Scene classification of high-resolution remote sensing imagery based on deep transfer deformable convolutional neural networks

被引：0
|
作者：
Shi H. [1 ,2 ]
Xu Y. [1 ,2 ]
Teng W. [3 ]
Wang N. [4 ,5 ]
机构：
[1] Co-Innovation Center for the Sustainable Forestry in Southern China, Nanjing Forestry University, Nanjing
[2] College of Forest, Nanjing Forestry University, Nanjing
[3] Department of Geosciences, University of Massachusetts, 01003, MA
[4] Anhui Engineering Laboratory of Geographical Information Intelligent Sensor and Service, Chuzhou
[5] School of Geographic Information and Tourism, Chuzhou University, Chuzhou
来源：
Cehui Xuebao/Acta Geodaetica et Cartographica Sinica | 2021年 / 50卷 / 05期
关键词：
Convolutional neural networks; Deformable convolutional; Remote sensing; Scene classification; Transfer learning;
D O I：
10.11947/j.AGCS.2021.20200190
中图分类号：
学科分类号：
摘要：
In recent years, scene classification of high-resolution remote sensing images based on deep convolutional neural networks has become the focus of attention. Because of the existing deep convolution neural network is not robust to the geometric deformation of remote sensing scene image, we proposed a novel scene classification method for high-resolution remote sensing image, based on the deep transfer deformable convolutional neural networks (DTDCNN). Specifically, the depth features of remote sensing image are extracted by using the trained depth model on the large-scale natural scene dataset (ImageNet), then, the deformable convolution layer is introduced to learn the depth features which are robust to the geometric deformation of remote sensing scene.The results show that: the accuracy of DTDCNN on AID, UC-Merced and NWPU-RESISC45 datasets is improved by 4.25%, 1.9% and 4.83% after adding the deformable convolution, respectively. By the adaptive adjustment of the receptive field for different objects in the scene, DTDCNN enhances the ability of spatial sampling position, and, effectively improves the accuracy of remote sensing scene classification. © 2021, Surveying and Mapping Press. All right reserved.
引用
收藏
页码：652 / 663
页数：11
相关论文
共 37 条
  • [1] LI Deren, TONG Qingxi, LI Rongxing, Et al., Current issues in high-resolution Earth observation technology, Science China Earth Sciences, 42, 6, pp. 805-813, (2012)
  • [2] YANG Yi, NEWSAM S., Bag-of-visual-words and spatial extensions for land-use classification, Proceedings of the 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems, pp. 270-279, (2010)
  • [3] CHERIYADAT A M., Unsupervised feature learning for aerial scene classification, IEEE Transactions on Geoscience and Remote Sensing, 52, 1, pp. 439-451, (2014)
  • [4] ZHANG Fan, Deep learning for very high resolution remote sensing data analysis, (2017)
  • [5] ZHU Qiqi, ZHONG Yanfei, ZHAO Bei, Et al., Bag-of-Visual-Words scene classifier with local and global features for high spatial resolution remote sensing imagery, IEEE Geoscience and Remote Sensing Letters, 13, 6, pp. 747-751, (2016)
  • [6] QIAN Xiaoliang, LI Jia, CHENG Gong, Et al., Evaluation of the effect of feature extraction strategy on the performance of high-resolution remote sensing image scene classification, Journal of Remote Sensing, 22, 5, pp. 758-776, (2018)
  • [7] YAN Miao, ZHAO Hongdong, LI Yuhai, Et al., Multi-classification and recognition of hyperspectral remote sensing objects based on convolutional neural network, Laser & Optoelectronics Progress, 56, 2, (2019)
  • [8] GONG Xi, WU Liang, XIE Zhong, Et al., Classification method of high-resolution remote sensing scenes based on fusion of global and local deep features, Acta Optica Sinica, 39, 3, (2019)
  • [9] MARMANIS D, DATCU M, ESCH T, Et al., Deep learning earth observation classification using ImageNet pretrained networks, IEEE Geoscience and Remote Sensing Letters, 13, 1, pp. 105-109, (2016)
  • [10] ZHUANG Fuzhen, LUO Ping, HE Qing, Et al., Survey on transter learning research, Journal of Software, 26, 1, pp. 26-39, (2015)
1234