基于自适应上下文聚合网络的双高遥感影像分类

doi:10.11947/j.AGCS.2023.20220237

测绘学报 ›› 2023, Vol. 52 ›› Issue (7): 1175-1186.doi: 10.11947/j.AGCS.2023.20220237

基于自适应上下文聚合网络的双高遥感影像分类

胡鑫^1,2, 王心宇³, 钟燕飞²

1. 广州市城市规划勘测设计研究院, 广东广州 510060;
2. 武汉大学测绘遥感信息工程国家重点实验室, 湖北武汉 430079;
3. 武汉大学遥感信息工程学院, 湖北武汉 430079

收稿日期:2022-04-05 修回日期:2023-06-12 发布日期:2023-07-31
通讯作者: 王心宇 E-mail:wangxinyu@whu.edu.cn
作者简介:胡鑫(1994-),男,博士,研究方向为高光谱遥感信息处理。E-mail:whu_huxin@whu.edu.cn
基金资助:
国家重点研发计划（2022YFB3903405）；国家自然科学基金（42071350；42101327）

Adaptive context aggregation network for H² remote sensing imagery classification

HU Xin^1,2, WANG Xinyu³, ZHONG Yanfei²

1. Guangzhou Urban Planning and Design Survey Research Institute, Guangzhou 510060, China;
2. State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China;
3. School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China

Received:2022-04-05 Revised:2023-06-12 Published:2023-07-31
Supported by:
The National Key Research and Development Program of China (No. 2022YFB3903405); The National Natural Science Foundation of China (Nos. 42071350; 42101327)

摘要/Abstract

摘要： 融合高光谱和高空间分辨率（双高）遥感的优势可以实现地物目标更为全面和精细的属性识别。然而，空间分辨率的显著提升使得双高影像中地物细节特征凸显出来，呈现出极高的空谱异质性，进而导致同物异谱现象大量发生，地物类内方差明显增大。基于此，本文提出一种局部-全局上下文信息自适应聚合的快速双高影像分类框架（adaptive context aggregation network，ACANet），通过编码-解码的全卷积网络架构顾及全局空谱信息，在编码器中构建局部到全局的长距离上下文感知模块缓解双高影像极大的类内方差，在解码器中构建自适应上下文聚合模块进一步实现局部和全局的上下文信息自适应聚合。本文方法在WHU-Hi双高影像分类基准数据集中取得了优异的分类性能，试验表明可以很好缓解双高影像极高空谱异质性对地物精细分类的影响。

关键词: 高空间高光谱分辨率影像, 地物精细分类, 深度学习, 上下文信息

Abstract: High spectral and spatial resolution (H²) remote sensing imagery can achieve more comprehensive and precise attribute recognition of ground objects. However, the details of ground objects are gradually revealed with the significant improvement of the spatial resolution, which makes the H² images show extremely high spectral variability and spatial heterogeneity, and then the phenomenon of the same class with different spectrums occurs in large numbers; the intraclass variance increases significantly. As a result, an adaptive aggregation context network was proposed for H² image classification, which uses a full convolution network with encoder-decoder architecture to achieve global spectrum-spatial fusion. A local-to-global long-distance context module was designed to alleviate the intraclass variance in the encoder module. Then an adaptive context aggregation module was constructed in the decoder module for the adaptive aggregation of local and global context information. ACANet has achieved excellent performance in the WHU-Hi benchmark dataset, and the experiments show that it can sufficiently alleviate the impact of the spatial-spectrum heterogeneity of the H² image in the precise classification.

Key words: hyperspectral image with high spatial resolution, precise classification, deep learning, context information

中图分类号:

P237

胡鑫, 王心宇, 钟燕飞. 基于自适应上下文聚合网络的双高遥感影像分类[J]. 测绘学报, 2023, 52(7): 1175-1186.

HU Xin, WANG Xinyu, ZHONG Yanfei. Adaptive context aggregation network for H² remote sensing imagery classification[J]. Acta Geodaetica et Cartographica Sinica, 2023, 52(7): 1175-1186.

