전기전자학회논문지 (Journal of IKEEE)

  • 제26권3호
  • /
  • Pages.364-372
  • /
  • 2022
  • /
  • 1226-7244(pISSN)
  • /
  • 2288-243X(eISSN)
한국전기전자학회 (Institute of Korean Electrical and Electronics Engineers)
권호 표지
DOI QR코드

DOI QR Code

FMCW 레이다 센서 기반 사람과 사물 분류 시스템 설계 및 구현

Design and Implementation of Human and Object Classification System Using FMCW Radar Sensor

  • Sim, Yunsung (School of Electronics and Information Engineering, Korea Aerospace University) ;
  • Song, Seungjun (School of Electronics and Information Engineering, Korea Aerospace University) ;
  • Jang, Seonyoung (School of Electronics and Information Engineering, Korea Aerospace University) ;
  • Jung, Yunho (Department of Smart Air Mobility, Korea Aerospace University)
  • 투고 : 2022.08.09
  • 심사 : 2022.09.05
  • 발행 : 2022.09.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문에서는 FMCW(frequency modulated continuous wave) 레이다 센서를 활용한 사람과 사물을 분류하는 시스템 설계 및 구현 결과를 제시한다. 해당 시스템은 다중 객체 탐지를 위한 레이다 센서 신호처리 과정과 객체를 사람 및 사물로 분류하는 딥러닝 과정을 수행한다. 딥러닝의 경우 높은 연산량과 많은 양의 메모리를 요구하기 때문에 경량화가 필수적이다. 따라서 CNN (convolution neural network) 연산을 이진화하여 동작하는 BNN (binary neural network) 구조를 적용하였으며, 실시간 동작을 위해 하드웨어 가속기를 설계하고 FPGA 보드 상에서 구현 및 검증하였다. 성능 평가 및 검증 결과 90.5%의 다중 객체 구분 정확도, CNN 대비 96.87% 감소된 메모리 구현이 가능하며, 총 수행 시간은 5ms로 실시간 동작이 가능함을 확인하였다.

This paper proposes the design and implementation results for human and object classification systems utilizing frequency modulated continuous wave (FMCW) radar sensor. Such a system requires the process of radar sensor signal processing for multi-target detection and the process of deep learning for the classification of human and object. Since deep learning requires such a great amount of computation and data processing, the lightweight process is utmost essential. Therefore, binary neural network (BNN) structure was adopted, operating convolution neural network (CNN) computation in a binary condition. In addition, for the real-time operation, a hardware accelerator was implemented and verified via FPGA platform. Based on performance evaluation and verified results, it is confirmed that the accuracy for multi-target classification of 90.5%, reduced memory usage by 96.87% compared to CNN and the run time of 5ms are achieved.

키워드

과제정보

This work was supported by Institute of Information & communications Technology Planning & Evaluation(IITP) grant funded by-and-by the Korea government(MSIT) (No. 2020-0-00201, 2022-0-00960) and CAD tools were supported by IDEC.

