Target Classification of Synthetic Aperture Radar Image Based on Neural Network Ensemble
As we know,the target classification of synthetic aperture radar image is often affected by its azimuths.On the other hand,because of the uncertainty of target class,tank or truck for example,it” s hard to evaluate the azimuth.So in this paper,neural network ensemble will be applied to solve this problem.Feature vectors of target images are extracted with principal component analysis in wavelet domain.Several neural networks are trained to tell the classification of the target image,each for the eigenspace of a given azimuth set.During the recognition period,their results are combined by another neural network to do the final decision.The novel method can effectively improve the classification accuracy by eliminating the disturbance of azimuth information.It also shows a new way to solve such problems.
neural network synthetic aperture radar image ensemble learning
Qian Bo
Nanjing Research Institute of Electronic Technology, Nanjing, 210013, China
国内会议
深圳
英文
60-65
2009-11-01（万方平台首次上网日期，不代表论文的发表时间）