Anomaly Detection in Traffic Trajectories Using a Combination of Fuzzy, Deep Convolutional and Autoencoder Networks

Document Type : Original Article

Authors

1 Azadi Campus, Yazd University, Yazd, Iran, Email:Banifakhr.

2 Department of Electrical Engineering, Yazd University, Yazd, Iran.

Abstract

Due to the increasing deployment of vehicles in human societies and the necessity for smart traffic control, anomaly detection is among the various tasks widely employed in traffic monitoring. As the issue of urban traffic and their relative smart monitoring systems have gained popularity among researchers in recent years, there exist several studies in this regard. In most of these studies, classification is performed based on the behavior of drivers, where a set of default trajectories are used in order to learn the system and classify the related data. However, two under-studied challenges are the lack of access to sufficient data to provide an efficient model, along with the lack of access to anomaly data that covers all possible abnormal trajectories. While the former challenge can be tackled through long-term data recording, the latter requires appropriate considerations. To this aim, we have utilized a combination of optimized convolutional neural network and fuzzy neural network classifiers, along with autoencoding neural networks. The final combination occurs at the decision level. First, the CNN-ANFIS classifier assigns the input trajectory to one of the predefined categories. Then, the trained autoencoder networks examine the result in order to find whether the trajectory is normal or abnormal. Obtaining 87.5% accuracy on QMUL and 99.5% on the T15 datasets confirms the superior performance of the proposed method.
 

Keywords

Main Subjects


  •  

    • Karimi Zandian, and M. R. Keyvanpour, “SSLBM: A New Fraud Detection Method Based on Semi-Supervised Learning,” Computer and Knowledge Engineering, vol. 2, no. 2, pp.10-18, 2020.
    • Ab azar, A. Shahmansoorian, M. Davoudi, “Uncertainty-aware Path Planning Using Reinforcement Learning and Deep Learning Methods,” Computer and Knowledge Engineering, 2020.
    • Kianian, S. Farzi, “Assessment of Customer Credit Risk using an Adaptive Neuro-Fuzzy System,” Computer and Knowledge Engineering, vol. 2, no. 2, pp.19-28, 2020.
    • Kelathodi Kumaran, D. Prosad Dogra, P. Pratim Roy, A. Mitra, “Video Trajectory Classification and Anomaly Detection Using Hybrid CNN-VAE,” arXiv preprint arXiv:1812.07203, 2018.
    • Mirjalili, A. Lewis, “The whale optimization algorithm. Advances in engineering software,” 95, pp.51-67, 2016.
    • Barucija, A. Mujcinovic, B. Muhovic, E. Zunic, D. Donko, “Data-driven approach for anomaly detection of real GPS trajectory data,” In2019 XXVII International Conference on Information, Communication and Automation Technologies (ICAT) IEEE, pp. 1-6, 2019.
    • Choong, L. Angeline, RK. Chin, KB. Yeo, KT. Teo. “Modeling of vehicle trajectory using K-means and fuzzy C-means clustering,” IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET) IEEE, pp. 1-6, 2018.
    • Li, T. Guo, R. Xia, W. Xie, “Road traffic anomaly detection based on fuzzy theory,”IEEE Access, vol. 6, pp.40281-8, 2018.
    • Kumar, V. Vaidehi, “A transfer learning framework for traffic video using neuro-fuzzy approach,” Sādhanā, vol. 42, no. 9, pp.1431-42, 2017.
    • Nawaratne, D. Alahakoon, D. De Silva, X. Yu, “Spatiotemporal anomaly detection using deep learning for real-time video surveillance,” IEEE Transactions on Industrial Informatics, vol. 16, no. 1, pp. 393-402, 2019.
    • Moallem, A. Pouyan, “Anomaly Detection using LSTM AutoEncoder,” Journal of Modeling in Engineering, vol. 17, no.56, pp. 191-211, 2019.
    • Aboah, “A vision-based system for traffic anomaly detection using deep learning and decision trees,” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pp. 4207-4212, 2021.
    • Zhang, Y. Zheng, Z. Zhao, Y. Liu, M. Blumenstein, and J. Li, “Deep learning detection of anomalous patterns from bus trajectories for traffic insight analysis,” Knowledge-Based Systems, 217, p.106833, 2021.
    • Rezaee, S.M. Rezakhani, M.R. Khosravi, and M.K. Moghimi, “A survey on deep learning-based real-time crowd anomaly detection for secure distributed video surveillance,” Personal and Ubiquitous Computing, pp.1-17, 2021.
    • G. Narasimhan, and S. Kamath, “Dynamic video anomaly detection and localization using sparse denoising autoencoders,” Multimedia Tools and Applications, vol.77, no.11 , pp.13173-13195, 2018.
    • Zhao, Z. Yi, S. Pan, Y. Zhao, Z. Zhao, F. Su, and B.Zhuang, “Unsupervised Traffic Anomaly Detection Using Trajectories,” In CVPR Workshops, pp. 133-140, 2019.
    • Ahmed, ML. Wong, AK. Nandi, “Intelligent condition monitoring method for bearing faults from highly compressed measurements using sparse over-complete features,” Mechanical Systems and Signal Processing, 99 pp,459-77, 2018.
    • S. Jang, “ANFIS: adaptive-network-based fuzzy inference system,” IEEE transactions on systems, man, and cybernetics, vol 23, no 3, pp.665-685, 1993.
    • Zenati, CS. Foo, B. Lecouat, G. Manek, VR. Chandrasekhar. “Efficient gan-based anomaly detection,” arXiv preprint arXiv:1802.06222, 2018.
    • C. Loy, T. Xiang, and S. Gong, “From local temporal correlation to global anomaly detection,” In ECCV, 2008.
    • Xu, Y. Zhou, W. Lin, and H. Zha, “Unsupervised trajectory clustering via adaptive multi-kernel-based shrinkage,” In ICCV, 2015.
    • Kingma, M. Welling, “Auto-encoding variational bayes,” arXiv preprint arXiv:1312.6114. 2013.
    • Averbuch-Elor, N. Bar, D. Cohen-Or, “Border-Peeling Clustering,” IEEE transactions on pattern analysis and machine intelligence. Vol 42,no 7, pp.1791-7, 2019.
    • Santhosh, DP. Dogra, PP. Roy, “Temporal unknown incremental clustering model for analysis of traffic surveillance videos,” IEEE Transactions on Intelligent Transportation Systems, vol 20, no 5, pp. 1762-73, 2018.