Name
Title | ||
|---|---|---|
Impacts of Feature Normalization on Optical and SAR Data Fusion for Land Use/Land Cover Classification |
Abstract | ||
|---|---|---|
Land use/land cover (LULC) classification using optical and synthetic aperture radar (SAR) remote sensing images is becoming increasingly important to produce more accurate LULC products. As an important step, feature normalization techniques have been studied by the areas of pattern recognition. Nevertheless, because of the totally different imaging mechanisms of optical and SAR sensors, most of the existing normalization approaches are not suitable for optical and SAR data fusion. Moreover, whether normalization is a significant step remains unclear regarding optical and SAR fusion. Taking the Satellite Pour l'Observation de la Terre (SPOT-5) and the Advanced Land Observing Satellite (ALOS)/Phased Array type L-band SAR (PALSAR) (HH and HV polarizations) as the optical and SAR data, this letter aims to evaluate the impact of feature normalization. Experimental results indicated that feature normalization is not necessarily significant depending on fusion methods. For instance, distribution-dependent classifiers (e.g., a maximum likelihood classifier) are independent of feature normalization; thus, it has no impact on the results when using these classifiers. Moreover, advanced classifiers (e.g., a support vector machine) with built-in normalization are also not influenced by feature normalization. In contrast, a minimum distance classifier and an artificial neural network (ANN) depend on the input values of optical and SAR features and thus can be influenced by feature normalization. However, our experiments showed a fluctuation in classification accuracy using an ANN with normalized features. Therefore, more experiments are required to investigate the optimal normalization approaches for the optical and SAR images when using an ANN as the fusion method. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1109/LGRS.2014.2377722 | IEEE Geosci. Remote Sensing Lett. |
Keywords | Field | DocType |
synthetic aperture radar remote sensing images,terrain mapping,lulc products,synthetic aperture radar,phased array type l-band sar,land cover,pattern recognition,sar sensors,land use,optical and synthetic aperture radar (sar) data fusion,imaging mechanisms,sar data fusion,normalization,land use classification,polarimetric sar,optimal normalization approaches,land cover classification,remote sensing by radar,minimum distance classifier,feature normalization,feature extraction,image classification,support vector machine,geophysical image processing,optical sensors,advanced land observing satellite,ann,land use/land cover (lulc),artificial neural network,classification accuracy,optical data fusion,radar imaging,maximum likelihood classifier,feature normalization impact,neural nets,feature normalization techniques,sensor fusion,normalized features,distribution-dependent classifiers,remote sensing,adaptive optics,accuracy,optical imaging | Normalization (statistics),Synthetic aperture radar,Remote sensing,Artificial intelligence,Classifier (linguistics),Contextual image classification,Computer vision,Radar imaging,Pattern recognition,Support vector machine,Feature extraction,Sensor fusion,Mathematics | Journal |
Volume | Issue | ISSN |
12 | 5 | 1545-598X |
Citations | PageRank | References |
11 | 0.61 | 9 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hongsheng Zhang | 1 | 69 | 12.62 |
| Hui Lin | 2 | 459 | 64.06 |
| Yu Li | 3 | 18 | 3.88 |