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.

Multi-channel Synthetic Aperture Radar (MSAR) in the maritime environment has proven to be an effective technique for improved image fidelity and scene characterization. Past demonstrations of MSAR-based methods for improvements such as motion induced distortion correction and image classification were performed using a uniformly spaced array of phase centers. In this paper, we derive novel extensions of these techniques to the case of sparse and non-uniformly spaced phase center configurations and demonstrate their effectiveness for a variety of platforms and sensor arrangements. We establish general techniques for correcting motion induced distortions, establish theoretical bounds of performance, and empirically validate our techniques on data derived from our airborne MSAR system. We then use these images to characterize the structure of the maritime scene using our MSAR-based classification technique. Our imaging and classification techniques are amenable to efficient implementation on diverse hardware platforms and sensor arrangements, and thus can find ready application in practical multichannel radar systems.

We develop an end-to-end deep learning-based approach for the classification of complex maritime environments via multichannel synthetic aperture radar (MSAR) sensors. In particular, we introduce a novel convolutional neural network (CNN)-based multichannel structure that incorporates a divisive normalization technique that is critical for achieving consistent classification performance across maritime scenes. We evaluate the performance of our technique, called MSAR-Net, using datasets collected by the U.S. Naval Research Laboratory’s experimental airborne MSAR system. Our results demonstrate that MSAR-Net achieves consistently and substantially superior performance compared to conventional amplitude-based scene classification. Finally, though we focus on the specific (yet difficult) problem of maritime surveillance, MSAR-Net, introduced in this article, is a fundamental technique that can potentially result in significant performance improvements in a variety of multichannel surveillance and remote sensing applications.