FMICW 레이다에서 기계 학습을 활용한 다수 표적 탐지 기법 연구 = Multi-Target Detection in FMICW Radar Using Machine Learning

다국어 초록 (Multilingual Abstract)

This study proposes an effective method for detecting multiple targets in frequency-modulated interrupted continuous wave (FMICW) radar by using periodic signal characteristics and applying machine learning. FMICW radars are typically used for detecting a single target, but this method overcomes the challenges of range-Doppler coupling and spurious wave generation caused by the switching of transmit and receive signals, to detect multiple targets. The method first uses FMICW radar to generate an RD-Map by applying MLE (maximum likelihood estimation) , and then enhances the targets by identifying the intersection of lines generated by range-Doppler coupling. Thus, by applying a machine-learning-based object detection algorithm to the enhanced images, multiple target detection be- comes possible.

참고문헌 (Reference)

1 양희성 ; 전주환 ; 송성찬, "주파수 변조 단속 지속파를 이용하는 고해상도 밀리미터파 탐색기의 스퓨리어스 제거를 위한 스펙트럼 분석 기법" 한국전자파학회 23 (23): 85-95, 2012

2 이용환 ; 김영섭, "객체 검출을 위한 CNN과 YOLO 성능 비교 실험" 한국반도체디스플레이기술학회 19 (19): 85-92, 2020

3 S. Shinde, "YOLO based human action recognition and localization" 133 : 831-838, 2018

4 R. H. Khan, "Waveform analysis for high-frequency FMICW radar" 138 (138): 411-419, 1991

5 L. Rejfek, "System for automatic detection and analysis of targets in FMICW radar signal" 67 (67): 36-41, 2016

6 V. Winkler, "Range Doppler detection for automotive FMCW radars" 1445-1448, 2007

7 C. Liu, "Multipath propagation analysis and Ghost target removal for FMCW automotive radars" 330-334, 2020

8 K. J. Hickey, "Measurement of ocean surface currents using a long-range, high-frequency ground wave radar" 19 (19): 549-554, 1994

9 S. M. Kay, "Fundamentals of Statistical Signal Processing: Estimation Theory" Pearson 157-191, 1993

10 Y. Sun, "Chatter detection with beat effect based on beat frequency estimation" 18 (18): 2166-2174, 2021

11 Z. Liu, "An efficient pedestrian detection method based on YOLOv2" 2018 : 3518959-, 2018