Learning Change from Synthetic Aperture Radar Images: Performance Evaluation of a Support Vector Machine to Detect Earthquake and Tsunami-Induced Changes

For the problem of reliable decision in synthetic aperture radar (SAR) target recognition, a method based on updated classifiers is proposed. The convolutional neural network (CNN) and support vector machine (SVM) are used as basic classifiers to classify samples with unknown target labels. The two decisions are fused and the reliability of the fused decision is evaluated. The classified test samples with high reliabilities are added to the original training samples to update the classifiers. The updated classifiers have stronger classification abilities and the fused result of the two classifiers can obtain a more reliable decision. The proposed method is tested and verified based on the moving and stationary target acquisition and recognition (MSTAR) dataset. The experimental results verify the effectiveness and robustness of the proposed method.

Download Full-text

Support vector machine classification of woody patches in New Zealand from synthetic aperture radar and optical data, with LiDAR training

Journal of Applied Remote Sensing ◽

10.1117/1.jrs.9.095984 ◽

2015 ◽

Vol 9 (1) ◽

pp. 095984 ◽

Cited By ~ 5

Author(s):

Markus U. Müller ◽

James D. Shepherd ◽

John R. Dymond

Keyword(s):

Support Vector Machine ◽

New Zealand ◽

Synthetic Aperture Radar ◽

Synthetic Aperture ◽

Optical Data ◽

Support Vector ◽

Support Vector Machine Classification ◽

Aperture Radar

Download Full-text

Mining Subsidence Prediction by Combining Support Vector Machine Regression and Interferometric Synthetic Aperture Radar Data

ISPRS International Journal of Geo-Information ◽

10.3390/ijgi9060390 ◽

2020 ◽

Vol 9 (6) ◽

pp. 390

Author(s):

Lichun Sui ◽

Fei Ma ◽

Nan Chen

Keyword(s):

Support Vector Machine ◽

Synthetic Aperture Radar ◽

Loess Plateau ◽

Mining Subsidence ◽

Shaanxi Province ◽

Synthetic Aperture ◽

Support Vector ◽

Interferometric Synthetic Aperture Radar ◽

The Loess Plateau ◽

Aperture Radar

Mining subsidence is time-dependent and highly nonlinear, especially in the Loess Plateau region in Northwestern China. As a consequence, and mainly in building agglomerations, the structures can be damaged severely during or after underground extraction, with risks to human life. In this paper, we propose an approach based on a combination of a differential interferometric synthetic aperture radar (DInSAR) technique and a support vector machine (SVM) regression algorithm optimized by grid search (GS-SVR) to predict mining subsidence in a timely and cost-efficient manner. We consider five Advanced Land Observing Satellite (ALOS)/Phased Array type L-band Synthetic Aperture Radar (PALSAR) images encompassing the Dafosi coal mine area in Binxian and Changwu counties, Shaanxi Province. The results show that the subsidence predicted by the proposed InSAR and GS-SVR approach is consistent with the Global Positioning System (GPS) measurements. The maximum absolute errors are less than 3.1 cm and the maximum relative errors are less than 14%. The proposed approach combining DInSAR with GS-SVR technology can predict mining subsidence on the Loess Plateau of China with a high level of accuracy. This research may also help to provide disaster warnings.

Download Full-text

Stripe detection and recognition of oceanic internal waves from synthetic aperture radar based on support vector machine and feature fusion

International Journal of Remote Sensing ◽

10.1080/01431161.2021.1943040 ◽

2021 ◽

Vol 42 (17) ◽

pp. 6710-6728

Author(s):

Ying-gang Zheng ◽

Hong-sheng Zhang ◽

You-Qiang Wang

Keyword(s):

Support Vector Machine ◽

Synthetic Aperture Radar ◽

Internal Waves ◽

Feature Fusion ◽

Synthetic Aperture ◽

Support Vector ◽

Detection And Recognition ◽

Aperture Radar

Download Full-text

Building Damage Assessment in the 2015 Gorkha, Nepal, Earthquake Using Only Post-Event Dual Polarization Synthetic Aperture Radar Imagery

Earthquake Spectra ◽

10.1193/121516eqs232m ◽

2017 ◽

Vol 33 (1_suppl) ◽

pp. 185-195 ◽

Cited By ~ 11

Author(s):

Yanbing Bai ◽

Bruno Adriano ◽

Erick Mas ◽

Shunichi Koshimura

Keyword(s):

Feature Selection ◽

Synthetic Aperture Radar ◽

Urban Areas ◽

Damage Assessment ◽

Texture Features ◽

Synthetic Aperture ◽

Support Vector ◽

Radar Images ◽

Nepal Earthquake ◽

Aperture Radar

This paper takes the 2015 Nepal earthquake as a case study to explore the use of post-event dual polarimetric synthetic aperture radar images for earthquake damage assessment. The radar scattering characteristics of damaged and undamaged urban areas were compared by using polarimetric features derived from PALSAR-2 and Sentinel-1 images, and the results showed that distinguishing between damaged and undamaged urban areas with a single polarimetric feature is challenging. A split-based image analysis, feature selection, and supervised classification were employed on a PALSAR-2 image. The texture features derived from the intensity of cross-polarization show higher correlations with the damage class. Additionally, feature selection revealed a positive influence on the overall performance. Employing 70% of the data for training and 30% data for testing, the support vector machine classifier achieved an accuracy of 80.5% compared with the reference data generated from the damage map that was provided by the United Nations Operational Satellite Applications Programme.

Download Full-text