Abstract
High-frequency surface wave radar (HFSWR) is of great significance for maritime detection, but in the HFSWR echo signal, ship targets are often submerged in a variety of clutter and interference, making it difficult to detect vessels. In this paper, we propose an intelligent detection algorithm for targets concealed in strong clutter and complex interference environments. The algorithm has two stages: preprocessing and target detection. In the preprocessing stage, faster region-based convolutional neural networks Faster R-CNN are designed to identify and locate clutter and interference regions in the range Doppler spectrum; in the target detection stage, a two-level cascade algorithm is proposed. First, an extremum detection algorithm is proposed to identify suspicious target points in the clutter/interference regions, including real and false target points, to quickly obtain potential target positions. Second, in consideration of the characteristics of radar targets, two lightweight networks are designed to extract the CNN features and the stacked autoencoder features of the potential target locations. Then, fusion features are obtained and sent to an extreme learning machine that acts as a second-level classifier to distinguish between real and false target points. Experiments show that the proposed HFSWR target-detection algorithm has better performance for vessel detection in clutter/interference regions than the current mainstream detection algorithms.
Highlights
H IGH-FREQUENCY surface wave radar (HFSWR) has over- the-horizon detection ability for real time monitoring of large areas of the exclusive economic zone and has been widely used for vessel target detection [1]
To reduce the difficulty of target detection in complex environments affected by strong clutter and interference, we propose an intelligent algorithm based on cascade deep learning networks combined with ELM and feature fusion to effectively detect targets under the influence of strong clutter and interference, including targets at the edge of the clutter/interference region and partially submerged by the clutter/interference
We propose a new intelligent algorithm for target detection in clutter and interference regions for HFSWR, based on a cascade deep learning network combined with ELM and feature fusion
Summary
H IGH-FREQUENCY surface wave radar (HFSWR) has over- the-horizon detection ability for real time monitoring of large areas of the exclusive economic zone and has been widely used for vessel target detection [1]. 3) Most of the current algorithms have good detection in a stable environment, but drastically worse performance in strong clutter or interference due to the reduction of the SNR In these circumstances, the extracted morphological features in the algorithms cannot effectively distinguish target and clutter. To reduce the difficulty of target detection in complex environments affected by strong clutter and interference, we propose an intelligent algorithm based on cascade deep learning networks combined with ELM and feature fusion to effectively detect targets under the influence of strong clutter and interference, including targets at the edge of the clutter/interference region and partially submerged by the clutter/interference. The purpose of the extremum detector we use in this level is to separate all suspicious target points from the clutter and interference region to improve the real time performance of the algorithm and to complete the target localization.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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
