Remote sensing image classification framework based on self-attention convolutional neural network

Li Yanfu; Fan Xijian; Yang Xubing; Xu Xinzhou

doi:10.12171/j.1000-1522.20210196

Journal of Beijing Forestry University > 2021 > 43(10): 81-88. > DOI: 10.12171/j.1000-1522.20210196

Li Yanfu, Fan Xijian, Yang Xubing, Xu Xinzhou. Remote sensing image classification framework based on self-attention convolutional neural network[J]. Journal of Beijing Forestry University, 2021, 43(10): 81-88. DOI: 10.12171/j.1000-1522.20210196

Citation:

PDF (5729 KB)

Remote sensing image classification framework based on self-attention convolutional neural network

1.
College of Information Science and Technology, Nanjing Forestry University, Nanjing 210037, Jiangsu, China
2.
School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing 210003, Jiangsu, China

More Information

Received Date: May 23, 2021
Revised Date: July 02, 2021
Available Online: July 20, 2021
Published Date: October 29, 2021

Graphical Abstract

Abstract

Abstract

Objective Remote sensing image classification technology plays a vital role in forestry monitoring operations such as forest resource survey, ecological engineering planning and forest pest and disease control.
Method The work proposes a remote sensing image classification method based on multi-headed self-attentive modules, which uses the convolutional neural network framework ResNet50 as the backbone network of the whole framework. The intermediate layers of the last three bottleneck layers of the ResNet50 network were replaced with multi-headed self-attentive modules, which enable the model to focus on the regions with the highest discrimination and thus improve the classification accuracy. The experiments in this study used three publicly available datasets, RSSCN7, EuroSAT and PatternNet, based on the Pytorch machine learning library, to train and test the framework, and add a comparison experiment with the accuracy of existing classification frameworks. At the same time, different batch sizes were used to train the proposed framework and test the classification effect.
Result Experimental results showed the average recognition rate of the proposed method on the three remote sensing classification datasets reaching 91.30%, 97.88% and 97.37%, respectively, which was better than the existing algorithms based on deep convolutional networks. Also, the total number of parameters of this algorithm was 2.08 × 10⁷, which was also much lower than that of existing algorithms.
Conclusion The results show that the proposed framework is able to achieve higher accuracy in a GPU-accelerated environment, reduce the number of parameters included in the framework, reduce the video memory consumption, and improve the accuracy of the classification results compared with existing remote sensing image classification frameworks.
- remote sensing image,
- convolutional neural network,
- multi-head self-attention block,
- image classification

FullText(HTML)

References (19)

