19-11-2012, 05:04 PM
Sea Clutter Reduction and Target Enhancement by Neural Networks in a Marine Radar System
1Sea Clutter Reduction.pdf (Size: 2.08 MB / Downloads: 38)
Abstract:
The presence of sea clutter in marine radar signals is sometimes not desired. So,
efficient radar signal processing techniques are needed to reduce it. In this way, nonlinear
signal processing techniques based on neural networks (NNs) are used in the proposed clutter
reduction system. The developed experiments show promising results characterized by different
subjective (visual analysis of the processed radar images) and objective (clutter reduction,
target enhancement and signal-to-clutter ratio improvement) criteria. Moreover, a deep study
of the NN structure is done, where the low computational cost and the high processing speed
of the proposed NN structure are emphasized.
Introduction
The measurement of radar backscatter from an ocean surface, usually referred to as sea clutter, plays
an important role in ocean surveillance and remote sensing. In particular, two different points of view
may be identified depending on the application. From the first one, sea clutter contains useful information
about the ocean surface and the characterization of sea clutter becomes the focal point of the study. From the second one, if the primary objective is the detection of targets, such as ships and/or boats, then, the
presence of sea clutter is viewed as a source of interference to be suppressed. The studies presented in
this paper are focused on the last case, where the suppression of sea clutter signals and the enhancement
of signals related to ship/s play an important role.
Measuring and Monitoring Marine System
The radar measurements considered in our experiments were acquired in the FINO 1 (Forschungsplattformen
in Nord-und Ostsee) German research platform located at the German basin of the North Sea
(see Figure 1). In this platform, an incoherent radar system is available and a WaMoS II system [14]
is installed, which compose the measuring and monitoring marine system used during the experiments
(Figure 1). The WaMoS II system is an operational Wave Monitoring System developed by the German
research institute GKSS and commercialized by OceanWaveS GmbH. This system acquires every five
minutes a temporal sequence of 32 consecutive radar images. The intensity of each radar image cell
is coded without sign and 1 byte (8 bits), what sets a dynamic range of [0