《Table 9 Individual class accuracies by PA and UA for Stockholm data》

《Table 9 Individual class accuracies by PA and UA for Stockholm data》   提示:宽带有限、当前游客访问压缩模式
本系列图表出处文件名:随高清版一同展现
《D-SS Frame: deep spectral-spatial feature extraction and fusion for classification of panchromatic and multispectral images》


  1. 获取 高清版本忘记账户?点击这里登录
  1. 下载图表忘记账户?点击这里登录

The ground truth map of‘Washington DC’and‘Stockholm’data[14]were constructed.In each labeled scene,the black area represents the unlabeled area.Different values of the SSAE and SAE parameters were experimented,and Tables 3,4,5,6 list the classification accuracy of(SSAE+SVM)and(SAE+SVM)for MS and PAN images of Washington DC and Stockholm data respectively,versus the number of neurons in a hidden layer.