참고문헌

  1. A. Jalil and M. Matalangi, "Object motion detection in home security system using the binary-image comparison method based on robot operating system 2 and Raspberry Pi," Ilk. J. Ilm., vol.13, no.1, pp.1-8, 2021. DOI: 10.33096/ilkom.v13i1.686.1-8
  2. I. G. M. N. Desnanjaya and I. N. A. Arsana, "Home security monitoring system with IoT-based Raspberry Pi," Indones. J. Electr. Eng. Comput. Sci., vol.22, no.3, pp.1295-1302, 2021. DOI: 10.11591/ijeecs.v22.i3
  3. G. Wang, J.-M. Munoz-Ferreras, C. Gu, C. Li, and R. Gomez-Garcia, "Application of linearfrequency-modulated continuous-wave (LFMCW) radars for tracking of vital signs," IEEE Trans. Microw. Theory Techn., vol.62, no.6, pp.1387-1399, 2014. DOI: 10.1109/TMTT.2014.2320464
  4. H. Lee, B.-H. Kim, and J.-G. Yook, "Path loss compensation method for multiple target vital sign detection with 24-GHz FMCW radar," in Proc. IEEE Asia-Pacific Conf. Antennas Propag. (APCAP), pp.100-101, 2018. DOI: 10.1109/APCAP.2018.8538182
  5. H. Rohling and M. Kronauge, "New radar waveform based on a chirp sequence," in Proc. Int. Radar Conf., pp.1-4, 2014. DOI: 10.1109/RADAR.2014.7060246
  6. M. Kronauge, H. Rohling, "Fast Two-Dimensional CFAR Procedure," IEEE Trans. Aerosp. Electron. Syst., vol.49, no.3, pp.1817-1823, 2013. DOI: 10.1109/TAES.2013.6558022
  7. H. Rohling, "Radar CFAR thresholding in clutter and multiple target situations," IEEE Trans. Aerosp. Electron. Syst., vol.AES-19, no.4, pp.608-621, 1983. DOI: 10.1109/TAES.1983.309350
  8. H. Rohling, "Ordered statistic cfar technique-an overview," in Proc. 12th Int. Radar Symp. (IRS), pp.631-638, 2011.
  9. Q. Zheng et al., "A target detection scheme with decreased complexity and enhanced performance for range-Doppler FMCW radar," IEEE Trans. Instrum. Meas., vol.70, pp.1-13, 2021. DOI: 10.1109/TIM.2020.3027407
  10. Martin Ester, Hans-Peter Kriegel, Jorg Sander, and Xiaowei Xu, "A density-based algorithm for discovering clusters in large spatial databases with noise," In Proceedings of the Second International Conference on Knowledge Discovery and Data Mining (KDD'96), pp.226-231, 1996.
  11. Nagesh Singh Chauhan, "DBSCAN Clustering Algorithm in Machine Learning," https://www.kdnuggets.com/2020/04/dbscan-clustering-algorithm-machine-learning.html
  12. E. Hyun and J.-H. Lee, "Multi-target tracking scheme using a track management table for automotive radar systems," in Proc. 17th Int. Radar Symp. (IRS), pp.1-5, 2016. DOI: 10.1109/IRS.2016.7497283
  13. Hieu Vo Quang, L. W. Kim, C. S. Hong, "A Deep Learning Accelerator for a Typical Binary Neural Network Layer," KCC, pp.597-599, 2021.
  14. D. H. Jang, H. Kim, Y. H. Jung, "Design and implementation of human-detecting radar system for indoor security applications," The Institute of Korean Electrical and Electronics Engineers, vol.24, no.3, pp.783-790, 2020. DOI: 10.7471/ikeee.2020.24.3.783
  15. Jeonghee Nam, Chaeyoung Kang, Jeongyeon Kook, Yunho Jung, "Design and Implementation of CW Radar-based Human Activity Recognition System," Korea Citation Index (kci), vol.25, no.5, pp.415-425, 2021.
  16. Young-Joo Kong, Seon-Keol Woo, Sungho Park, Seung-Yong Shin, Youn Hui Jang, Eunjung Yang, "OS CFAR Computation Time Reduction Technique to Apply Radar System in Real Time," The Journal of Korean Institute of Electromagnetic Engineering and Science, vol.29 no.10, pp.791-798, 2018. DOI: 10.5515/KJKIEES.2018.29.10.791
  17. Md Alamgir Hossain, Md Imtiaz Hossain, Md Delowar Hossain, Ji Hoo Chun, Eui-Nam Huh, "Performance Assessment of Background Subtraction Algorithm," Korea Software Congress, pp.1049-1051, 2019.
  18. Infineon Technologies, "DEMO DISTANCE2GO" https://www.infineon.com/cms/en/product/evaluation-boards/demo-distance2go/
  19. Raspberry Pi, "raspberry-pi-4-model-b," https://www.raspberrypi.com/products/raspberry-pi-4-model-b/
  20. terasic Technologies, "DE1 - SoC Board," https://www.terasic.com.tw/cgi-bin/page/archive.pl?Language=English&No=836