Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Deep learning-based target distance and velocity estimation technique for OFDM radars

OFDM 레이다를 위한 딥러닝 기반 표적의 거리 및 속도 추정 기법

  • Choi, Jae-Woong (Department of Mobile Convergence and Engineering, Hanbat National University) ;
  • Jeong, Eui-Rim (Department of Information and Communication Engineering, Hanbat National University)
  • Received : 2021.11.04
  • Accepted : 2021.11.22
  • Published : 2022.01.31
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose deep learning-based target distance and velocity estimation technique for OFDM radar systems. In the proposed technique, the 2D periodogram is obtained via 2D fast Fourier transform (FFT) from the reflected signal after removing the modulation effect. The periodogram is the input to the conventional and proposed estimators. The peak of the 2D periodogram represents the target, and the constant false alarm rate (CFAR) algorithm is the most popular conventional technique for the target's distance and speed estimation. In contrast, the proposed method is designed using the multiple output convolutional neural network (CNN). Unlike the conventional CFAR, the proposed estimator is easier to use because it does not require any additional information such as noise power. According to the simulation results, the proposed CNN improves the mean square error (MSE) by more than 5 times compared with the conventional CFAR, and the proposed estimator becomes more accurate as the number of transmitted OFDM symbols increases.

본 논문에서는 OFDM 레이다를 위한 딥러닝 기반 표적의 거리 및 속도 추정 기법을 제안한다. 제안하는 기법은 표적으로부터 반사된 수신 신호를 받아 변조신호 제거 후 2차원 FFT를 통해 2차원 주기도를 얻는다. 주기도는 기존 및 제안 방법에서 표적의 거리 및 속도를 추정하는 입력신호이다. 주기도에서 정점은 표적의 위치를 나타내는데 표적의 거리 및 속도 추정을 위해 널리 사용되는 기존 기법은 CFAR (Constant False Alarm Rate) 알고리즘이다. 반면 제안하는 기법은 다중 출력 CNN (Convolutional Neural Network)을 이용하여 거리 및 속도를 추정한다. 기존 기법과 달리 제안 기법은 주기도 이외에 잡음 전력과 같이 추가적인 정보가 필요하지 않아 사용하기 편리하다. 컴퓨터 시뮬레이션 결과에 따르면 제안 추정 기법은 기존 기법보다 거리 및 속도 추정 MSE (Mean Square Error)오차 성능을 5배 이상 개선하며 송신 OFDM 심볼 개수가 증가할수록 정확도가 향상되는 특성을 보인다.

Keywords

Acknowledgement

This work has been supported by the UAV Intelligence Systems Research Laboratory program of Defense Acquisition Program Administration and Agency for Defense Development. (UD200027ED)

References

  1. W. Na, S. Jang, Y. Lee, L. Park, N. Dao, and S. Cho, "Frequency resource allocation and interference management in mobile edge computing for an Internet of Things system," IEEE Internet of Things Journal, vol. 6, no. 3, pp. 4910-4920, Jun. 2019. https://doi.org/10.1109/jiot.2018.2885348
  2. Y. Kawamoto, H. Takagi, H. Nishiyama, and N. Kato, "Efficient resource allocation utilizing Q-Learning in multiple UA communications," in IEEE Transactions on Network Science and Engineering, vol. 6, no. 3, pp. 293-302, Mar. 2019. https://doi.org/10.1109/tnse.2018.2842246
  3. K. Satyanarayana, M. El-Hajjar, P. H. Kuo, and L. Hanzo, "Hybrid beamforming design for full-duplex millimeter wave communication," IEEE Transactions on Vehicular Technology, vol. 68, no. 2, pp. 1394-1404, Jun. 2017. https://doi.org/10.1109/tvt.2018.2884049
  4. T. Wild, V. Braun, and H. Viswanathan, "Joint design of communication and sensing for beyond 5G and 6G systems," IEEE Access, vol. 9, pp. 30845-30857, Feb. 2021. https://doi.org/10.1109/ACCESS.2021.3059488
  5. M. Braun, M. Muller, M. Fuhr, and F. K. Jondral, "A USRP-based testbed for OFDM-based radar and communication systems," in Proceedings of 22nd Virginia Tech. Symposium on Wireless Communications, Blacksburg: VA, Jun. 2012.
  6. C. B. Barneto, T. Riihonen, M. Turunen, L. Anttila, M. Fleischer, K. Stadius, and M. Valkama, "Full-duplex OFDM radar with LTE and 5G NR waveforms: Challenges, solutions, and measurements," IEEE Transactions on Microwave Theory and Techniques, vol. 67, no. 10, pp. 4042-4054, Oct. 2019. https://doi.org/10.1109/tmtt.2019.2930510
  7. A. Evers and J. A. Jackson, "Analysis of an LTE waveform for radar applications," in 2014 IEEE Radar Conference, Cincinnati: OH, pp. 0200-0205, May. 2014.
  8. B. Dekker, S. Jacobs, A. S. Kossen, M. C. Kruithof, A. G. Huizing, and M. Geurts, "Gesture recognition with a low power FMCW radar and a deep convolutional neural network," in 2017 European Radar Conference (EURAD), Nuremberg: DE, pp. 163-166, Oct. 2017.
  9. L. Zhang, W. You, Q. Wu, S. Qi, and Y. Ji, "Deep learning-based automatic clutter/interference detection for HFSWR," Remote Sensing, vol. 10, no. 10, pp. 1517, Sep. 2018. https://doi.org/10.3390/rs10101517
  10. B. Major, D. Fontijne, A. Ansari, R. T. Sukhavasi, P. Gowaikar, M. Hamilton, S. Lee, S. Grechnik, and S. Subramanian, "Vehicle detection with automotive radar using deep learning on range-azimuth-doppler tensors," in Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, Seoul: KR, pp. 924-932, Oct. 2019.
  11. S. Mercier, S. Bidon, D. Roque, and C. Enderli, "Comparison of correlation-based OFDM radar receivers," IEEE Transactions on Aerospace and Electronic Systems, vol. 56, no. 6, pp. 4796-4813, Dec. 2020. https://doi.org/10.1109/TAES.2020.3003704
  12. J. Joung, S. Jung, S. Chung, and E. R. Jeong, "CNN-based Tx-Rx distance estimation for UWB system localisation," Electronics Letters, vol. 55, no. 17, pp. 938-940, Aug. 2019. https://doi.org/10.1049/el.2019.1084
  13. G. M. Nam, T. Y. Jung, S. H. Jung, and E. R. Jeong, "Distance estimation using convolutional neural network in UWB systems," Institute of Information and Communication Engineering, vol. 23, no. 10, pp. 640-651, Oct. 2019.
  14. K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas: LV, pp. 770-778, Jun. 2016.