结合上下文编码与特征融合的SAR图像分割  

The integrated contextual encoding and feature fusion SAR images segmentation method

作　　者：范艺华 董张玉[1,2,3] 杨学志 Fan Yihua;Dong Zhangyu;Yang Xuezhi(Cllge of Computer and Information,Hefi University of Technology,Hefei 230031,China;Anhui Prouince Key Laboratory of Industry Safety and Emergency Technology,Hefei 230031,China;Anhui Province Laboratory of Intlligent Interconnection System,Hefei230031,China;College of Sofuware,Hefei University of Technology,Hefei230031,China)

机构地区：[1]合肥工业大学计算机与信息学院,合肥230031 [2]工业安全与应急技术安徽省重点实验室,合肥230031 [3]智能互联系统安徽省实验室,合肥230031 [4]合肥工业大学软件学院,合肥230031

出　　处：《中国图象图形学报》2022年第8期2527-2536,共10页Journal of Image and Graphics

基　　金：安徽省重点研发计划资助(202004a07020030)。

摘　　要：目的 图像分割的中心任务是寻找更强大的特征表示,而合成孔径雷达(synthetic aperture radar, SAR)图像中斑点噪声阻碍特征提取。为加强对SAR图像特征的提取以及对特征充分利用,提出一种改进的全卷积分割网络。方法 该网络遵循编码器—解码器结构,主要包括上下文编码模块和特征融合模块两部分。上下文编码模块(contextual encoder module, CEM)通过捕获局部上下文和通道上下文信息增强对图像的特征提取;特征融合模块(feature fusion module, FFM)提取高层特征中的全局上下文信息,将其嵌入低层特征,然后将增强的低层特征并入解码网络,提升特征图分辨率恢复的准确性。结果 在两幅真实SAR图像上,采用5种基于全卷积神经网络的分割算法作为对比,并对CEM与CEM-FFM分别进行实验。结果显示,该网络分割结果的总体精度(overall accuracy, OA)、平均精度(average accuracy, AA)与Kappa系数比5种先进算法均有显著提升。其中,网络在OA上表现最好,CEM在两幅SAR图像上OA分别为91.082%和90.903%,较对比算法中性能最优者分别提高了0.948%和0.941%,证实了CEM的有效性。而CEM-FFM在CEM基础上又将结果分别提高了2.149%和2.390%,验证了FFM的有效性。结论 本文提出的分割网络较其他方法对图像具有更强大的特征提取能力,且能更好地将低层特征中的空间信息与高层特征中的语义信息融合为一体,使得网络对特征的表征能力更强、图像分割结果更准确。Objective Pixel-wise segmentation for synthetic aperture radar(SAR) images has been challenging due to the constraints of labeled SAR data, as well as the coherent speckle contextual information. Current semantic segmentation is challenged like existing algorithms as mentioned below: First, the ability to capture contextual information is insufficient. Some algorithms ignore contextual information or just focus on local spatial contextual information derived of a few pixels, and lack global spatial contextual information. Second, in order to improve the network performance, researchers are committed to developing the spatial dimension and ignoring the relationship between channels. Third, a neural network based high-level features extracted from the late layers are rich in semantic information and have blurred spatial details. A network based low-level features extraction contains more noise pixel-level information from the early layers. They are isolated from each other, so it is difficult to make full use of them. The most common ways are not efficient based on concatenate them or per-pixel addition. Method To solve these problems, a segmentation algorithm is proposed based on fully convolutional neural network(CNN). The whole network is based on the structure of encoder-decoder network. Our research facilitates a contextual encoding module and a feature fusion module for feature extraction and feature fusion. The different rates and channel attention mechanism based contextual encoding module consists of a residual connection, a standard convolution, two dilated convolutions. Among them, the residual connection is designed to neglect network degradation issues. Standard convolution is obtained by local features with 3 × 3 convolution kernel. After convolution, batch normalization and nonlinear activation function ReLU are connected to resist over-fitting. Dilated convolutions with 2 × 2 and 3 × 3 dilated rates extend the perception field and capture multi-scale features and local contextual features further

关 键 词：图像分割 全卷积神经网络(FCN) 特征融合 上下文信息 合成孔径雷达(SAR) 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]