Multi-Channel Synthetic Aperture Radar Based Classification of Maritime Scenes

Abstract

We present novel experimental evidence that demonstrates the effectiveness of exploiting scene motion information for the analysis of scene structure in maritime imaging applications. We analyze data captured by our novel airborne Multi-channel SAR (MSAR) system that is particularly suited to sampling the velocity profile of scatterers in the maritime environment. While previous works have shown the utility MSAR systems for correcting scene motion induced blurring artifacts, our work shows, for the first time, how the information furnished by an MSAR system can systematically render accurate classification of maritime scenes into different perceptual categories. We offer a methodology that is superior to traditional classification techniques that are based purely on the spatial structure of an image. Furthermore, the simplicity of the feature space involved together with the demonstrated classification performance on imagery captured by our airborne MSAR system underscore the strength of the methodology. INDEX TERMS Multi-channel synthetic aperture radar (SAR), ocean imaging, image classification

Sparse Multi-Channel Synthetic Aperture Radar Based Motion Induced Distortion Correction and Classification of Maritime Scenes

“…Eigen analysis of this covariance matrix identifies a single large eigenvalue and its associated eigenvector. Further details of the eigenanalysis of (23) and its relationship to dominant scattering mechanisms is given in [5]. Given this, the key idea is to perform an eigen-analysis of the multichannel covariance matrix associated with each scatterer in the image.…”

“…In the context of SAR imaging, a particular multi-sensor architecture that has been shown over the past several years to be particularly effective in delivering high-quality imaging products-especially in maritime imaging scenarios-is the multichannel synthetic aperture radar (MSAR) system [1][2][3][4][5][12][13] . In particular, MSAR systems have been shown to be highly effective in combatting blurring artifacts due to scene motion [1][2][3][4] and, more recently, for yielding superior classification performance in maritime sensing scenarios [5].…”

“…A much more elegant and powerful approach of combatting the deleterious effects of scene motion is to add additional antenna receive elements to the moving platform aligned along the flight direction; this constitutes the aforementioned MSAR architecture [1][2][3][4][5]. There are 2 classes of processing structures that have proven to be successful for correcting these distortions using MSAR systems: 1) Fast Fourier Transform (FFT) based velocity SAR (VSAR) processing [9,[1][2][3][4] and 2) Multiple Along Track Interferometry (MATI) processing approach that was introduced in [1].…”

“…These distortion corrected images can then be used as a starting point for further image analysis. In particular, on the side of classification, we have recently shown [5] that MSAR based systems furnish valuable covariance based motion information that complements traditional spatial amplitude based features, resulting in an elegant and superior approach to maritime scene classification [5].…”

Target Classification in Synthetic Aperture Radar Images Using Quantized Wavelet Scattering Networks

“…There are innumerable approaches to feature extraction, a necessary precursor to classification, including decision-theoretic approaches using quantitative descriptors such as length, area, and texture [ 1 , 2 ]; structural approaches using qualitative descriptors, such as relational descriptors [ 3 ]; projection of data into fixed basis sets, such as wavelets [ 4 ] and Zernike polynomial moments [ 5 ], or adaptive basis sets [ 6 ]. Other examples include robust edges and corners that are popular in computer vision, blind synthesis of template classes by using singular value decomposition, Karhunen–Loeve Transform [ 7 , 8 ] and estimation theoretic templates [ 9 ], motion-based covariance matrix-based features for multi-sensor architectures [ 10 ], and finally micro-Doppler- [ 11 ] and vibrometry-based [ 12 ] features that have applications in radar-based sensing systems. The advent of deep neural networks, a variant of which is the focus of our work, has systematized to a large extent the process of feature extraction and classification.…”