SAR Image Change Detection Based on Iterative Label-Information Composite Kernel Supervised by Anisotropic Texture
- 3 February 2015
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 53 (7), 3960-3973
- https://doi.org/10.1109/tgrs.2015.2388495
Abstract
Kernel methods with specifically designed kernel function are suitable for dealing with practical nonlinear problems. However, kernel methods have found limited applications to synthetic aperture radar (SAR) image change detection in that their performances are affected by the inherent multiplicative speckle noise of SAR images. It is known that the spatial-contextual information is helpful in suppressing the degrading effects of the noise. Therefore, a label-information composite kernel (LIC kernel) constructed on the basis of the spatial-contextual information is proposed in this paper for SAR image change detection. A typical spatial information, the output-space label-neighborhood information that is extracted using all labels in the neighborhood of each pixel, may enhance noise immunity, but with inaccurate edge locations simultaneously. Consequently, the anisotropic Gaussian kernel model is utilized for analyzing anisotropic textures of the bitemporal images, and then, a comparison scheme acting on the input-space textures of the bi-temporal images is proposed to supervise the extraction of the output-space label-neighborhood information in the construction of the LIC kernel. The constructed LIC kernel is of good preservation of edge locations of changed areas as well as strong noise immunity. The LIC kernel is updated iteratively with the newest change map outputted from the support vector machine, until the change map converges. Experiments on real SAR images demonstrate the effectiveness of the LIC kernel method and illustrate that it has both strong noise immunity and good preservation of edge locations of changed areas for SAR image change detection.Keywords
Funding Information
- Natural Science Foundation of China (61272281, 61271297, 61301284)
- Specialized Research Fund for the Doctoral Program of Higher Education (20110203110001)
- National Ministries and Research Foundation (9140A07020913DZ01001)
This publication has 26 references indexed in Scilit:
- Semisupervised SAR Image Change Detection Using a Cluster-Neighborhood KernelIEEE Geoscience and Remote Sensing Letters, 2014
- Unsupervised Change Detection on SAR Images Using Triplet Markov Field ModelIEEE Geoscience and Remote Sensing Letters, 2012
- Wavelet Fusion on Ratio Images for Change Detection in SAR ImagesIEEE Geoscience and Remote Sensing Letters, 2012
- Multitemporal Image Change Detection Using Undecimated Discrete Wavelet Transform and Active ContoursIEEE Transactions on Geoscience and Remote Sensing, 2010
- Unsupervised Change Detection From Multichannel SAR Data by Markovian Data FusionIEEE Transactions on Geoscience and Remote Sensing, 2009
- Kernel-Based Framework for Multitemporal and Multisource Remote Sensing Data Classification and Change DetectionIEEE Transactions on Geoscience and Remote Sensing, 2008
- Change Detection in Multisensor SAR Images Using Bivariate Gamma DistributionsIEEE Transactions on Image Processing, 2008
- A detail-preserving scale-driven approach to change detection in multitemporal SAR imagesIEEE Transactions on Geoscience and Remote Sensing, 2005
- An unsupervised approach based on the generalized Gaussian model to automatic change detection in multitemporal SAR imagesIEEE Transactions on Geoscience and Remote Sensing, 2005
- An introduction to kernel-based learning algorithmsIEEE Transactions on Neural Networks, 2001