Scene classification of high-resolution remote sensing image based on multi-kernel SVM using features extracted from LDCNN

doi:10.13474/j.cnki.11-2246.2021.0233

Abstract

Abstract: Due to the problem that the feature dimension of convolutional neural network is high and the single-layer feature cannot accurately express the complex semantic information of high-resolution remote sensing image, a scene classification method of the low dimension of convolutional neural network (LDCNN) based on multi-kernel SVM is proposed in this paper. Firstly, the pre-trained convolutional neural network is modified into a low-dimensional network structure. Then, different high-level features extracted from the low-dimensional network is performed to find the corresponding optimal kernel function via SVM classification using different kernel functions, and these multiple optimal kernel functions are fused into a new composite kernel. Finally, multi-kernel SVM classification is carried out. Experimental results show that the proposed method has low feature dimension, and can combine the advantages of features extracted from each layer via multi-kernel SVM, thus achieving more than 99% classification accuracy on two benchmark datasets. In addition, the experiment also proves that this method has strong transfer learning ability.

Key words: high-resolution remote sensing image, scene classification, convolutional neural network, features extraction, multi-kernel SVM

CLC Number:

P237

GENG Wanxuan, ZHOU Weixun, JIN Shuanggen. Scene classification of high-resolution remote sensing image based on multi-kernel SVM using features extracted from LDCNN[J]. Bulletin of Surveying and Mapping, 2021, 0(8): 14-21.

References

[1] 李德仁, 童庆禧, 李荣兴, 等. 高分辨率对地观测的若干前沿科学问题[J]. 中国科学:地球科学, 2012, 42(6):805-813.
[2] LOWE D G. Object recognition from local scale-invariant features[C]//Proceedings of the Seventh IEEE International Conference on Computer Vision. Kerkyra:IEEE, 1999(2):1150-1157.
[3] WANG W, CAAMAÑO G P, WILDE E, et al. What is the gist? Understanding the use of public gists on GitHub[C]//2015 IEEE/ACM 12th Working Conference on Mining Software Repositories. Florence:IEEE, 2015:314-323.
[4] 赵理君, 唐娉, 霍连志, 等. 图像场景分类中视觉词包模型方法综述[J]. 中国图象图形学报, 2014, 19(3):333-343.
[5] 王宇新, 郭禾, 何昌钦, 等. 用于图像场景分类的空间视觉词袋模型[J]. 计算机科学, 2011, 38(8):265-268.
[6] OKUMURA S, MAEDA N, NAKATA K, et al. Visual categorization method with a bag of PCA packed key points[C]//Proceedings of 4th International Congress on Image and Signal. Shanghai:IEEE, 2011, 950-953.
[7] 孟庆祥, 吴玄.基于深度卷积神经网络的高分辨率遥感影像场景分类[J]. 测绘通报, 2019(7):17-22.
[8] HAN X, ZHONG Y, CAO L, et al. Pre-trained AlexNet architecture with pyramid pooling and supervision for high spatial resolution remote sensing image scene classification[J]. Remote Sensing, 2017, 9(8):848.
[9] LIU N, LU X K, WAN L H, et al. Improving the separ-ability of deep features with discriminative convolution filters for RSI classification[J]. ISPRS International Journal of Geo-Information, 2018, 7(3):95.
[10] HU F, XIA G S, HU J W, et al. Transferring deep convolutional neural networks for the scene classification of high-resolution remote sensing imagery[J]. Remote Sensing, 2015, 7(11):14680-14707.
[11] ZHOU W X, NEWSAM S, LI C, et al. Learning low dimensional convolutional neural networks for high-resolution remote sensing image retrieval[J]. Remote Sensing, 2017, 9(5):489.
[12] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[C]//Advances in Neural Information Processing Systems.[S.l.]:Curran Associates Inc., 2012:1097-1105.
[13] 张学工.关于统计学习理论与支持向量机[J]. 自动化学报, 2000, 6(1):36-46.
[14] 李湘眷, 孙显, 王宏琦.基于多核学习的高分辨率遥感图像目标检测方法[J]. 测绘科学, 2013, 38(5):84-87.
[15] LIU Q, HANG R, SONG H, et al. Learning multiscale deep features for high-resolution satellite image scene classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(1):117-126.
[16] YANG Y, NEWSAM S. Bag-of-visual-words and spatial extensions for land-use classification[C]//Proceedings of the 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems. New York:ACM, 2010:270-279.
[17] XIA G S, HU J, HU F, et al. AID:a benchmark dataset for performance evaluation of aerial scene classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(7):3965-3981.
[18] BI Q, QIN K, ZHANG H, et al. APDC-Net:attention pooling-based convolutional network for aerial scene classification[J]. IEEE Geoscience and Remote Sensing Letters, 2020, 17(9):1603-1607.
[19] LU X, SUN H, ZHENG X. A feature aggregation convolu-tional neural network for remote sensing scene classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(10):7894-7906.
[20] XU K J, HUANG H, LI Y. Multilayer feature fusion network for scene classification in remote sensing[J]. IEEE Geoscience and Remote Sensing Letters, 2020, 17(11):1894-1898.