Abstract
The synthetic aperture radar (SAR) image preprocessing techniques and their impact on target recognition performance are researched. The performance of SAR target recognition is improved by composing a variety of preprocessing techniques. The preprocessing techniques achieve the effects of suppressing background redundancy and enhancing target characteristics by processing the size and gray distribution of the original SAR image, thereby improving the subsequent target recognition performance. In this study, image cropping, target segmentation, and image enhancement algorithms are used to preprocess the original SAR image, and the target recognition performance is effectively improved by combining the above three preprocessing techniques. On the basis of image enhancement, the monogenic signal is used for feature extraction and then the sparse representation-based classification (SRC) is used to complete the decision. The experiments are conveyed on the moving and stationary target acquisition and recognition (MSTAR) dataset, and the results prove that the combination of multiple preprocessing techniques can effectively improve the SAR target recognition performance.
Highlights
Synthetic aperture radar (SAR) is widely used in military and civilian fields because of its all-weather data measurement and imaging capabilities. e key technology represented by SAR automatic target recognition (ATR) has become an important support for intelligence reconnaissance, missile guidance, and other links [1]
Since the scattering center model is generally very complicated, it is difficult to estimate the parameters of the scattering center with high efficiency and precision. e classifiers used in SAR target recognition are mostly inherited from the field of optical pattern recognition or optimized and improved according to the characteristics of SAR images, such as K nearest neighbors (K-NN) in [8], support vector machine (SVM) used in [19, 20], adaptive
Image cropping is a very common preprocessing technique in SAR target recognition, which can efficiently eliminate a large amount of background redundancy in original SAR image. e image cropping operation is very simple, by segmenting a square area with a certain side length in the center of the original SAR image as the target image. e selected side length of the square has a certain influence on the final target recognition performance. e larger the side length is, the more background clutter will be removed, but at the same time it is possible to remove a part of the target area. erefore, it is very important to select a suitable cropping window
Summary
Synthetic aperture radar (SAR) is widely used in military and civilian fields because of its all-weather data measurement and imaging capabilities. e key technology represented by SAR automatic target recognition (ATR) has become an important support for intelligence reconnaissance, missile guidance, and other links [1]. In [8,9,10,11,12,13,14,15], principal component analysis (PCA), monogenic signal, mode decomposition, and other mathematical projection or signal decomposition algorithms were employed to obtain SAR image features Such features have good consistency and high extraction efficiency. Three types of preprocessing methods, image cropping, target segmentation, and image enhancement, are adopted for the problem of SAR image target recognition. On this basis, the monophonic signal is further used as the basic method of feature extraction to obtain multilevel spectrum features. Experiments are conveyed on the moving and stationary target acquisition and recognition (MSTAR) dataset. e results validate the effectiveness of the proposed method
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.
