顾及地形辐射校正的极化SAR图像分类应用

针对极化SAR(Polarimetric SAR,PolSAR)影像在复杂地形区域中存在严重的地形效应问题,该文将极化方位角(Polarisation Orientation Angle,POA)、有效散射面积(Effective Scattering Area,ESA)及角度效应(Angular Variation Effect,AVE)校正方法应用到PolSAR影像的分类中,并针对AVE校正提出一种n值确定方法。首先,对预处理后的SAR数据进行POA校正,对校正结果进行地理编码;其次,进行基于投影角的ESA校正;然后,基于训练样本确定AVE校正中的n值,进而实现AVE校正;最后,利用GF-3 PolSAR影像进行基于复Wishart分类器的分类实验。研究结果表明,POA校正前后变化不明显;ESA校正可实现约3 dB的校正效果,总体分类精度提升约9.42%;此外,选用受地形影响最大的林地n值进行AVE校正得到的结果最好,总体分类精度较ESA阶段而言提升约8.2%。

In order to solve the problem of serious terrain effect in the classification of land cover types in complex terrain areas of polarimetric SAR(PolSAR)images,this paper analyzes the Polarisation Orientation Angle(POA),Effective Scattering Area(ESA)and Angular Variation Effect(AVE)correction and other terrain radiation correction methods are applied to the classification of PolSAR images,and an n-value determination method is proposed for AVE correction to improve the classification accuracy.Firstly,the preprocessed SAR data undergoes polarization orientation angle(POA)correction,followed by the geographical encoding of the corrected results.Secondly,a projection angle-based effective scattering area(ESA)correction is applied to account for terrain effects.Subsequently,the"n"value crucial for angular variation effect(AVE)correction is determined through analysis of training samples,enabling the subsequent implementation of AVE correction.Finally,classification experiments are conducted on PolSAR imagery using a complex Wishart classifier to validate the proposed approach.The results show that the change before and after POA correction are not obvious.ESA correction can achieve the correction effect of about 3 dB,resulting in an overall classification accuracy improvement of about 9.42%.In addition,the AVE correction results were best obtained by selecting the n-value of the forest land most affected by topography,and an increase of about 8.2%in the ESA stage of the overall classification accuracy.