Research On Classification Methods Of Polarimetric SAR Image Based On Target Decomposition Theorem

Polarimetric Synthetic Aperture Radar (POLSAR) is a kind of SAR system which can acquire polarimetric scattering information of target at definite wavelength and visual angle. Because of comprehensive description for target, vast image resources obtained by polarimetric SAR have played an important role in many domains of SAR image interpretation. Especially, terrain classification with the help of polarimetric SAR image has been an important aspect of SAR application. Actually, perfect classification can't achieve by actual technique due to altitudinal complexity of target and multidimensional processing of polarimetric data. Thus, it is a hotspot subject on how to implement fast and exact classification of polarimetric SAR image.Polarimetric SAR image classification is pivotal in SAR image interpretation. According to current literature, the classification algorithm for polarimetric SAR image based on target decomposition theorems is the most practical and exact one with fast developing speed among all algorithms. Under this background of research, the basic theory on radar polarimetric is discussed at first in this paper. Then the characteristic of typical target decomposition algorithms is analyzed in detail. Finally, typical polarimetric SAR image classification based on target decomposition theorems are summarized, and a classification algorithm based on Freeman decomposition and scattering entropy is proposed. The major contents in this paper include:Firstly, as the theory foundation, several familiar formats of polarimetric SAR data and their physical meanings are introduced in detail as academic support for further research.Secondly, target decomposition theorem, the effective means for analysis of physical information in polarimetric SAR data, are expatiated in this paper. A useful conclusion that Cloude decomposition and Freeman decomposition are potential in improving the performance of classification is gained by experiments.Finally, three polarimetric SAR image classifications based on target decomposition theorems and their characteristic are presented, then an iterative classification of polarimetric SAR image based on Freeman decomposition and scattering entropy is proposed. The results of our experiment prove that this algorithm can advance the performance of classification.