References

[1]	王海晖. 不同遥感图像的融合与应用[D]. 武汉: 华中科技大学, 2003. Wang H H. Fusion and application of different remote sensing images[D]. Wuhan: Huazhong University of Science and Technology, 2003.
[2]	曾如珠. 遥感图像分类识别探究[J]. 泉州师范学院学报, 2000, 18(4):1−4. doi: 10.3969/j.issn.1009-8224.2000.04.011 Zeng R Z. On identification of classification of remote sensing images[J]. Journal of Quanzhou Nor-Mal College, 2000, 18(4): 1−4. doi: 10.3969/j.issn.1009-8224.2000.04.011
[3]	李石华, 王金亮, 毕艳. 遥感图像分类方法研究综述[J]. 国土资源遥感, 2005, 64(2):1−6. doi: 10.3969/j.issn.1001-070X.2005.02.001 Li S H, Wang J L, Bi Y. A review of methods for classification of remote sensing images[J]. Remote Sensing for Land & Resources, 2005, 64(2): 1−6. doi: 10.3969/j.issn.1001-070X.2005.02.001
[4]	张裕, 杨海涛, 袁春慧. 遥感图像分类方法综述[J]. 兵器装备工程学报, 2018, 39(8):108−112. doi: 10.11809/bqzbgcxb2018.08.023 Zhang Y, Yang H T, Yuan C H. A survey of remote sensing image classification methods[J]. Journal of Ordnance Equipment Engineering, 2018, 39(8): 108−112. doi: 10.11809/bqzbgcxb2018.08.023
[5]	罗军, 潘瑜春, 王纪华. 基于高分辨率遥感影像的设施农业资源信息采集技术研究[J]. 地理与地理信息科学, 2007, 23(3):51−54. doi: 10.3969/j.issn.1672-0504.2007.03.012 Luo J, Pan Y C, Wang J H. Study on building agricultural resource information collection technology based on high-resolution remote sensing image[J]. Geography and Geo-Information Science, 2007, 23(3): 51−54. doi: 10.3969/j.issn.1672-0504.2007.03.012
[6]	刘建闽, 黄帆, 戴军. 基于机器学习的遥感图像识别检测技术研究及应用[J]. 西安文理学院学报(自然科学版), 2015, 18(4):66−69. doi: 10.3969/j.issn.1008-5564.2015.04.016 Liu J M, Huang F, Dai J. Study and application of the technology of remote sensing image recognition and detection based on machine learning[J]. Journal of Xi’an University of Arts and Science (Natural Science Edition), 2015, 18(4): 66−69. doi: 10.3969/j.issn.1008-5564.2015.04.016
[7]	李国和, 乔英汉, 吴卫江, 等. 深度学习及其在计算机视觉领域中的应用[J]. 计算机应用研究, 2019, 36(12):3521−3529, 3564. doi: 10.19734/j.issn.1001-3695.2018.08.0604 Li G H, Qiao Y H, Wu W J, et al. Review of deep learning and its application in computer vision[J]. Application Research of Computers, 2019, 36(12): 3521−3529, 3564. doi: 10.19734/j.issn.1001-3695.2018.08.0604
[8]	陈超, 齐峰. 卷积神经网络的发展及其在计算机视觉领域中的应用综述[J]. 计算机科学, 2019, 46(3):63−73. doi: 10.11896/j.issn.1002-137X.2019.03.008 Chen C, Qi F. Review on development of convolutional neural network and its application in computer vision[J]. Computer Science, 2019, 46(3): 63−73. doi: 10.11896/j.issn.1002-137X.2019.03.008
[9]	陈波. 基于循环结构的卷积神经网络文本分类方法[J]. 重庆邮电大学学报(自然科学版), 2018, 30(5):705−710. doi: 10.3979/j.issn.1673-825X.2018.05.018 Chen B. Text classification method based on the cycle structured convolutional neural network[J]. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), 2018, 30(5): 705−710. doi: 10.3979/j.issn.1673-825X.2018.05.018
[10]	Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[J/OL]. ArXiv Preprint ArXiv: 1409.1556, 2014[2020−09−04]. https://arxiv.org/abs/1409.1556.
[11]	Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston: IEEE, 2015: 1−9.
[12]	He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas: IEEE, 2016: 770−778.
[13]	张德园, 常云翔, 张利国, 等. SAT-CNN: 基于卷积神经网络的遥感图像分类算法[J]. 小型微型计算机系统, 2018, 39(4):859−864. doi: 10.3969/j.issn.1000-1220.2018.04.042 Zhang D Y, Chang Y X, Zhang L G, et al. SAT-CNN: convolutional neural network framework for remote sensing image classification[J]. Journal of Chinese Computer Systems, 2018, 39(4): 859−864. doi: 10.3969/j.issn.1000-1220.2018.04.042
[14]	徐风, 苗哲, 业巧林. 基于卷积注意力模块的端到端遥感图像分类[J]. 林业工程学报, 2020, 5(4):133−138. doi: 10.13360/j.issn.2096-1359.201907003 Xu F, Miao Z, Ye Q L. End-to-end remote sensing image classification framework based on convolutional block attention module[J]. Journal of Forestry Engineering, 2020, 5(4): 133−138. doi: 10.13360/j.issn.2096-1359.201907003
[15]	Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate[J/OL]. ArXiv Preprint ArXiv: 1409.0473, 2014[2020−12−01]. https://arxiv.org/abs/1409.0473.
[16]	Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16x16 words: transformers for image recognition at scale[J/OL]. ArXiv Preprint ArXiv: 2010.11929, 2020[2021−03−01]. https://arxiv.org/abs/2010.11929.
[17]	Alex K, Ilya S, Geoffrey E H. ImageNet classification with deep convolutional neural networks[C]// Pereira F, Burges C J C, Bottou L, et al. Proceedings of the 25th International Conference on Neural Information Processing Systems. New York: Curran Associates Inc., 2012: 1097−1105.
[18]	Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]// Luxburg U V. 31st Annual Conference on Neural Information Processing Systems (NIPS 2017). Long Beach: Curran Associates Inc., 2017: 5998−6008.
[19]	Selvaraju R R, Cogswell M, Das A, et al. Grad-CAM: visual explanations from deep networks via gradient-based localization[J]. International Journal of Computer Vision, 2020, 128(2): 336−359. doi: 10.1007/s11263-019-01228-7

Cited By

Cited by

Periodical cited type(3)

1.	李林. 生活垃圾绝氧热解发电工艺构建与评估. 工业技术创新. 2020(01): 53-59 .
2.	陈立林，刘琼，杜沄燕. 森林自燃火灾中的凋落物辐射升温特性研究——以岳麓山为例. 中国安全生产科学技术. 2018(02): 174-179 .
3.	李华，李林. 竹类生物质热解技术构建与评估. 工业技术创新. 2017(03): 49-53 .

Other cited types(5)

Get Citation

PDF

XML

Article views (2184) PDF downloads (162) Cited by(8)

Turn off MathJax

Article Contents

Abstract

References

Remote sensing image classification framework based on self-attention convolutional neural network

Abstract

References

Cited by

Periodical cited type(3)

Other cited types(5)

Catalog

Export File

Citation

Format

Content