A novel deinterleaving method for radar pulse trains using pulse descriptor word dot matrix images and cascade‐recurrent loop network
Open Access
- 1 August 2023
- journal article
- research article
- Published by Institution of Engineering and Technology (IET) in IET Radar, Sonar & Navigation
- Vol. 17 (11) , 1626-1638
Abstract
Traditional signal deinterleaving methods depend on preset parameters, use complicated steps and have limitations in handling complex electromagnetic environments where signals overlap in the space, time and frequency domains. This paper presents a novel approach using a deep segmentation network for radar signal deinterleaving. The pulse descriptor word data is transformed into a dot matrix image, which is then processed by a Cascade‐Recurrent Loop Network (CRLN) for segmentation. The CRLN consists of a Type Segmentation Network, an Amount Decision Network and a Recurrent Individual Segmentation Network. By recursively segmenting each target and determining the number of sources, the CRLN overcomes the challenges posed by the discontinuity and high overlap of individuals in the dot matrix image. Experimental results demonstrate the effectiveness of the proposed method, surpassing traditional deinterleaving methods, achieving high accuracy, low omission rate and effectively mitigates the increasing batch problem in complex scenarios. The experiments conducted on a randomly generated dataset yielded impressive results: over 90% accuracy when dealing with pulses from 15 radars of different types, over 96% accuracy when deinterleaving pulses from 4 radar individuals of a same type and over 90% accuracy when handling 5 radars of different types with 10% pulse loss.Keywords
This publication has 13 references indexed in Scilit:
- Subspace Decomposition Based Adaptive Density Peak Clustering for Radar Signals SortingIEEE Signal Processing Letters, 2021
- Improved DBSCAN Radar Signal Sorting Algorithm Based on Rough Set2021
- Multi-Function Radar Signal Sorting Based on Complex NetworkIEEE Signal Processing Letters, 2020
- CenterMask: Real-Time Anchor-Free Instance Segmentation2020
- BASNet: Boundary-Aware Salient Object Detection2019
- Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation2019
- Improved Algorithm of Radar Pulse Repetition Interval Deinterleaving Based on Pulse CorrelationIEEE Access, 2019
- Radar signal sorting algorithm of k-means clustering based on data field2017
- Improved algorithm for the deinterleaving of radar pulsesIEE Proceedings F Radar and Signal Processing, 1992
- New techniques for the deinterleaving of repetitive sequencesIEE Proceedings F Radar and Signal Processing, 1989