Abstract
Classification of clutter, especially in the context of shore based radars, plays a crucial role in several applications. However, the task of distinguishing and classifying the sea clutter from land clutter has been historically performed using clutter models and/or coastal maps. In this paper, we propose two machine learning, particularly neural network, based approaches for sea-land clutter separation, namely the regularized randomized neural network (RRNN) and the kernel ridge regression neural network (KRR). We use a number of features, such as energy variation, discrete signal amplitude change frequency, autocorrelation performance, and other statistical characteristics of the respective clutter distributions, to improve the performance of the classification. Our evaluation based on a unique mixed dataset, which is comprised of partially synthetic clutter data for land and real clutter data from sea, offers improved classification accuracy. More specifically, the RRNN and KRR methods offer 98.50% and 98.75% accuracy, outperforming the conventional support vector machine and extreme learning based solutions.
Highlights
In the context of target tracking and target identification, radar returns from unwanted objects, termed as clutter, compete with the intended true returns
We present two novel classification systems based on the regularized randomized neural network (RRNN) and kernel ridge regression neural network (KRR) utilizing the ECAV
We show the overall performance of the RRNN and KRR classifiers against the support vector machines (SVMs) and extreme learning machine (ELM)
Summary
In the context of target tracking and target identification, radar returns from unwanted objects, termed as clutter, compete with the intended true returns. A ground based radar should focus only on ground based targets, and returns from sea-bound targets should be treated as clutter For this reason, discriminating between different clutter types is crucially vital for robust tracking and identification of objects from one surface type [1]. Model-driven approaches have been demonstrated to be significant enough, the accuracy of the land-sea clutter discrimination from a model-driven approach directly depends on the correctness of the underlying model This requires the model parameters to be captured properly; their range of values has to be reasonable enough to render accurate results. Even if model-driven approaches are considered to be good enough, they do demand a great deal of effort towards the estimation of the relevant parameter space for accurate discrimination of the land-sea clutter.
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
