Traffic Accident Detection with Spatiotemporal Impact Measurement

Traffic incidents continue to cause a significant loss in deaths, injuries, and property damages. Reported traffic accident data contains a considerable amount of human errors, hindering the studies on traffic accidents. Several approaches have been developed to detect accidents using traffic data in real time. However, those approaches do not consider the spatiotemporal patterns inherent in traffic data, resulting in high false alarm rates. In this paper, we study the problem of traffic accident detection by considering multiple traffic speed time series collected from road network sensors. To capture the spatiotemporal impact of traffic accidents to upstream locations, we adopt Impact Interval Grouping (IIG), which compares real-time traffic speed with historical data, and generates impact intervals to determine the presence of accidents. Furthermore, we take a multivariate time series classification approach and extract three novel features to measure the severity of traffic accidents. We use real-world traffic speed and accident datasets in our empirical evaluation, and our solutions outperform state-of-the-art approaches in multivariate time series classification.

[1]  Samuel C Tignor,et al.  FREEWAY INCIDENT-DETECTION ALGORITHMS BASED ON DECISION TREES WITH STATES , 1978 .

[2]  Liang Wang,et al.  Structure-Based Statistical Features and Multivariate Time Series Clustering , 2007, Seventh IEEE International Conference on Data Mining (ICDM 2007).

[3]  Emily Parkany,et al.  A COMPLETE REVIEW OF INCIDENT DETECTION ALGORITHMS & THEIR DEPLOYMENT: WHAT WORKS AND WHAT DOESN'T , 2005 .

[4]  Yorgos J. Stephanedes,et al.  FREEWAY INCIDENT DETECTION THROUGH FILTERING , 1993 .

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

[6]  Nick S. Jones,et al.  Highly Comparative Feature-Based Time-Series Classification , 2014, IEEE Transactions on Knowledge and Data Engineering.

[7]  M. Reinders,et al.  Multi-Dimensional Dynamic Time Warping for Gesture Recognition , 2007 .

[8]  Chetan Gupta,et al.  Forecasting Spatiotemporal Impact of Traffic Incidents on Road Networks , 2013, 2013 IEEE 13th International Conference on Data Mining.

[9]  H J Payne,et al.  DEVELOPMENT AND TESTING OF INCIDENT DETECTION ALGORITHMS, VOLUME 2: RESEARCH METHODOLOGY AND DETAILED RESULTS , 1976 .

[10]  Hui Ding,et al.  Querying and mining of time series data: experimental comparison of representations and distance measures , 2008, Proc. VLDB Endow..

[11]  Weifeng Lv,et al.  Outlier mining based Automatic Incident Detection on urban arterial road , 2009, Mobility Conference.

[12]  Cyrus Shahabi,et al.  Feature subset selection and feature ranking for multivariate time series , 2005, IEEE Transactions on Knowledge and Data Engineering.

[13]  Muzaffar Bashir,et al.  Reduced Dynamic Time Warping for Handwriting Recognition Based on Multidimensional Time Series of a Novel Pen Device , 2008 .

[14]  Cyrus Shahabi,et al.  Inferring Traffic Incident Start Time with Loop Sensor Data , 2016, CIKM.

[15]  Ayoub Al-Hamadi,et al.  A Statistical Framework for Real-Time Traffic Accident Recognition , 2010, J. Signal Inf. Process..