Semantic Segmentation in Remote Sensing through A Heavy Feature Reuse Based Network

作     者：Eric Rene Narciso Molina 

作者单位：上海交通大学 

学位级别：硕士

导师姓名：Zenghui Zhang

授予年度：2019年

学科分类：0810[工学-信息与通信工程] 12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 08[工学] 081104[工学-模式识别与智能系统] 0835[工学-软件工程] 081002[工学-信号与信息处理] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

摘      要：Semantic segmentation is the task of clustering pixels into an ob-ject *** the field of remote sensing semantic segmentation has wide applications ranging from scene cover classification to change detection for scene *** the success of deep learning algorithms for classification tasks,there has been much work to apply convolutional neu-ral networks in remote sensing with much ***,feature ex-traction of high resolution remote sensing imagery poses a challenge when applying such *** particular,there is a need to extract high level features while maintaining an objects resolution in the networks feature *** masters thesis proposes an efficient deep fully convolution architecture that obtains high level features without loss of spatial resolu-tion by replacing the standard convolutional layers in U-Net with dense residual *** stacking identity blocks,we allow the input to flow through the network at every proceeding *** network is termed DRU-Net,and is shown to outperform standard *** further add to this by using a pyramid pooling layer as a global context prior before the decoding layers of our *** additional step further improves this *** then perform several analysis of different data set,and show an application of fully convolutional networks in the context of radar images.