Anomaly Monitoring Framework in Lane Detection With a Generative Adversarial Network

The safety of an automated vehicle requires accurate information of surrounding conditions, because a false sensor output can lead to a fatal accident during driving. Thus, monitoring of abnormalities in every sensor is important for robust perception of the environment. Since it is difficult to obtain anomalous data, it is hard to develop a robust detection algorithm using only a relatively small number of anomalies. In this paper, we propose a data augmentation method for oversampling minority anomalies in lane detection. Using a generative adversarial network that makes the generator learn to estimate the distribution of anomalous data, it generates synthesized minority anomalies. The generated anomalies are used to train an anomaly detection network while minimizing latency for use in real situations. During training, the generated anomalies, with various mixed quality, are sampled differently according to their quality. This helps the detection network to be optimized with better quality data. Experimental result shows that when using the proposed anomaly detection framework for monitoring lane abnormality, it improves the performance by 12% when compared to the vanilla recurrent neural network.

[1]  Anup K. Ghosh,et al.  Detecting anomalous and unknown intrusions against programs , 1998, Proceedings 14th Annual Computer Security Applications Conference (Cat. No.98EX217).

[2]  Dinesh Babu Jayagopi,et al.  A robust lane detection and departure warning system , 2015, 2015 IEEE Intelligent Vehicles Symposium (IV).

[3]  Georg Langs,et al.  Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery , 2017, IPMI.

[4]  Angelos Amditis,et al.  A Situation-Adaptive Lane-Keeping Support System: Overview of the SAFELANE Approach , 2010, IEEE Transactions on Intelligent Transportation Systems.

[5]  Takashi Fuse,et al.  Statistical Anomaly Detection in Human Dynamics Monitoring Using a Hierarchical Dirichlet Process Hidden Markov Model , 2017, IEEE Transactions on Intelligent Transportation Systems.

[6]  Kunsoo Huh,et al.  Road Surface Classification Using a Deep Ensemble Network with Sensor Feature Selection , 2018, Sensors.

[7]  Cheng Zhang,et al.  Native API based Windows anomaly intrusion detection method using SVM , 2006, IEEE International Conference on Sensor Networks, Ubiquitous, and Trustworthy Computing (SUTC'06).

[8]  Yasser Yasami,et al.  A novel unsupervised classification approach for network anomaly detection by k-Means clustering and ID3 decision tree learning methods , 2010, The Journal of Supercomputing.

[9]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[10]  David M. W. Powers,et al.  Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation , 2011, ArXiv.

[11]  Jürgen Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[12]  Jianxin Wu,et al.  Minimal gated unit for recurrent neural networks , 2016, International Journal of Automation and Computing.

[13]  Nicu Sebe,et al.  Abnormal event detection in videos using generative adversarial nets , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[14]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[15]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[16]  Yukihiro Tadokoro,et al.  Structured Denoising Autoencoder for Fault Detection and Analysis , 2014, ACML.

[17]  Francesco Borrelli,et al.  Kinematic and dynamic vehicle models for autonomous driving control design , 2015, 2015 IEEE Intelligent Vehicles Symposium (IV).

[18]  Jonathon Shlens,et al.  Conditional Image Synthesis with Auxiliary Classifier GANs , 2016, ICML.

[19]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[20]  Salvatore J. Stolfo,et al.  One Class Support Vector Machines for Detecting Anomalous Windows Registry Accesses , 2003 .

[21]  Tom Schaul,et al.  Prioritized Experience Replay , 2015, ICLR.

[22]  Dong Wang,et al.  Anomaly Detection in Traffic Scenes via Spatial-Aware Motion Reconstruction , 2017, IEEE Transactions on Intelligent Transportation Systems.

[23]  Luke S. Zettlemoyer,et al.  Deep Contextualized Word Representations , 2018, NAACL.

[24]  Yunyi Yan,et al.  Robust feature learning by improved auto-encoder from non-Gaussian noised images , 2015, 2015 IEEE International Conference on Imaging Systems and Techniques (IST).

[25]  Nanning Zheng,et al.  Efficient Lane Boundary Detection with Spatial-Temporal Knowledge Filtering , 2016, Sensors.

[26]  Anthony Widjaja,et al.  Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond , 2003, IEEE Transactions on Neural Networks.

[27]  Naim Dahnoun,et al.  Multiple Lane Detection Algorithm Based on Novel Dense Vanishing Point Estimation , 2017, IEEE Transactions on Intelligent Transportation Systems.

[28]  Shaomin Mu,et al.  Sequence-similarity kernels for SVMs to detect anomalies in system calls , 2007, Neurocomputing.

[29]  Pierre Baldi,et al.  Autoencoders, Unsupervised Learning, and Deep Architectures , 2011, ICML Unsupervised and Transfer Learning.

[30]  Alberto Del Bimbo,et al.  Context-Aware Trajectory Prediction , 2017, 2018 24th International Conference on Pattern Recognition (ICPR).

