Improvement of classification accuracy integrating C- and X-band synthetic aperture radar data

Remote sensing for the monitoring of agricultural crops has been widely used in the past. Synthetic aperture radar (SAR) system, for its characteristics of all-weather, all-day image obtain capacity, is an attractive source of information for agriculture crop classification applications, particularly in regions where cloud cover is a problem. The accuracy with which crops can be classified is dependent on a range of sensor properties, including the SAR operating configuration. This paper focuses on the effect of integrating C- and X-band SAR data on the improvement of classification accuracy. The study was carried out on Yucheng Ecological Experimental Station (China). Radarsat-2 and TerraSAR-X data were acquired, and during the satellite overpass, the ground investigation was implemented. Support vector machine classifier was used to classify the image based on the backscattering coefficients and texture features. The classification was conducted separately on Radarsat-2, TerraSAR-X and the integrating of the two. The performance of single band SAR was not acceptly good, but the integrating of the two had a great increase on classification accuracy (more than 10%). With different frequency we would get more information about the earth surface. Integrating of multiband of SAR data was a dependable way to improve classification accuracy.