Spectral classification of ecological spatial polarization SAR image based on target decomposition algorithm and machine learning
- 19 Downloads
With the development of science and technology, the classification of polarimetric SAR images has become an important part of the research of target recognition and image interpretation. However, for the research method is relatively simple and the accuracy is low, this paper carries out the work from the two aspects of feature extraction and feature classification of the ground object, and analyzes and studies the application and value of the polarimetric SAR system. The basic algorithm of polarization SAR image classification is proposed. A polarimetric SAR image feature classification method based on polarization target decomposition and support vector machine is proposed. Four kinds of scattering features and Freeman decomposition are obtained by Cloude decomposition. The simulation results show that the accuracy of using combined features is about 6.5% higher than that of single features. A polarization classification model based on polarization target decomposition and limit learning method is proposed. The simulation experiment shows ELM learning. The algorithm is indeed much faster than SVM learning. In this paper, a polarimetric SAR image classification method based on improved scattering mechanism coefficients is proposed, and the effectiveness of the polarimetric SAR image classification method based on improved scattering mechanism coefficients is verified. Experimental results show that after feature selection, the method of combining Freeman decomposition and Wishart classifier can get better classification results.
KeywordsPolarimetric SAR Target decomposition Machine learning Image feature classification Extreme learning
This work was supported by the Science and Technology Research Program of Chongqing Municipal Education Commission (Nos. KJQN201802101, KJZD-K201802101); the Doctoral high school talent training project (BYJS2016003); the Chongqing Graduate Scientific Research Innovation Project (CYB17131); the National Natural Science Foundation of China under Grants (71473074); and the National Natural Science Foundation of Shandong Province (ZR2018BF005). Jouf University, Sakaka, Al-Jouf, KSA (40/140).
Compliance with ethical standards
Conflict of interest
The authors declared that they have no conflicts of interest to this work.
- 4.Zhang Q, Liu Y (2017) Overview of Chinese first C band multi-polarization SAR satellite GF-3. Aerosp China 18(03):24–33Google Scholar
- 8.Gao W, Wang C, Yang M, Hu C, Luo X (2019) Analysis and classification of crop scattering characteristics based on polarimetric SAR data of high scores. Surv Eng 28(03):50–56Google Scholar
- 9.Wang J, Zhang J, Huang G, Zhao Z (2019) Study on the method of full-polarization SAR image classification based on BRF neural network. Surv Spatial Geogr Inf 42(01):198–201 + 205Google Scholar
- 10.Zhao Q, Hu G, Li X, Li Y (2019) Classification and change analysis of Shuangtai estuary wetland based on fully polarimetric SAR image. Environ Sci Res 32(02):309–316Google Scholar
- 11.Tang D, Wang F, Wang H (2019) A method for detection of flooding water in single polarized SAR data based on markov segmentation. J Electron Inf Technol 41(03):619–625Google Scholar
- 12.Han J, Wang H (2019) Classification of polarimetric SAR images based on MV and Wishart distance. J Chengdu Univ Inf Technol 34(01):31–34Google Scholar
- 13.Chen Q, Nie Y, Li L, Liu X (2017) Evaluation of building damage based on multi-texture features after polarization decomposition. J Remote Sens 21(06):955–965Google Scholar
- 15.Guo S, Yang L, Wen H et al (2016) Model-based target decomposition with the π/4 mode compact polarimetry data. Sci China 59(6):1–10Google Scholar
- 20.Deng H, Xu J, Shan W, Yuan C (2018) Extraction of polarimetric SAR image building area by active deep learning. J Surv Mapp Sci Technol 35(03):278–284Google Scholar
- 21.Xu J, Yuan C, Cheng Y, Zeng C, Xu K (2018) A classification of polarimetric SAR images based on active deep learning. Remote Sens Land Resour 30(01):72–77Google Scholar
- 22.Li Z, Li W, Yan Y (2019) Multi-objective decomposition optimization algorithm based on improved balance strategy. Comput Eng 45(03):155–161Google Scholar
- 23.Zhao Q, Guo S, Li X, Li Y (2018) A full-polarization SAR sea ice classification using target decomposition features. Acta Geochim Sin 47(12):1609–1620Google Scholar
- 24.Chen Y, Xu W (2018) Multi-objective decomposition particle swarm optimization algorithm based on comprehensive learning strategy. Microelectron Comput 35(10):75–79Google Scholar