent advancements in data collection techniques, abundant real-time traffic data is available for use. Big data infrastructure and machine learning algorithms can utilize this data to provide suitable solutions for the highway traffic safety system. This paper explores the feasibility of using deep learning models to detect crash occurrence and predict crash risk. Volume, Speed and Sensor Occupancy data collected from roadside radar sensors along Interstate 235 in Des Moines, IA is used for this study. This real-world traffic data is used to design feature set for the deep learning models for crash detection and crash risk prediction. The results show that a deep model has better crash detection performance and similar crash prediction performance than state of the art shallow models. Additionally, a sensitivity analysis was conducted for crash risk prediction using data 1-minute, 5-minutes and 10-minutes prior to crash occurrence. It was observed that is hard to predict the crash risk of a traffic condition, 10 min prior to a crash.

[1]  Li-Li Wang,et al.  Automatic Incident Classification for Big Traffic Data by Adaptive Boosting SVM , 2015, ArXiv.

[2]  Mohamed Abdel-Aty,et al.  Real-time crash prediction models: State-of-the-art, design pathways and ubiquitous requirements. , 2019, Accident; analysis and prevention.

[3]  Rajesh Krishnan,et al.  The Use of Convolutional Neural Networks for Traffic Incident Detection at a Network Level , 2018 .

[4]  Erdogan Dogdu,et al.  A real-time autonomous highway accident detection model based on big data processing and computational intelligence , 2016, 2016 IEEE International Conference on Big Data (Big Data).

[5]  Wei Wang,et al.  Decision tree learning for freeway automatic incident detection , 2009, Expert Syst. Appl..

[6]  Sebastian Ruder,et al.  An overview of gradient descent optimization algorithms , 2016, Vestnik komp'iuternykh i informatsionnykh tekhnologii.

[7]  Emma E. Regentova,et al.  A Hybrid Model Using Logistic Regression and Wavelet Transformation to Detect Traffic Incidents , 2016 .

[8]  Juneyoung Park,et al.  Real-time crash prediction for expressway weaving segments , 2015 .

[9]  Fang Yuan,et al.  INCIDENT DETECTION USING SUPPORT VECTOR MACHINES , 2003 .

[10]  Stephen G. Ritchie,et al.  Real-time hazardous traffic condition warning system: framework and evaluation , 2005, IEEE Transactions on Intelligent Transportation Systems.

[11]  Xuan Song,et al.  Learning Deep Representation from Big and Heterogeneous Data for Traffic Accident Inference , 2016, AAAI.

[12]  Yuncai Liu,et al.  Traffic Incident Detection Using Multiple-Kernel Support Vector Machine , 2012 .

[13]  Jie Bao,et al.  A spatiotemporal deep learning approach for citywide short-term crash risk prediction with multi-source data. , 2019, Accident; analysis and prevention.

[14]  Sruthi Ashraf,et al.  A Comparative Analysis on Performance of Severe Crash Prediction Methods , 2018 .

[15]  Moinul Hossain,et al.  Understanding crash mechanism on urban expressways using high-resolution traffic data. , 2013, Accident; analysis and prevention.

[16]  Wenfang Lin,et al.  Highway traffic incident detection based on BPNN , 2010 .

[17]  Jaouad Boumhidi,et al.  Fuzzy deep learning based urban traffic incident detection , 2017, Cognitive Systems Research.

[18]  Ling Wang,et al.  Analysis of real-time crash risk for expressway ramps using traffic, geometric, trip generation, and socio-demographic predictors. , 2017, Accident; analysis and prevention.

[19]  Wei Wang,et al.  Predicting crash likelihood and severity on freeways with real-time loop detector data. , 2013, Accident; analysis and prevention.

[20]  Milos Hauskrecht,et al.  Learning to Detect Adverse Traffic Events from Noisily Labeled Data , 2007, PKDD.

[21]  Wei Wang,et al.  Construct support vector machine ensemble to detect traffic incident , 2009, Expert Syst. Appl..

[22]  Joost N. Kok,et al.  Knowledge Discovery in Databases: PKDD 2007, 11th European Conference on Principles and Practice of Knowledge Discovery in Databases, Warsaw, Poland, September 17-21, 2007, Proceedings , 2007, PKDD.

[23]  Mohamed Abdel-Aty,et al.  Identifying crash propensity using specific traffic speed conditions. , 2005, Journal of safety research.

[24]  Habibollah Nassiri,et al.  Prediction of Roadway Accident Frequencies: Count Regressions versus Machine Learning Models , 2014 .

[25]  Jinzhi Lei,et al.  A Deep Learning Approach to the Citywide Traffic Accident Risk Prediction , 2017, 2018 21st International Conference on Intelligent Transportation Systems (ITSC).

[26]  Yan Shen,et al.  Traffic Conflict Detection of Vehicle and Non-motorized Vehicle at Intersection Based on Deep Learning , 2018 .

[27]  Qi Shi,et al.  Predicting Crashes on Expressway Ramps with Real-Time Traffic and Weather Data , 2015 .

[28]  Mohamed Abdel-Aty,et al.  A data fusion framework for real-time risk assessment on freeways , 2013 .

[29]  Mohamed Abdel-Aty,et al.  Predicting Freeway Crashes from Loop Detector Data by Matched Case-Control Logistic Regression , 2004 .