参考文献

[1] 童庆禧, 张兵, 郑兰芬. 高光谱遥感:原理、技术与应用[M].北京:高等教育出版社,2006. TONG Qingxi, ZHANG Bing,ZHENG Lanfen. Hyperspectral remote sensing:principle, technology and application[M].Beijing:Higher Education Press,2006.
[2] 张良培, 张立福. 高光谱遥感[M].北京:测绘出版社,2011. ZHANG Liangpei, ZHANG Lifu. Hyperspectral remote sensing[M].Beijing:Surveying and Mapping Press,2011.
[3] 杜培军, 夏俊士, 薛朝辉,等. 高光谱遥感影像分类研究进展[J]. 遥感学报, 2016, 20(2):236-256. DU Peijun, XIA Junshi, XUE Zhaohui, et al. Review of hyperspectral remote sensing image classification[J]. Journal of Remote Sensing, 2016, 20(2):236-256.
[4] ZHONG Yanfei, WANG Xinyu, XU Yao, et al. Mini-UAV-borne hyperspectral remote sensing:from observation and processing to applications[J]. IEEE Geoscience and Remote Sensing Magazine, 2018, 6(4):46-62.
[5] ZHONG Y, HU X, LUO C, et al. WHU-Hi:UAV-borne hyperspectral with high spatial resolution (H²) benchmark datasets and classifier for precise crop identification based on deep convolutional neural network with CRF[J]. Remote Sensing of Environment, 2020, 250:112012.
[6] HU Xin, ZHONG Yanfei, WANG Xinyu, et al. SPNet:spectral patching end-to-end classification network for UAV-borne hyperspectral imagery with high spatial and spectral resolutions[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60:1-17.
[7] HU Xin, WANG Xinyu, ZHONG Yanfei, et al. S3ANet:spectral-spatial-scale attention network for end-to-end precise crop classification based on UAV-borne H² imagery[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2022, 183:147-163.
[8] MIRZAPOUR F, GHASSEMIAN H. Improving hyperspectral image classification by combining spectral, texture and shape features[J]. International Journal of Remote Sensing, 2015, 36(4):1070-1096.
[9] GHAMISI P, MAGGIORI E, LI Shutao, et al. New frontiers in spectral-spatial hyperspectral image classification:the latest advances based on mathematical morphology, Markov random fields, segmentation, sparse representation and deep learning[J]. IEEE Geoscience and Remote Sensing Magazine, 2018, 6(3):10-43.
[10] LI Wei, PRASAD S, FOWLER J E. Hyperspectral image classification using Gaussian mixture models and Markov random fields[J]. IEEE Geoscience and Remote Sensing Letters, 2014, 11(1):153-157.
[11] SUN Shujin, ZHONG Ping, XIAO Huaitie, et al. An MRF model-based active learning framework for the spectral-spatial classification of hyperspectral imagery[J].IEEE Journal of Selected Topics in Signal Processing, 2015, 9(6):1074-1088.
[12] ZHAO J,ZHONG Y,JIA T,et al.Spectral-spatial classification of hyperspectral imagery with cooperative game[J].ISPRS Journal of Photogrammetry and Remote Sensing, 2018, 135:31-42.
[13] 魏立飞, 余铭, 钟燕飞, 等.空-谱融合的条件随机场高光谱影像分类方法[J]. 测绘学报,2020,49(3):343-354.DOI:10.11947/j.AGCS.2020.20190042. WEI Lifei, YU Ming, ZHONG Yanfei, et al. Hyperspectral image classification method based on space-spectral fusion conditional random field[J]. Acta Geodaetica et Cartographica Sinica,2020,49(3):343-354.DOI:10.11947/j.AGCS.2020.20190042.
[14] LI Shutao, SONG Weiwei, FANG Leyuan, et al. Deep learning for hyperspectral image classification:an overview[J].IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(9):6690-6709.
[15] CHEN Yushi, LIN Zhouhan, ZHAO Xing, et al. Deep learning-based classification of hyperspectral data[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014, 7(6):2094-2107.
[16] 刘冰, 余旭初, 张鹏强, 等. 联合空-谱信息的高光谱影像深度三维卷积网络分类[J]. 测绘学报,2019,48(1):53-63.DOI:10.11947/j.AGCS.2019.20170578. LIU Bing, YU Xuchu, ZHANG Pengqiang, et al. Deep 3D convolutional network combined with spatial-spectral features for hyperspectral image classification[J]. Acta Geodaetica et Cartographica Sinica,2019,48(1):53-63.DOI:10.11947/j.AGCS.2019.20170578.
[17] 左溪冰, 刘冰, 余旭初,等.高光谱影像小样本分类的图卷积网络方法[J]. 测绘学报,2021,50(10):1358-1369.DOI:10.11947/j.AGCS.2021.20200155. ZUO Xibing, LIU Bing, YU Xuchu, et al. Graph convolutional network method for small sample classification of hyperspectral images[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(10):1358-1369. DOI:10.11947/j.AGCS.2021.20200155.
[18] ZHENG Zhuo, ZHONG Yanfei, MA Ailong, et al. FPGA:fast patch-free global learning framework for fully end-to-end hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(8):5612-5626.
[19] XU Yonghao, DU Bo, ZHANG Liangpei. Beyond the patchwise classification:spectral-spatial fully convolutional networks for hyperspectral image classification[J].IEEE Transactions on Big Data, 2020, 6(3):492-506.
[20] SHEN Yu, ZHU Sijie, CHEN Chen, et al. Efficient deep learning of nonlocal features for hyperspectral image classification[J].IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(7):6029-6043.
[21] WANG Di, DU Bo, ZHANG Liangpei. Fully contextual network for hyperspectral scene parsing[J].IEEE Transactions on Geoscience and Remote Sensing,2022,60:1-16.
[22] HOU Qibin, ZHANG Li, CHENG Mingming, et al. Strip pooling:rethinking spatial pooling for scene parsing[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Seattle:IEEE,2020:4002-4011.
[23] CAO Yue, XU Jiarui, LIN S, et al. GCNet:non-local networks meet squeeze-excitation networks and beyond[C]//Proceedings of 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW).Seoul:IEEE, 2020:1971-1980.
[24] HU Jie, SHEN Li, ALBANIE S, et al. Squeeze-and-excitation networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(8):2011-2023.
[25] CHANG C C, LIN C J. LIBSVM:a library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology, 2011,2(3):1-27.
[26] MEI Xiaoguang, PAN Erting, MA Yong, et al. Spectral-spatial attention networks for hyperspectral image classification[J]. Remote Sensing, 2019, 11(8):963.
[27] ZHONG Zilong, LI J, LUO Zhiming, et al. Spectral-spatial residual network for hyperspectral image classification:a 3-D deep learning framework[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(2):847-858.
[28] PAOLETTI M E, HAUT J M, FERNANDEZ-BELTRAN R, et al. Deep pyramidal residual networks for spectral-spatial hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(2):740-754.

