SAR Image Classification by Exploiting Adaptive Contextual Information and Composite Kernels
| Autor: | Dongdong Guan, Deliang Xiang, Xiaoan Tang, Ganggang Dong, Tao Tang, Gangyao Kuang |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Synthetic aperture radar
Pixel Contextual image classification Computer science business.industry Feature extraction ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 0211 other engineering and technologies Pattern recognition 02 engineering and technology Land cover Geotechnical Engineering and Engineering Geology Support vector machine Kernel (linear algebra) Speckle pattern Kernel (image processing) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence Electrical and Electronic Engineering Cluster analysis business Spatial analysis 021101 geological & geomatics engineering |
| Zdroj: | IEEE Geoscience and Remote Sensing Letters. 15:1035-1039 |
| ISSN: | 1558-0571 1545-598X |
| DOI: | 10.1109/lgrs.2018.2821711 |
| Popis: | For synthetic aperture radar (SAR) image land cover classification, traditional feature-based methods are not always effective because of the heavy multiplicative noise. To solve this problem, we herein propose a new classification method for SAR images considering adaptive spatial contextual information. In contrast to preceding studies, the spatial contextual information of the SAR images is exploited via composite kernels (CKs). Additionally, an image superpixel strategy is employed to design an adaptive neighborhood, which enables the extraction of more accurate spatial information than a fixed-size neighborhood. Specifically, a modified superpixel map is first generated to produce the neighborhood. With this neighborhood, a context kernel is then defined by means of the Gaussian radial basis function. The resulting context kernel is combined with the conventional feature kernel via the designed CKs scheme. The relative proportion of these two kernels is controlled by a weight parameter. The label of each pixel is predicted by feeding the final CKs into a support vector machine classifier. Experiments on two real SAR images demonstrate that the proposed method can greatly improve the classification performance, both visually and quantitatively, in comparison to other traditional feature-based methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|