Year-end Sale % OFF 
Abstract
The algorithm of synthetic aperture radar (SAR) for automatic target recognition consists of two stages: feature extraction and classification. The quality of extracted features has significant impacts on the final classification performance. This paper presents a SAR automatic target classification method based on the wavelet-scattering convolution network. By introducing a deep scattering convolution network with complex wavelet filters over spatial and angular variables, robust feature representations can be extracted across various scales and angles without training data. Conventional dimension reduction and a support vector machine classifier are followed to complete the classification task. The proposed method is then tested on the moving and stationary target acquisition and recognition (MSTAR) benchmark data set and achieves an average accuracy of 97.63% on the classification of ten-class targets without data augmentation.
Highlights
synthetic aperture radar (SAR) automatic target recognition (ATR) is defined as employing a computerized tool to predict the class of a target in SAR images or to describe certain attributes of interest for the target, such as the geometric and physical properties of the target in the absence of direct manual intervention
SAR images with these four classes of targets at a 17◦ depression angle are used for training, and those at 30◦ depression angle are used for testing
This paper presents a SAR automatic target classification method based on a wavelet-scattering convolution network
Summary
SAR automatic target recognition (ATR) is defined as employing a computerized tool to predict the class of a target in SAR images or to describe certain attributes of interest for the target, such as the geometric and physical properties of the target in the absence of direct manual intervention. A standard architecture of SAR ATR proposed by the MIT Lincoln Laboratory was described as three stages: detection, discrimination, and classification [1,2]. Detection is to extract candidate targets from SAR images using a false alarm rate (CFAR) detector. At the following discrimination stage, in order to eliminate false alarms, several features are selected to train a discriminator to solve the two-class (target and clutter) problem. In this paper, ‘recognition’ means the third stage, that is, classification of different types. There is a more advanced process called the identification process, which is not discussed in this paper. Factors such as imaging angles, target configuration and background conditions have significant impacts on the SAR image classification. Extracting good feature representations that are insensitive to the above factors is important to develop an effective SAR ATR system
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.
