摘要
图像语义分割作为一种像素级分类技术,已应用于合成孔径雷达(SAR)图像的解译领域中。U-Net是一种端到端的图像语义分割网络,具有典型的编码-解码结构。其中,编码部分主要由卷积层和池化层组成,可以有效提取图像中的目标特征,但难以获取目标的位置和方向等信息。胶囊网络是一种能够获取目标姿态(位置、大小、方向)等信息的神经网络,因此,提出了一种基于U-Net和胶囊网络的SAR图像语义分割方法。此外,考虑到SAR图像数据集较小的特点,将U-Net的编码部分设计成视觉几何组(VGG16)结构,将预训练的VGG16模型直接迁移至编码部分。为了验证本方法的有效性,在两个极化SAR图像数据集上开展了建筑物目标的分割实验。结果表明,相比U-Net,本方法的精确率、召回率、F1分数和交并比更高,且能减少网络模型的训练时间。
As a pixel-level classification technique,image semantic segmentation has been employed in the field of synthetic aperture radar(SAR)image interpretations.U-Net is an end-to-end image semantic segmentation network with a typical encoder-decoder architecture.Among them,the coding part mainly comprises a convolutional layer and a pooling layer,which can effectively extract the features of a target image;however,extracting information such as the target position and direction is difficult.Capsule network is a type of neural network that can obtain the target pose(position,size,and direction)and other information.Therefore,this study proposes an SAR image semantic segmentation method based on the U-Net and capsule network.Moreover,considering the small data set of SAR images,the U-Net encoder is designed to be identical to the visual geometry group(VGG16)to allow the trained VGG16 model to be directly transferred to the encoder.The effectiveness of the method is verified by conducting a segmentation experiment of building targets on two polarimetric SAR image data sets.Results show that the method can achieve improved precision,recall,F1-score,and intersection over union as well as reduce the training time of the network model when compared with the U-Net.
作者
敬绍迪
喻玲娟
胡跃虹
杨泽洲
卢忠亮
谢晓春
Jing Shaodi;Yu Lingjuan;Hu Yuehong;Yang Zezhou;Lu Zhongliang;Xie Xiaochun(School of Information Engineering,Jiangxi University of Science and Technology,Ganzhou,Jiangxi 341000,China;Guangzhou Wayful Technology Development Co.,Ltd.,Guangzhou,Guangdong 510200,China;School of Physics and Electronic Information,Gannan Normal University,Ganzhou,Jiangxi 341000,China)
出处
《激光与光电子学进展》
CSCD
北大核心
2021年第20期148-157,共10页
Laser & Optoelectronics Progress
基金
国家自然科学基金(61501210,61701203)
江西省教育厅科技项目(GJJ190459)。
关键词
图像处理
合成孔径雷达
图像语义分割
U-Net
胶囊网络
迁移学习
image processing
synthetic aperture radar
image semantic segmentation
U-Net
capsule network
transfer learning