基于自适应上下文聚合网络的双高遥感影像分类

Adaptive context aggregation network for H² remote sensing imagery classification

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	杜培军, 张伟, 张鹏, 林聪, 郭山川, 胡泽周. 一种联合空谱特征的高光谱影像分类胶囊网络[J]. 测绘学报, 2023, 52(7): 1090-1104.
[2]	余旭初, 刘冰, 薛志祥. 高光谱地物要素识别潜力分析与前景展望[J]. 测绘学报, 2023, 52(7): 1115-1125.
[3]	杭仁龙, 李成相, 刘青山. 谱间对比学习的高光谱图像无监督特征提取[J]. 测绘学报, 2023, 52(7): 1164-1174.
[4]	张蒙蒙, 李伟, 刘欢, 赵旭东, 陶然. 基于形态变换与空间逻辑聚合的高光谱森林树种分类[J]. 测绘学报, 2023, 52(7): 1202-1211.
[5]	宋尚真, 杨怡欣, 王会峰, 王晓艳, 荣生辉, 周慧鑫. 高光谱图像稀疏约束与自编码器特征提取相结合的异常检测方法[J]. 测绘学报, 2023, 52(6): 932-943.
[6]	邓敏, 罗斌, 唐建波, 姚志鹏, 刘国平, 温翔, 胡润波, 柴华, 胡文柯. 顾及轨迹密度分布异质性的道路交叉口提取方法[J]. 测绘学报, 2023, 52(6): 1000-1009.
[7]	马梦锴, 董箭, 唐露露, 彭认灿, 周寅飞, 王芳. 兼顾要素正确分类及精准定位的栅格海图水深注记自动提取方法[J]. 测绘学报, 2023, 52(6): 1022-1036.
[8]	刘帅, 李笑迎, 于梦, 邢光龙. 高分辨率遥感图像双解耦语义分割网络模型[J]. 测绘学报, 2023, 52(4): 638-647.
[9]	张永显, 马国锐, 崔志祥, 张志军. 面向大视角差的无人机影像序列学习型特征匹配[J]. 测绘学报, 2023, 52(2): 230-243.
[10]	卜丽静, 吴文玉, 张正鹏, 杨银. 先验引导的多降质特征“珞珈一号”夜光遥感影像质量提升方法[J]. 测绘学报, 2023, 52(2): 244-259.
[11]	孙根云, 王鑫, 安娜, 张爱竹. 基于多源遥感的大尺度高分辨率不透水面深度学习提取方法[J]. 测绘学报, 2023, 52(2): 272-282.
[12]	禹文豪, 魏铖, 陈佳鑫. 面向不平衡POI类别分布的电子地图多层次标签预测模型[J]. 测绘学报, 2023, 52(2): 318-328.
[13]	杨敏, 陈果, 李连营, 黄浩然, 苗静, 晏雄锋. 序列卷积神经网络支持下线状地图目标的分段方法[J]. 测绘学报, 2023, 52(1): 108-116.
[14]	眭海刚, 刘畅, 干哲, 江政杰, 徐川. 多模态遥感图像匹配方法综述[J]. 测绘学报, 2022, 51(9): 1848-1861.
[15]	张良培, 何江, 杨倩倩, 肖屹, 袁强强. 数据驱动的多源遥感信息融合研究进展[J]. 测绘学报, 2022, 51(7): 1317-1337.

基于自适应上下文聚合网络的双高遥感影像分类

Adaptive context aggregation network for H2 remote sensing imagery classification

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

Adaptive context aggregation network for H² remote sensing imagery classification