改进空洞卷积的极化合成孔径雷达数据分类方法

doi:10.13474/j.cnki.11-2246.2026.0512

摘要/Abstract

摘要： [目的]针对传统极化合成孔径雷达图像解译方法难以通过有局限性物理模型识别出准确地物的问题,本文提出了一种基于金字塔空洞空间池化卷积的改进模块。[方法]改进后的模块由4个并行的分支组成,4个分支通过不同的卷积方式进行数据处理,在保证模型性能的前提下减少一定的计算参数,改进后的4个分支能够有效地提取多尺度特征,并通过卷积块注意力模块完成对关键信息的学习能力。[结果]试验结果表明,改进方法在水体分类中的平均行正确率为91.2%,优于对比网络;在植被分类中也表现出色,平均行正确率达到82%。[结论]这表明通过增加网络的深度,能够提高深度学习模型对复杂数据的学习能力。

关键词: 极化合成孔径雷达, 语义分割, 卷积神经网络, 金字塔空洞空间池化卷积, 卷积块注意力模块

Abstract: [Purposes] Aiming at the problem that traditional polarization synthetic aperture radar image interpretation methods are difficult to accurately identify ground objects through limited physical models,this paper proposes an improved module based on atrous spatial pyramid pooling convolution.[Methods] The improved module consists of four parallel branches.These four branches process data through different convolution methods,reducing certain computational parameters while ensuring model performance.The improved four branches can effectively extract multi-scale features and complete the learning ability of key information through the convolutional block attention module.[Findings] The experimental results show that the average row accuracy rate of the improved method in water body classification is 91.2%,which is superior to the comparison network.It also performed well in vegetation classification,with an average row accuracy rate of 82%.[Conclusions] This indicates that by increasing the depth of the network,the learning ability of deep learning models for complex data can be enhanced.

Key words: PolSAR, semantic segmentation, convolutional neural networks, atrous spatial pyramid pooling convolution, convolutional block attention module

中图分类号:

张继超, 高子善, 张兵. 改进空洞卷积的极化合成孔径雷达数据分类方法[J]. 测绘通报, 2026, 0(5): 64-71.

ZHANG Jichao, GAO Zishan, ZHANG Bing. An improved atrous convolution method for polarimetric synthetic aperture radar data classification[J]. Bulletin of Surveying and Mapping, 2026, 0(5): 64-71.

