Anomaly Detection Using Convolutional Adversarial Autoencoder and One-class SVM for Landslide Area Detection from Synthetic Aperture Radar Images

Authors
Shingo Mabu1, *, Soichiro Hirata1, Takashi Kuremoto2
1Graduate School of Sciences and Technology for Innovation, Yamaguchi University, 2-16-1 Tokiwadai, Ube, Yamaguchi 755-8611, Japan
2Department of Information Technology and Media Design, Nippon Institute of Technology, 4-1 Gakuendai, Miyashiro-machi, Minamisaitama-gun, Saitama 345-8501, Japan
*Correponding author. Email: [email protected]
Corresponding Author
Shingo Mabu
Received 25 November 2020, Accepted 23 May 2021, Available Online 24 July 2021.
DOI
https://doi.org/10.2991/jrnal.k.210713.014
Keywords
Anomaly detection; adversarial autoencoder; one-class SVM; synthetic aperture radar
Abstract
An anomaly detection model using deep learning for detecting disaster-stricken (landslide) areas in synthetic aperture radar images is proposed. Since it is difficult to obtain a large number of training images, especially disaster area images, with annotations, we design an anomaly detection model that only uses normal area images for the training, where the proposed model combines a convolutional adversarial autoencoder, principal component analysis, and one-class support vector machine. In the experiments, the ability in detecting normal and abnormal areas is evaluated.
Copyright
© 2021 The Authors. Published by ALife Robotics Corp. Ltd
Open Access
This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)