Abstract
The capability to exploit multiple sources of information is of fundamental importance in a battlefield scenario. Information obtained from different sources, and separated in space and time, provides the opportunity to exploit diversities to mitigate uncertainty. In this study, the authors address the problem of automatic target recognition (ATR) from synthetic aperture radar platforms. The author's approach exploits both channel (e.g. polarisation) and spatial diversity to obtain suitable information for such a critical task. In particular they use the pseudo-Zernike moments (pZm) to extract features representing commercial vehicles to perform target identification. The proposed approach exploits diversities and invariant properties of pZm leading to high confidence ATR, with limited computational complexity and data transfer requirements. The effectiveness of the proposed method is demonstrated using real data from the Gotcha dataset, in different operational configurations and data source availability.
Highlights
In the modern battlefield scenarios, the availability of multiple sources of information, such as spatial, temporal or other diversities, allows improvements in sensor performance and capabilities
Spatial diversity can be given by multiple platforms observing from different positions, whereas temporal diversity can be provided by multiple passes over the same area from the same platform
Noted that in [18], we have introduced the use of the pseudo-Zernike moments (pZm) for automatic target recognition (ATR) applied to micro-Doppler signatures
Summary
In the modern battlefield scenarios, the availability of multiple sources of information, such as spatial, temporal or other diversities, allows improvements in sensor performance and capabilities. The approach represents the electromagnetic scattering with primitive geometries (such as cylinders, spheres, edges, top hats etc.) and the physical geometry of the target, which can be seen as a combination of different elementary geometries Another approach has been investigated in [5], where a two-dimensional cepstrum-based feature is extracted with the aim of discriminating between clutter and man-made objects in a SAR image. A novel algorithm for ATR, with target identification capabilities, from multiple spatially separated, multi-channel SAR data, is presented. The novel feature extraction algorithm and the decision fusion frameworks are presented in detail
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have