Detecting Anomalous Trajectories Using the Dempster-Shafer Evidence Theory Considering Trajectory Features from Taxi GNSS Data

In road networks, an ‘optimal’ trajectory is a geometrically optimal drive from the source point to the destination point. In reality, the driver’s driving experience or road traffic conditions will lead to differences between the ‘actual’ trajectory and the ‘optimal’ trajectory. When the differences are excessive, these trajectories are considered as anomalous trajectories. In addition, these differences can be observed in various trajectory features, such as velocity, distance, turns, and intersections. In this paper, our aim is to fuse these trajectory features and to quantitatively describe this difference to infer anomalous trajectories. The Dempster-Shafer (D-S) evidence theory is a theory and method that uses different features as evidence to infer uncertainty. The theory does not require prior knowledge or conditional probabilities. Therefore, we propose an automatic, anomalous trajectory inference method based on the D-S evidence theory that considers driving behavior and road network constraints. To achieve this objective, we first obtain all of the ‘actual’ trajectories of drivers for different source-destination pairs in taxi Global Navigation Satellite System (GNSS) trajectories. Second, we define and extract five trajectory features: route selection ( R S ), intersection rate ( I R ), heading change rate ( HCR ) , slow point rate ( SPR ), and velocity change rate ( VCR ) . Then, different features of each trajectory are combined as evidence according to Dempster’s combinational rule. The precise probability interval of each trajectory is calculated based on the D-S evidence theory. Finally, we obtain the anomalous possibility of all real trajectories and infer anomalous trajectories whose trajectory features are significantly different from normal ones. The experimental results show that the proposed method can infer anomalous trajectories effectively and that it can be used to monitor driver behavior automatically and to discover adverse urban traffic events.

[1]  Henry A. Kautz,et al.  Recognizing Multi-Agent Activities from GPS Data , 2010, AAAI.

[2]  S. Phithakkitnukoon,et al.  Urban mobility study using taxi traces , 2011, TDMA '11.

[3]  Gian Luca Foresti,et al.  Distributed architectures and logical-task decomposition in multimedia surveillance systems , 2001, Proc. IEEE.

[4]  Andrew Hunter,et al.  Application of the self-organising map to trajectory classification , 2000, Proceedings Third IEEE International Workshop on Visual Surveillance.

[5]  Blas Galván,et al.  Application of Dempster-Shafer theory for the quantification and propagation of the uncertainty caused by the use of AIS data , 2013, Reliab. Eng. Syst. Saf..

[6]  Ilya Kolmanovsky,et al.  A New Clustering Algorithm for Processing GPS-Based Road Anomaly Reports With a Mahalanobis Distance , 2017, IEEE Transactions on Intelligent Transportation Systems.

[7]  Jae-Gil Lee,et al.  Trajectory Outlier Detection: A Partition-and-Detect Framework , 2008, 2008 IEEE 24th International Conference on Data Engineering.

[8]  Ronald R. Yager,et al.  Classic Works of the Dempster-Shafer Theory of Belief Functions , 2010, Classic Works of the Dempster-Shafer Theory of Belief Functions.

[9]  Hai Huang,et al.  Anomalous behavior detection in single-trajectory data , 2015, Int. J. Geogr. Inf. Sci..

[10]  Andreas Leich,et al.  Identifying hazardous locations at intersections by automatic traffic surveillance , 2015 .

[11]  Donald B. Johnson,et al.  A Note on Dijkstra's Shortest Path Algorithm , 1973, JACM.

[12]  Yang Gao,et al.  TRASMIL: A local anomaly detection framework based on trajectory segmentation and multi-instance learning , 2013, Comput. Vis. Image Underst..

[13]  Liu Liang.  Efficient Trajectory Outlier Detection Algorithm Based on R-Tree , 2009 .

[14]  Stephan Winter,et al.  Detecting Urban Transport Modes Using a Hybrid Knowledge Driven Framework from GPS Trajectory , 2016, ISPRS Int. J. Geo Inf..

[15]  Minjie Zhang,et al.  An approach for real-time urban traffic state estimation by fusing multisource traffic data , 2012, WCICA 2012.

[16]  Hui Xiong,et al.  A taxi business intelligence system , 2011, KDD.

[17]  Xintao Liu,et al.  Uncovering Spatio-Temporal Cluster Patterns Using Massive Floating Car Data , 2013, ISPRS Int. J. Geo Inf..

[18]  Gian Luca Foresti,et al.  Multimedia Video-Based Surveillance Systems: Requirements, Issues and Solutions , 2000 .

