Polarization imaging technology is an optical reconnaissance method based on the polarization characteristics of the target, which can simultaneously obtain a variety of information about the target. This information is very useful for visual tasks such as target detection. The traditional polarization parameter map as the input source for target detection has the problems of low accuracy and weak generalization ability. To solve the above problems, this paper builds a polarization parameter feature extraction network on the basis of Faster R-CNN, and adaptively generates polarization parameters. Perform feature extraction. It has been verified that the detection accuracy has been improved compared to the traditional network with polarization parameters as the input source.
Compressed sensing (CS) techniques have shown promise for radar imaging applications due to the excellent images they can produce. In this paper, a two dimensional (2D) sparse signal model for turntable radar imaging is developed, and a 2D CS based image reconstruction algorithm with a hyperbolic tangent constraint is proposed to improve the imaging performance and avoid the huge computational burden of 1D CS based methods, which require a tremendous amount of memory and computational resources. The augmented Lagrange multiplier and a 2D iterative soft thresholding function are used for solving the minimally sparse nonconvex optimization problem with parameter adjustment. Moreover, its convergence can be proved. Experimental results are presented to demonstrate the validity of the proposed approach.
Matrix completion (MC) is a technique of recovering a low rank matrix from partial observed elements and their corresponding subset of the entries, which has been applied in synthetic aperture radar (SAR) and inverse synthetic aperture radar (ISAR) imaging for compressing the sampling data. It is effective for undersampled data with random echo elements missing, but will not work well for situation that there are some random rows and columns with none of entries observed because the echo matrix will not satisfy the required condition of MC. However, it is easier to operate in practical application for the latter way and it needs to store limited number of corresponding subset. Thus, a novel way of matrix rearrangement is proposed for ISAR data based on the characteristics of ISAR echo. The new matrix satisfies the condition of MC, and it has better low rank property while reduces the computational time compared with the existing methods of matrix rearrangement. The effectiveness of the proposed method can be demonstrated by the simulation and experimental results.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.