期刊
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
卷 12, 期 11, 页码 4517-4529出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSTARS.2019.2953128
关键词
Feature extraction; Synthetic aperture radar; Radar polarimetry; Speckle; Training; Deep learning; Reliability; Change detection; deep cascade network (DCNet); deep learning; residual learning; synthetic aperture radar (SAR)
类别
资金
- National Key R&D Program of China [2018AAA0100602]
- National Natural Science Foundation of China [41606198, 41576011]
- Key R&D Program of Shandong Province [2019GHY11204]
Deep learning methods have recently demonstrated their significant capability for synthetic aperture radar (SAR) image change detection. However, with the increase of network depth, convolutional neural networks often encounter some negative effects, such as overfitting and exploding gradients. In addition, the existing deep networks employed in SAR change detection tend to produce a lot of redundant features that affect the performance of the network. To solve the aforementioned problems, this article proposed a deep cascade network (DCNet) for SAR image change detection. On the one hand, a very DCNet is established to exploit discriminative features, and residual learning is introduced to solve the exploding gradients problem. In addition, a fusion mechanism is employed to combine the outputs of different hierarchical layers to further alleviate the exploding gradient problem. Moreover, a simple yet effective channel weighting-based module is designed for SAR change detection. Average pooling and max pooling are used to aggregate channel-wise information. Meaningful channel-wise features are emphasized and unnecessary ones are suppressed. Therefore, the similarity in feature maps can be reduced, and then, the classification performance of the DCNet is improved. Experimental results on four real SAR datasets demonstrated that the proposed DCNet can obtain better change detection performance than several competitive methods. Our codes are available at https://github.com/summitgao/SAR_CD_DCNet.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据