Abstract
Ship detection with synthetic aperture radar (SAR) images, acquired at different working frequencies, is presented in this paper where a novel technique is proposed based on the generalized-likelihood ratio test (GLRT). Suitable electromagnetic models for both the sea clutter and the signal backscattered from the ship are considered in the new technique in order to improve the detector performance. The GLRT is compared to the traditional constant false alarm rate (CFAR) algorithm through Monte–Carlo simulations in terms of receiver operating characteristic (ROC) curves and computational load at different bands (S-, C-, and X-). Performances are also compared through simulations with different orbital and scene parameters at fixed values of band and polarization. The GLRT is then applied to real datasets acquired from different sensors (TerraSAR-X, Sentinel-1, and Airbus airborne demonstrator) operating at different bands (S-, C-, and X-). An analysis of the target-to-clutter ratio (TCR) is then performed and detection outcomes are compared with an automatic identification system data when available. Simulations show that the GLRT presents better ROCs than those obtained through the CFAR algorithm. On the other side, results on real SAR images demonstrate that the proposed approach greatly improves the TCR (between 22 and 32 dB on average), but its computational time is 1.5 times slower when compared to the CFAR algorithm.
Highlights
T HE request for maritime security and safety applications is increased in the recent years due to the growing interest in maritime surveillance
This paper is organized as follows: In Section II, the derivation of the generalized-likelihood ratio test (GLRT) for the ship detection is explained along with the estimation methods to compute the clutter and target parameters; in Section III, the to-clutter ratio (TCR) is analytically evaluated at different bands (S, C, and X-) for a typical ship target; in Section IV, the GLRT and constant false alarm rate (CFAR) algorithms are compared through Monte– Carlo simulations; in Section V, the ship detection algorithm is applied to real datasets acquired from different spaceborne and airborne sensors; in Section VI, conclusions are drawn
From the traditional CFAR algorithm, the GLRT approach is based on the target distribution, which is modeled according to the geometric optics (GO) model already presented in [25] by Iervolino et al The theoretical TCR has been evaluated at HH polarization for S, C, and X-bands
Summary
T HE request for maritime security and safety applications is increased in the recent years due to the growing interest in maritime surveillance. A model-based approach is employed in a SAR ship-detection chain for the first time in order to improve the overall performance. This paper is organized as follows: In Section II, the derivation of the GLRT for the ship detection is explained along with the estimation methods to compute the clutter and target parameters; in Section III, the TCR is analytically evaluated at different bands (S-, C-, and X-) for a typical ship target; in Section IV, the GLRT and CFAR algorithms are compared through Monte– Carlo simulations; in Section V, the ship detection algorithm is applied to real datasets acquired from different spaceborne and airborne sensors; in Section VI, conclusions are drawn
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 call
