From unsupervised to semi-supervised anomaly detection methods for HRRP targets

Responding to the challenge of detecting unusual radar targets in a well identified environment, innovative anomaly and novelty detection methods keep emerging in the literature. This work aims at presenting a benchmark gathering common and recently introduced unsupervised anomaly detection (AD) methods, the results being generated using high-resolution range profiles. A semi-supervised AD (SAD) is considered to demonstrate the added value of having a few labeled anomalies to improve performances. Experiments were conducted with and without pollution of the training set with anomalous samples in order to be as close as possible to real operational contexts. The common AD methods composing our baseline will be One-Class Support Vector Machines (OC-SVM), Isolation Forest (IF), Local Outlier Factor (LOF) and a Convolutional Autoencoder (CAE). The more innovative AD methods put forward by this work are Deep Support Vector Data Description (Deep SVDD) and Random Projection Depth (RPD), belonging respectively to deep and shallow AD. The semi-supervised adaptation of Deep SVDD constitutes our SAD method. HRRP data was generated by a coastal surveillance radar, our results thus suggest that AD can contribute to enhance maritime and coastal situation awareness.

[1]  Hans-Peter Kriegel,et al.  LOF: identifying density-based local outliers , 2000, SIGMOD '00.

[2]  Jesús Angulo,et al.  Random Projection Depth for Multivariate Mathematical Morphology , 2012, IEEE Journal of Selected Topics in Signal Processing.

[3]  Shuanghui Zhang,et al.  Radar HRRP Target Recognition Based on Stacked Autoencoder and Extreme Learning Machine , 2018, Sensors.

[4]  Hongwei Liu,et al.  Radar HRRP target recognition with deep networks , 2017, Pattern Recognit..

[5]  Zhi-Hua Zhou,et al.  Isolation Forest , 2008, 2008 Eighth IEEE International Conference on Data Mining.

[6]  Anoop Cherian,et al.  GODS: Generalized One-Class Discriminative Subspaces for Anomaly Detection , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[7]  Y. Zuo.  Projection-based depth functions and associated medians , 2003 .

[8]  Bernhard Schölkopf,et al.  Estimating the Support of a High-Dimensional Distribution , 2001, Neural Computation.

[9]  Takehisa Yairi,et al.  Anomaly Detection Using Autoencoders with Nonlinear Dimensionality Reduction , 2014, MLSDA'14.

[10]  Bin Xu,et al.  Convolutional neural networks for radar HRRP target recognition and rejection , 2019, EURASIP J. Adv. Signal Process..

[11]  Alexander Binder,et al.  Deep Semi-Supervised Anomaly Detection , 2019, ICLR.

[12]  Svetha Venkatesh,et al.  Memorizing Normality to Detect Anomaly: Memory-Augmented Deep Autoencoder for Unsupervised Anomaly Detection , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[13]  Thomas Brox,et al.  Anomaly Detection With Multiple-Hypotheses Predictions , 2018, ICML.

[14]  Chandan Srivastava,et al.  Support Vector Data Description , 2011 .

[15]  Simon Wagner,et al.  Target Detection using Autoencoders in a Radar Surveillance System , 2019, 2019 International Radar Conference (RADAR).

[16]  Bo Li,et al.  HRRP Clutter Rejection Via One-Class Classifier With Hausdorff Distance , 2020, IEEE Transactions on Aerospace and Electronic Systems.

[17]  Rikard Laxhammar,et al.  Anomaly detection for sea surveillance , 2008, 2008 11th International Conference on Information Fusion.

[18]  Alexander Binder,et al.  Deep One-Class Classification , 2018, ICML.