Convolutional neural network (CNN) has achieved promising results in image segmentation recently. However, for the segmentation of synthetic aperture radar (SAR) images with complicated scene, the single receptive field in CNN has a limited ability to effectively capture structural and regional information at the same time. In this paper, we propose a hierarchical fusion CNN (HIFCNN) model for SAR image segmentation. At each convolutional layer, HIFCNN sets several different-sized receptive fields, and thus extracts hierarchical features. Concretely, the larger-sized receptive field captures regional information and is robust against speckle, while the smaller one preserves the structural information well. Then, based on the Dempster-Shafer evidential theory, the proposed hierarchical network, HIFCNN, implements a decision-level fusion to integrate these hierarchical features. In this way, the structural and regional information can be accurately captured by different receptive fields, which is beneficial for edge location, structure preservation and region homogeneity in SAR image segmentation. The effectiveness of HIFCNN model is demonstrated by the application to the segmentation of the simulated images and real SAR images.

卷积神经网络（CNN）最近在图像分割方面取得了可喜的成果。但是，对于具有复杂场景的合成孔径雷达（SAR）图像的分割，CNN中的单个接收场具有有限的能力，无法同时有效捕获结构和区域信息。在本文中，我们提出了一种用于SAR图像分割的分层融合CNN（HIFCNN）模型。在每个卷积层，HIFCNN设置几个不同大小的接收场，从而提取层次特征。具体而言，较大的接收场可以捕获区域信息，并且对斑点具有鲁棒性，而较小的接收场则可以很好地保留结构信息。然后，基于Dempster-Shafer证据理论，提出了分层网络HIFCNN，实现决策级融合以集成这些分层功能。这样，可以通过不同的接收场准确地捕获结构和区域信息，这有利于SAR图像分割中的边缘定位，结构保持和区域均匀性。HIFCNN模型在模拟图像和真实SAR图像分割中的应用证明了其有效性。