PolSAR Image Crop Classification Based on Deep Residual Learning Network

被引:0
|
作者
Mei, Xin [1 ]
Nie, Wen [1 ]
Liu, Junyi [2 ]
Huang, Kui [3 ]
机构
[1] Hubei Univ, Fac Resources & Environm Sci, Wuhan, Hubei, Peoples R China
[2] Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & R, Wuhan, Hubei, Peoples R China
[3] Wuhan Univ, Sch Geodesy & Geomat, Wuhan, Hubei, Peoples R China
关键词
PolSAR image; Crop classification; Simple linear iterative cluster; Feature optimization; Deep residual network;
D O I
暂无
中图分类号
S3 [农学(农艺学)];
学科分类号
0901 ;
摘要
PolSAR image classification is one of the most basic applications of polarimetric synthetic aperture radar (PolSAR) data, which is of great significance to the research and subsequent application of PolSAR data. Traditional PolSAR image classification methods, mainly based on a single type of target decomposition method, the dimension of feature used in the process of PolSAR image classification process is relatively less and cannot make full use of the abundant feature of the PolSAR image, which is the one of the most essential characteristics of PolSAR data. With the development of deep learning, an amount of excellent deep learning models is proposed, such as deep brief net, AlexNet, deep residual network (ResNet) and so on. The classification method based on deep learning is proved to be better than traditional methods in the classification of optical and SAR images. This paper mainly analyzes the application of ResNet model in PolSAR image classification, the effectiveness of the method was proved by comparing the classical PolSAR image classification method. Firstly, some target decomposition methods were selected to calculate the multi-dimensional feature image. Secondly, the sample points of different land cover types were manually selected, and the multi-dimensional features were extracted to form the experimental data samples. Then, the PolSAR classification model based on ResNet was constructed, and the model parameters were adjusted dynamically according to the experimental sample data. Finally, the trained model was applied to the classification of experimental data, and the accuracy of the model was assessed by calculating the Kappa index of the classification result. In this paper, a quantitative index is proposed to calculate the ability of each feature to distinguish different land cover types, and the weak distinguishing feature was deleted to reduce the influence of classification independent features on the model and to improved classification accuracy. As for the speckle noise, the PolSAR image was preprocessed by simple linear iterative clustering (SLIC) superpixel segmentation, the experimental image was divided into a determined number of superpixel blocks, and the PolSAR image classification based on super-pixel blocks. Experimental results show that the PolSAR image classification method based on ResNet is conducive to the comprehensive utilization of multidimensional features of PolSAR image, the classification accuracy of PolSAR image is better than that of the classic classification method. The optimization of feature sets is beneficial to reduce model training time and improve the classification accuracy of PolSAR image as well. The superpixel segmentation is beneficial to reduce speckle noise and further improves the accuracy of classification.
引用
收藏
页码:247 / 252
页数:6
相关论文
共 50 条
  • [41] A hybrid network for PolSAR image classification based on polarization orientation angles
    Fang, Zheng
    Zhang, Gong
    Dai, Qijun
    Xue, Biao
    Wang, Peng
    REMOTE SENSING LETTERS, 2022, 13 (04) : 383 - 393
  • [42] Attention-Based Multiscale Sequential Network for PolSAR Image Classification
    Hua, Wenqiang
    Wang, Xinlei
    Zhang, Cong
    Jin, Xiaomin
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
  • [43] PolSAR Image Land Cover Classification Based on Hierarchical Capsule Network
    Cheng, Jianda
    Zhang, Fan
    Xiang, Deliang
    Yin, Qiang
    Zhou, Yongsheng
    Wang, Wei
    REMOTE SENSING, 2021, 13 (16)
  • [44] Crop pest classification based on deep convolutional neural network and transfer learning
    Thenmozhi, K.
    Reddy, U. Srinivasulu
    COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2019, 164
  • [45] A Deep Reinforcement Learning-Based Framework for PolSAR Imagery Classification
    Nie, Wen
    Huang, Kui
    Yang, Jie
    Li, Pingxiang
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
  • [46] Deep Residual Network-based Melanocytic Lesion Classification with Transfer Learning
    Saad, Murtaza
    Islam, Sheikh Md Rabiul
    Fazal, Fahmida Binte
    2019 5TH INTERNATIONAL CONFERENCE ON ADVANCES IN ELECTRICAL ENGINEERING (ICAEE), 2019, : 160 - 164
  • [47] Wavelet Network- Based Deep Learning System for Image Classification
    Blel, Dorsaf
    Hassairi, Salima
    Ejbali, Ridha
    FOURTEENTH INTERNATIONAL CONFERENCE ON MACHINE VISION (ICMV 2021), 2022, 12084
  • [48] A Social Network Image Classification Algorithm Based on Multimodal Deep Learning
    Bai, J. W.
    Chi, C.
    INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS & CONTROL, 2020, 15 (06) : 1 - 12
  • [49] Deep Learning Image Classification Based on Neural Network Optimized SVM
    Chen, Na
    Xiao, Aiping
    Zheng, Gang
    2018 7TH INTERNATIONAL CONFERENCE ON ADVANCED MATERIALS AND COMPUTER SCIENCE (ICAMCS 2018), 2019, : 329 - 333
  • [50] Deep Learning in Image Classification using Residual Network (ResNet) Variants for Detection of Colorectal Cancer
    Sarwinda, Devvi
    Paradisa, Radifa Hilya
    Bustamam, Alhadi
    Anggia, Pinkie
    5TH INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND COMPUTATIONAL INTELLIGENCE 2020, 2021, 179 : 423 - 431