基于支持向量机预测偏振模式  

Prediction of polarization pattern by SVM

作　　者：汪方斌[1,2] 洪津[1] 孙晓兵[1] 王羿 胡亚东 

机构地区：[1]中国科学院安徽光学精密机械研究所光学遥感中心,安徽合肥230031 [2]安徽建筑大学机械与电气工程学院,安徽合肥230601

出　　处：《光学精密工程》2014年第11期2914-2922,共9页Optics and Precision Engineering

基　　金：国家自然科学基金资助项目(No.40971196)

摘　　要：基于多光谱多角度偏振辐射探测研究了大气偏振模式预测方法。首先,介绍了航空多角度偏振辐射计的探测原理与支持向量机回归算法;然后,从矢量传输模型出发,说明大气状况不变时,偏振模式主要取决于地表特征与观测几何,并介绍了观测几何与姿态之间的关系以及地表特征的表达形式;最后,在考虑平台姿态与地表特征的情况下,利用支持向量机回归算法预测了航空多角度偏振辐射计的探测偏振度,并对预测与实际试验探测的偏振度进行了比较。结果显示:偏振度预测误差小于1%,影响模型精度的主要因素不是姿态变化本身,而是姿态改变造成的观测地表特性变化。On the basis of multi-spectral multi-angular radiative polarization measurements,a prediction method for atmospheric polarization patterns is investigated.Firstly,the principle of an Aviation Multi-angle Polarimetric Radiometer （AMPR） and the regression algorithm of a Support Vector Machine （SVM） are introduced.Then,according to Vector Radiative Transfer Equation （VRTE）,it points out that the atmospheric polarization pattern is primarily dependent on view geometry and surface features when atmosphere condition is invariant.Meanwhile,it intro duces the relationship between view geometry and platform attitude and the expressing form of surface features.Finally,how to use the regression algorithm of SVM to predict the detected polarization degree of the APMR and to validate the application process is introduced in the consideration of the surface features and platform attitudes.Furthermore,the predicted degrees of polarization is also compared to that of real measurements.The results indicate that the error of polarization degree predicted is less than 1％.It concludes that the serious factor to affect the model accuracy is not the change of attitude but the variation of underlying surface property caused by the changed attitudes.

关 键 词：大气遥感 大气偏振模式 预测 支持向量机 航空多角度偏振辐射计 

分 类 号：P407[天文地球—大气科学及气象学]