Abstract
In this paper, we propose a new discriminative dictionary learning method based on Riemann geometric perception for polarimetric synthetic aperture radar (PolSAR) image classification. We made an optimization model for geometry-aware discrimination dictionary learning in which the dictionary learning (GADDL) is generalized from Euclidian space to Riemannian manifolds, and dictionary atoms are composed of manifold data. An efficient optimization algorithm based on an alternating direction multiplier method was developed to solve the model. Experiments were implemented on three public datasets: Flevoland-1989, San Francisco and Flevoland-1991. The experimental results show that the proposed method learned a discriminative dictionary with accuracies better those of comparative methods. The convergence of the model and the robustness of the initial dictionary were also verified through experiments.
Highlights
Remote Sens. 2021, 13, 1218.Polarimetric synthetic aperture radar (PolSAR) is a powerful tool in remote sensing, which transmits and receives electromagnetic waves in different states
The other pixels without ground truth are filled with black. We visualize it as a composite RGB image on a Pauli basis shown in Figure 3a, where |S HH − SVV | is normalized as red, |S HV | is normalized as green and |S HH + SVV | is normalized as blue
To demonstrate the superiority of the proposed method, we compare it here with other classical and state-of-art methods, including the classical maximum likelihood classifier based on Wishart distance [32], the Laplacian Eigenmaps and nonlinear dimensionality for representation [33], the D-KSVD model based on an non-subsampled contourlet transform (NSCT)-domain [16] and the SVM model based on Riemannian sparse coding [18]
Summary
Polarimetric synthetic aperture radar (PolSAR) is a powerful tool in remote sensing, which transmits and receives electromagnetic waves in different states. Unlike 2D images, SAR complex images containing four polarized matrices could provide more detailed information using different polarimetric channels. Due to increasing demands of disaster assessment, field interpretation, and environmental monitoring, PolSAR image classification attracts more and more attention, in which the core problem is the feature representation of PolSAR images. The polarimetric decomposition methods [1,2,3], the informative signature methods [4,5,6,7,8,9], the dimensional reduction methods [10,11,12,13] and the sparse representation methods [14,15,16,17,18]
Sign-in/Register to view highlights & summary 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.