[19]  Junghans Marek,et al.  Chances for the evaluation of the traffic safety risk at intersections by novel methods , 2015 .

[20]  Guangnian Xiao,et al.  Travel mode detection based on GPS track data and Bayesian networks , 2015, Comput. Environ. Urban Syst..

[21]  Wei-Ying Ma,et al.  Understanding mobility based on GPS data , 2008, UbiComp.

[22]  Marek Junghans,et al.  Analysis of traffic safety for cyclists: the automatic detection of critical traffic situations for cyclists , 2014 .

[23]  Hui Xiong,et al.  A Taxi Driving Fraud Detection System , 2011, 2011 IEEE 11th International Conference on Data Mining.

[24]  Jie Zhu,et al.  Effective and efficient trajectory outlier detection based on time-dependent popular route , 2016, World Wide Web.

[25]  Zhi-Hua Zhou,et al.  iBAT: detecting anomalous taxi trajectories from GPS traces , 2011, UbiComp '11.

[26]  Jie Chen,et al.  Improvement of DS Evidence Theory for Multi-Sensor Conflicting Information , 2017, Symmetry.

[27]  Christos Faloutsos,et al.  F-Trail: Finding Patterns in Taxi Trajectories , 2013, PAKDD.

[28]  Yixiang Chen,et al.  Detecting Anomalous Trajectories and Behavior Patterns Using Hierarchical Clustering from Taxi GPS Data , 2018, ISPRS Int. J. Geo Inf..

[29]  Irfan A. Essa,et al.  Gaussian process regression flow for analysis of motion trajectories , 2011, 2011 International Conference on Computer Vision.

[30]  Nilanjan Dey,et al.  Advanced Topological Map Matching Algorithm Based on D–S Theory , 2018 .

[31]  Chunhua Hu,et al.  A method for real-time trajectory monitoring to improve taxi service using GPS big data , 2016, Inf. Manag..

[32]  Uwe Aickelin,et al.  Data classification using the Dempster–Shafer method , 2014, J. Exp. Theor. Artif. Intell..

[33]  Sangkyum Kim,et al.  Motion-Alert: Automatic Anomaly Detection in Massive Moving Objects , 2006, ISI.

[34]  Yikai Chen,et al.  An Improved Evidential Fusion Approach for Real-time Urban Link Speed Estimation , 2007, 2007 IEEE Intelligent Transportation Systems Conference.

[35]  Po-Ruey Lei,et al.  A framework for anomaly detection in maritime trajectory behavior , 2015, Knowledge and Information Systems.

[36]  Pavel V. Sevastjanov,et al.  An interpretation of intuitionistic fuzzy sets in terms of evidence theory: Decision making aspect , 2010, Knowl. Based Syst..

[37]  Gangyao Kuang,et al.  Target Recognition via Information Aggregation Through Dempster–Shafer's Evidence Theory , 2015, IEEE Geoscience and Remote Sensing Letters.

[38]  Sanjay Chawla,et al.  On detection of emerging anomalous traffic patterns using GPS data , 2013, Data Knowl. Eng..

[39]  Catherine K. Murphy.  Combining belief functions when evidence conflicts , 2000, Decis. Support Syst..

[40]  Shaojie Qiao,et al.  An efficient outlying trajectories mining approach based on relative distance , 2012, Int. J. Geogr. Inf. Sci..

[41]  Qing Wu,et al.  A neuromorphic architecture for anomaly detection in autonomous large-area traffic monitoring , 2013, 2013 IEEE/ACM International Conference on Computer-Aided Design (ICCAD).

[42]  José A. Pino,et al.  Efficient Planning of Urban Public Transportation Networks , 2015, UCAmI.

[43]  Terje Andreas Mathisen,et al.  Generalized transport costs in intermodal freight transport , 2012 .

[44]  Glenn Shafer,et al.  A Mathematical Theory of Evidence , 2020, A Mathematical Theory of Evidence.

[45]  Lin Sun,et al.  iBOAT: Isolation-Based Online Anomalous Trajectory Detection , 2013, IEEE Transactions on Intelligent Transportation Systems.

[46]  Huisheng Zhang,et al.  An Information Fusion Model Based on Dempster–Shafer Evidence Theory for Equipment Diagnosis , 2018 .

[47]  Luci Pirmez,et al.  An enhanced bootstrap method to detect possible fraudulent behavior in testing facilities , 2017, Accreditation and Quality Assurance.