Enhanced Radar False Alarm Mitigation in Low-RCS Target Detection Using Time-Varying Trajectories on Range-Doppler Diagrams with DCNN

Abstract

We propose detecting low-radar cross section (RCS) targets using the time-varying characteristics in the range-Doppler diagram with three-dimensional deep convolutional neural networks (3D-DCNN), which significantly suppresses false alarms (FA). When low-RCS targets are in cluttered environments, it is not easy to detect them because of the trade-off between the probability of detection and FA rate depending on the detection threshold. In this paper, we employ a 3DDCNN to observe the trajectory of an object over a certain time and determine whether the detected object is a target or not. We use constant false alarm rate (CFAR) to detect low-RCS targets using low thresholds in high cluttered environments. This approach results in the detection of a significant amount of unwanted clutter and noise. The proposed algorithm effectively suppresses the FA rate and enhances overall detection accuracy. A comparison of the performance through simulation revealed that the probability of false alarm (Pfa) from 3 × 10-3 with CFAR and density-based spatial clustering of applications with noise (DBSCAN) was reduced to 1.2 × 10-5 with the proposed algorithm. For validation, we measured a drone, an example of a low-RCS target, at 10 m using a 77 GHz frequency modulated continuous wave (FMCW) radar manufactured by TI. The Pfa was 3 × 10-3 when the CFAR and DBSCAN were applied with one and two drones, respectively. However, the proposed algorithm reduced this to 9.3×10-6 and 2.1×10-5, respectively. Additionally, a drone was measured and verified using FMCW radar manufactured by TORIS at 7 km. The proposed algorithm reduces the Pfa from 2.5 × 10-4 to 7.4 × 10-7 © IEEE.