[31]  Simone Calderara,et al.  Latent Space Autoregression for Novelty Detection , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[32]  Mohan M. Trivedi,et al.  Convolutional Social Pooling for Vehicle Trajectory Prediction , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[33]  Nicola Conci,et al.  Gaussian mixtures for anomaly detection in crowded scenes , 2013, Electronic Imaging.

[34]  Charles X. Ling,et al.  Data Mining for Direct Marketing: Problems and Solutions , 1998, KDD.

[35]  Charu C. Aggarwal,et al.  Outlier Detection for Temporal Data: A Survey , 2014, IEEE Transactions on Knowledge and Data Engineering.

[36]  D. Endler,et al.  Intrusion detection. Applying machine learning to Solaris audit data , 1998, Proceedings 14th Annual Computer Security Applications Conference (Cat. No.98EX217).

[37]  Zhaohui Wu,et al.  Robust feature learning by stacked autoencoder with maximum correntropy criterion , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[38]  Michael Schatz,et al.  Learning Program Behavior Profiles for Intrusion Detection , 1999, Workshop on Intrusion Detection and Network Monitoring.

[39]  Vir V. Phoha,et al.  K-Means+ID3: A Novel Method for Supervised Anomaly Detection by Cascading K-Means Clustering and ID3 Decision Tree Learning Methods , 2007, IEEE Transactions on Knowledge and Data Engineering.

[40]  Raymond Y. K. Lau,et al.  Least Squares Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[41]  Long Chen,et al.  Robust Lane Detection From Continuous Driving Scenes Using Deep Neural Networks , 2019, IEEE Transactions on Vehicular Technology.

[42]  David M. Bevly,et al.  A Low-Cost Solution for an Integrated Multisensor Lane Departure Warning System , 2009, IEEE Transactions on Intelligent Transportation Systems.

[43]  Luc Van Gool,et al.  Towards End-to-End Lane Detection: an Instance Segmentation Approach , 2018, 2018 IEEE Intelligent Vehicles Symposium (IV).

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

[45]  Seetha Hari,et al.  Learning From Imbalanced Data , 2019, Advances in Computer and Electrical Engineering.

[46]  Chanho Lee,et al.  Robust Lane Detection and Tracking for Real-Time Applications , 2018, IEEE Transactions on Intelligent Transportation Systems.

[47]  Kunsoo Huh,et al.  Estimating the Maximum Road Friction Coefficient with Uncertainty Using Deep Learning , 2018, 2018 21st International Conference on Intelligent Transportation Systems (ITSC).

[48]  Malik Yousef,et al.  One-Class SVMs for Document Classification , 2002, J. Mach. Learn. Res..

[49]  Roy E. Welsch,et al.  Anomaly detection via a Gaussian Mixture Model for flight operation and safety monitoring , 2016 .

[50]  Heng Tao Shen,et al.  Principal Component Analysis , 2009, Encyclopedia of Biometrics.

[51]  Amutha Prabakar Muniyandi,et al.  Network Anomaly Detection by Cascading K-Means Clustering and C4.5 Decision Tree algorithm , 2012 .

[52]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[53]  Jakub W. Pachocki,et al.  Learning dexterous in-hand manipulation , 2018, Int. J. Robotics Res..

[54]  Riccardo Marino,et al.  Nested PID steering control for lane keeping in autonomous vehicles , 2011 .

[55]  Raghavendra Chalapathy University of Sydney,et al.  Deep Learning for Anomaly Detection: A Survey , 2019, ArXiv.

[56]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[57]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[58]  Charles Elkan,et al.  Expectation Maximization Algorithm , 2010, Encyclopedia of Machine Learning.

[59]  Zhen Wang,et al.  On the Effectiveness of Least Squares Generative Adversarial Networks , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[60]  Léon Bottou,et al.  Wasserstein GAN , 2017, ArXiv.

[61]  Maria Riveiro,et al.  Anomaly Detection for Road Traffic: A Visual Analytics Framework , 2017, IEEE Transactions on Intelligent Transportation Systems.

[62]  Vasant Honavar,et al.  Learning Classifiers for Misuse Detection Using a Bag of System Calls Representation , 2005, ISI.

[63]  M. Elif Karsligil,et al.  Vision based lane keeping assistance control triggered by a driver inattention monitor , 2010, 2010 IEEE International Conference on Systems, Man and Cybernetics.

[64]  Anup K. Ghosh,et al.  A Study in Using Neural Networks for Anomaly and Misuse Detection , 1999, USENIX Security Symposium.

[65]  Andrew L. Maas.  Rectifier Nonlinearities Improve Neural Network Acoustic Models , 2013 .

[66]  Shenghua Gao,et al.  Encoding Crowd Interaction with Deep Neural Network for Pedestrian Trajectory Prediction , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[67]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.