A confabulation model for abnormal vehicle events detection in wide-area traffic monitoring

The advanced sensing and imaging technologies of today's digital camera systems provide the capability of monitoring traffic flows in a very large area. In order to provide continuous monitoring and prompt anomaly detection, an abstract-level autonomous anomaly detection model is developed that is able to detect various categories of abnormal vehicle events with unsupervised learning. The method is based on the cogent confabulation model, which performs statistical inference functions in a neuromorphic formulation. The proposed approach covers the partitioning of a large region, training of the vehicle behavior knowledge base and the detection of anomalies according to the likelihood-ratio test. A software version of the system is implemented to verify the proposed model. The experimental results demonstrate the functionality of the detection model and compare the system performance under different configurations.

[1]  Hongjun Lu,et al.  Finding centric local outliers in categorical/numerical spaces , 2006, Knowledge and Information Systems.

[2]  VARUN CHANDOLA,et al.  Anomaly detection: A survey , 2009, CSUR.

[3]  Tieniu Tan,et al.  Similarity based vehicle trajectory clustering and anomaly detection , 2005, IEEE International Conference on Image Processing 2005.

[4]  Chao Li,et al.  Real-time Detection of Abnormal Vehicle Events with Multi-Feature over Highway Surveillance Video , 2008, 2008 11th International IEEE Conference on Intelligent Transportation Systems.

[5]  Qing Wu,et al.  A Parallel Neuromorphic Text Recognition System and Its Implementation on a Heterogeneous High-Performance Computing Cluster , 2013, IEEE Transactions on Computers.

[6]  Kishan G. Mehrotra,et al.  Rank-based outlier detection , 2013 .

[7]  Lionel Sacks,et al.  Active Platform Security through Intrusion Detection Using Naïve Bayesian Network for Anomaly Detection , 2002 .

[8]  Robert Hecht-Nielsen,et al.  MECHANISM OF THOUGHT , 1939, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[9]  Robert Hecht-Nielsen.  Confabulation theory - the mechanism of thought , 2007 .

[10]  Hongxing He,et al.  Outlier Detection Using Replicator Neural Networks , 2002, DaWaK.

[11]  B. M. Golam Kibria,et al.  Some Liu and ridge-type estimators and their properties under the ill-conditioned Gaussian linear regression model , 2012 .

[12]  Volker Roth,et al.  Outlier Detection with One-class Kernel Fisher Discriminants , 2004, NIPS.