Abstract
Since the existing terrain classification algorithm based on deep learning is not ideal for unbalanced PolSAR classification, a effective terrain classification algorithm based on wavelet kernel sparse deep coding network under unbalanced data set is proposed in this paper. The algorithm firstly adopts a structured sparse operation so as to enhance the accuracy of feature propagation and reduce the amount of stored data, where the unimportant parameter connections in each group are gradually reduced by dividing the network convolution kernel into multiple groups during the training process; The wavelet kernel-based classifier is used instead of the Sigmoid function to classify and identify features for different terrain, which has high generalization performance for small sample, nonlinear and high-dimensional mode classification problems. The experimental results show that our proposed classification algorithm can improve the classification performance of unbalanced samples, and improve the classification efficiency while ensuring the accuracy of classification.
Highlights
Polarimetric synthetic aperture radar (PolSAR) has the advantages of all-weather, all-weather, high resolution, low degree of interference, and its unique phase data contains the information of target surface roughness, surface effect and position orientation, which is far superior to optical equipment, and widely used in geological exploration, regional planning, situation assessment and other fields [1]
By combining with the SSA network, our proposed algorithmovercomes overcomes the shortcomings of traditional polarimetric SAR image classification method which is greatly affected by speckle noise and the result is too rough to a certain extent
By combining with sparse stacked autoencoder network, our algorithm overcomes the shortcomings of traditional polarimetric SAR image classification method which is greatly affected by speckle noise and the result is too rough to a certain extent
Summary
Polarimetric synthetic aperture radar (PolSAR) has the advantages of all-weather, all-weather, high resolution, low degree of interference, and its unique phase data contains the information of target surface roughness, surface effect and position orientation, which is far superior to optical equipment, and widely used in geological exploration, regional planning, situation assessment and other fields [1]. The traditional methods can not make full use of the rich characteristics of polarimetric SAR data to improve the classification accuracy. According to the analysis of existing models, it can be found that polarimetric SAR image classification algorithm based on deep learning needs complex feature decomposition process [19]–[22]. According to the stacked sparse autoencoder(SSA) model, this paper proposes a robust polarimetric SAR terrain classification algorithm, which uses the least square support vector machine based on Morlet wavelet kernel to replace the commonly used softmax classifier in the deep model. By combining with the SSA network, our proposed algorithmovercomes overcomes the shortcomings of traditional polarimetric SAR image classification method which is greatly affected by speckle noise and the result is too rough to a certain extent. The learned feature parameters can present a structured and sparse distribution, and the subsequent pruning of weights will not bring too much precision loss [23]–[26]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