参考文献

[1] 郎丰铠,何苏颖,邱奥深,等.高砾石地表全极化SAR土壤水分反演方法[J].测绘学报,2024,53(11):2189-2200.
[2] 范亚雄,赵磊,陈尔学,等.高分航空多波段极化SAR寒温带针叶林蓄积量估测能力评价[J].遥感学报,2024,28(10):2525-2539.
[3] 邹小洲,戴可人,梁茹冰,等.基于SAR影像的城市建筑变化监测极化香农熵提取方法[J].地质灾害与环境保护,2026,37(1):104-112.
[4] 缪恒,王晓青,丁玲,等.基于全极化Radarsat-2影像的建筑物震害评估[J].中国地震,2022,38(2):338-347.
[5] 汪洋,鲁加国,张芬.Cameron分解法在极化SAR图像分析中的应用[J].合肥工业大学学报(自然科学版),2006,29(9):1177-1180.
[6] 常玲.基于贝叶斯分类的极化SAR图像机场跑道检测[D].天津:中国民航大学,2016.
[7] 张姝茵,侯彪,焦李成,等.基于稀疏自编码器和边缘保持的Wishart马尔科夫随机场的极化SAR图像分类[J].红外与毫米波学报,2018,37(2):177-183.
[8] 闫秋双,范陈清,赵欣彤,等.基于双极化SAR数据的西北太平洋台风海域风场智能反演[J].清华大学学报(自然科学版),2025,65(6):1090-1101.
[9] 段素素,依力亚斯江·努尔麦麦提,郭莉丹,等.基于全极化微波遥感的干旱区典型绿洲盐渍化信息提取[J].湖北农业科学,2018,57(2):110-114.
[10] HUYNEN J R.Phenomenological theory of radar targets[M]//Electromagnetic Scattering.Amsterdam:Elsevier,1978:653-712.
[11] 赵力文,周晓光,蒋咏梅,等.一种基于Freeman分解与散射熵的极化SAR图像迭代分类方法[J].电子与信息学报,2008,30(11):2698-2701.
[12] CORTES C,VAPNIK V.Support-vector networks[J].Machine Learning,1995,20(3):273-297.
[13] FUKUDA S,KATAGIRI R,HIROSAWA H.Unsupervised approach for polarimetric SAR image classification using support vector machines[C]//Proceedings of 2005 IEEE International Geoscience and Remote Sensing Symposium.Toronto:IEEE,2005:2599-2601.
[14] BREIMAN L.Random forests[J].Machine Learning,2001,45(1):5-32.
[15] HANSCH R,HELLWICH O.Evaluation of tree creation methods within random forests for classification of PolSAR images[C]//Proceedings of 2015 IEEE International Geoscience and Remote Sensing Symposium.Milan:IEEE,2015:361-364.
[16] 隋艳立.基于深度支持向量机的极化SAR图像分类[D].西安:西安电子科技大学,2014.
[17] 徐乔,张霄,余绍淮,等.综合多特征的极化SAR图像随机森林分类算法[J].遥感学报,2019,23(4):685-694.
[18] HINTON G E,SALAKHUTDINOV R R.Reducing the dimensionality of data with neural networks[J].Science,2006,313(5786):504-507.
[19] RUMELHART D E,HINTON G E,WILLIAMS R J.Learning representations by back-propagating errors[J].Nature,1986,323(6088):533-536.
[20] HINTON G E.Learning multiple layers of representation[J].Trends in Cognitive Sciences,2007,11(10):428-434.
[21] LECUN Y,BENGIO Y,HINTON G.Deep learning[J].Nature,2015,521(7553):436-444.
[22] NG A.Sparse autoencoder[J].CS294A Lecture Notes,2011,72(2011):1-19.
[23] 邓磊,付姗姗,张儒侠.深度置信网络在极化SAR图像分类中的应用[J].中国图象图形学报,2016,21(7):933-941.
[24] LIU Fang,JIAO Licheng,HOU Biao,et al.POL-SAR image classification based on wishart DBN and local spatial information[J].IEEE Transactions on Geoscience and Remote Sensing,2016,54(6):3292-3308.
[25] XIE Huiming,WANG Shuang,LIU Kun,et al.Multilayer feature learning for polarimetric synthetic radar data classification[C]//Proceedings of 2014 IEEE Geoscience and Remote Sensing Symposium.Quebec City:IEEE,2014:2818-2821.
[26] LECUN Y,BOTTOU L,BENGIO Y,et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[27] KRIZHEVSKY A,SUTSKEVER I,HINTON G E.ImageNet classification with deep convolutional neural networks[J].Communications of the ACM,2017,60(6):84-90.
[28] SZEGEDY C,LIU Wei,JIA Yangqing,et al.Going deeper with convolutions[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition.Boston:IEEE,2015:1-9.
[29] PIRAMANAYAGAM S,SCHWARTZKOPF W,KOEHLER F W,et al.Classification of remote sensed images using random forests and deep learning framework[J].Image and Signal Processing for Remote Sensing XXII,2016,10004:205-212.
[30] 张佳琪.基于深度学习的极化SAR地物分类研究[D].北京:中国测绘科学研究院,2018.
[31] 蔡烁,胡航滔,王威.基于深度卷积网络的高分遥感图像语义分割[J].信号处理,2019,35(12):2010-2016.
[32] 熊风光,张鑫,韩燮,等.改进的遥感图像语义分割研究[J].计算机工程与应用,2022,58(8):185-190.
[33] CHEN L C,PAPANDREOU G,KOKKINOS I,et al.Semantic image segmentation with deep convolutional nets and fully connected CRFs[J].Computer Science,2014(4):357-361.
[34] CHEN L C,PAPANDREOU G,KOKKINOS I,et al.DeepLab:semantic image segmentation with deep convolutional nets,atrous convolution,and fully connected CRFs[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2018,40(4):834-848.
[35] CHEN L C,PAPANDREOU G,SCHROFF F,et al.Rethinking atrous convolution for semantic image segmentation[EB/OL].[2025-09-06].https://arxiv.org/abs/1706.05587.
[36] CHEN L C,ZHU Yukun,PAPANDREOU G,et al.Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//Proceedings of 2018 Computer Vision.Cham:Springer,2018:833-851.
[37] WOO S,PARK J,LEE J Y,et al.CBAM:convolutional block attention module[C]//Proceedings of 2018 Computer Vision.Cham:Springer,2018:3-19.
[38] SHELHAMER E,LONG J,DARRELL T.Fully convolutional networks for semantic segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(4):640-651.
[39] RONNEBERGER O,FISCHER P,BROX T.U-Net:convolutional networks for biomedical image segmentation[C]//Proceedings of 2015 Medical Image Computing and Computer-Assisted Intervention.Cham:Springer,2015:234-241.