Research Article
BibTex RIS Cite

Adapting Object Detection Models for Multi-Target Detection Utilizing Radars

Year 2024, , 165 - 173, 30.08.2024
https://doi.org/10.46740/alku.1486054

Abstract

This paper investigates the use of Deep Learning (DL) in multiple input multiple output (MIMO) radar target detection, focusing on azimuth and elevation estimation. Traditional methods face challenges like interference and reflections, especially in multi-target scenarios. Feature extraction conventionally relies on range correlation, Doppler filtering, and angle beamforming, followed by detection after constant false alarm rate (CFAR) processing. However, early data sparsification by bin selection often leads to information loss, particularly with large data cubes required for practical implementation. Deep Learning techniques offer an alternative, specifically in azimuth and elevation detection at earlier stages of radar data processing. We developed a convolutional neural network (CNN) model that achieved Mean Square Errors (MSE) of 0.149 for azimuth and 0.168 for elevation on single-target data from 5,000 samples. The model's performance in dual-target scenarios showed MSEs ranging from 0.838 to 1.845, tested on 8,000 samples from a dataset of 72,000. This paper details the model development process, its impact on radar target detection, and potential future research directions involving the substitution of multi-bin Deep Learning blocks with traditional methods.

References

  • [1] Z.-Q. Zhao, P. Zheng, S. Xu, and X. Wu, “Object detection with deep learning: A review,” IEEE Trans. neural networks Learn. Syst., vol. 30, no. 11, pp. 3212–3232, 2019.
  • [2] K. He, G. Gkioxari, P. Dollár, and R. Girshick, “Mask r-cnn,” in Proceedings of the IEEE international conference on computer vision, 2017, pp. 2961–2969.
  • [3] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 779–788.
  • [4] W. Kim, H. Cho, J. Kim, B. Kim, and S. Lee, “YOLO-based simultaneous target detection and classification in automotive FMCW radar systems,” Sensors, vol. 20, no. 10, p. 2897, 2020.
  • [5] P. Lang et al., “A comprehensive survey of machine learning applied to radar signal processing,” arXiv Prepr. arXiv2009.13702, 2020.
  • [6] W. Jiang, Y. Ren, Y. Liu, and J. Leng, “Artificial neural networks and deep learning techniques applied to radar target detection: A review,” Electronics, vol. 11, no. 1, p. 156, 2022.
  • [7] L. Zhou, S. Wei, Z. Cui, and W. Ding, “YOLO-RD: A lightweight object detection network for range doppler radar images,” in IOP Conference Series: Materials Science and Engineering, 2019, vol. 563, no. 4, p. 42027.
  • [8] Z. Long, W. E. I. Suyuan, C. U. I. Zhongma, F. Jiaqi, Y. Xiaoting, and D. Wei, “Lira-YOLO: A lightweight model for ship detection in radar images,” J. Syst. Eng. Electron., vol. 31, no. 5, pp. 950–956, 2020.
  • [9] M. Amrani, A. Bey, and A. Amamra, “New SAR target recognition based on YOLO and very deep multi-canonical correlation analysis,” Int. J. Remote Sens., vol. 43, no. 15–16, pp. 5800–5819, 2022.
  • [10] Z. Baird, M. K. Mcdonald, S. Rajan, and S. J. Lee, “A cnn-lstm network for augmenting target detection in real maritime wide area surveillance radar data,” IEEE Access, vol. 8, pp. 179281–179294, 2020.
  • [11] M. Bharat Kumar and P. Rajesh Kumar, “Deep Convolutional Neural Network driven Neuro-Fuzzy System for Moving Target Detection Using the Radar Signals,” J. Inf. \& Knowl. Manag., vol. 21, no. 01, p. 2250010, 2022.
  • [12] Y. Zhang and Y. Hao, “A survey of SAR image target detection based on convolutional neural networks,” Remote Sens., vol. 14, no. 24, p. 6240, 2022.

Radarla Çoklu Hedef Tespiti için Nesne Tanıma Modellerinin Uyarlanması

Year 2024, , 165 - 173, 30.08.2024
https://doi.org/10.46740/alku.1486054

Abstract

Bu makale, çoklu giriş çoklu çıkış (MIMO) radar hedef tespitinde için Derin Öğrenme tekniğinin uygulamasını, özellikle azimut ve yükseklik tahminine odaklanarak ele almaktadır. Geleneksel yöntemler, özellikle çoklu hedef senaryolarında parazit ve yansıma gibi zorluklarla karşı karşıya kalmaktadır. Özellik çıkarımı, genellikle menzil korelasyonu, Doppler filtreleme, açı demetleme ve sabit yanlış alarm oranı (CFAR) işleminden sonra tespit adımlarını içeren klasik radar sinyal işleme hattına dayanmaktadır. Ancak, erken aşamada veri seyreltilmesi, pratik uygulamalar için gereken büyük veri küplerinde bilgi kaybına yol açabilmektedir. Derin Öğrenme teknikleri, azimut ve yükseklik tespiti için alternatif bir yaklaşım sunmaktadır. Geliştirdiğimiz konvolüsyonel sinir ağı (CNN) modeli, 5000 örnekten oluşan tek hedefli veri üzerinde azimut için 0.149 ve yükseklik için 0.168 Ortalama Kare Hata (MSE) değerleri ile yüksek performans göstermiştir. İki hedefli senaryolarda ise model, 72.000 örneklik veri setinden 8000 test örneği üzerinde 0.838 ile 1.845 arasında MSE değerleri elde etmiştir. Bu makale, model geliştirme sürecini, radar hedef tespitindeki etkisini ve Derin Öğrenme ile geleneksel yöntemlerin entegrasyonuna yönelik potansiyel gelecek araştırma yönlerini detaylı bir şekilde ele almaktadır.

References

  • [1] Z.-Q. Zhao, P. Zheng, S. Xu, and X. Wu, “Object detection with deep learning: A review,” IEEE Trans. neural networks Learn. Syst., vol. 30, no. 11, pp. 3212–3232, 2019.
  • [2] K. He, G. Gkioxari, P. Dollár, and R. Girshick, “Mask r-cnn,” in Proceedings of the IEEE international conference on computer vision, 2017, pp. 2961–2969.
  • [3] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 779–788.
  • [4] W. Kim, H. Cho, J. Kim, B. Kim, and S. Lee, “YOLO-based simultaneous target detection and classification in automotive FMCW radar systems,” Sensors, vol. 20, no. 10, p. 2897, 2020.
  • [5] P. Lang et al., “A comprehensive survey of machine learning applied to radar signal processing,” arXiv Prepr. arXiv2009.13702, 2020.
  • [6] W. Jiang, Y. Ren, Y. Liu, and J. Leng, “Artificial neural networks and deep learning techniques applied to radar target detection: A review,” Electronics, vol. 11, no. 1, p. 156, 2022.
  • [7] L. Zhou, S. Wei, Z. Cui, and W. Ding, “YOLO-RD: A lightweight object detection network for range doppler radar images,” in IOP Conference Series: Materials Science and Engineering, 2019, vol. 563, no. 4, p. 42027.
  • [8] Z. Long, W. E. I. Suyuan, C. U. I. Zhongma, F. Jiaqi, Y. Xiaoting, and D. Wei, “Lira-YOLO: A lightweight model for ship detection in radar images,” J. Syst. Eng. Electron., vol. 31, no. 5, pp. 950–956, 2020.
  • [9] M. Amrani, A. Bey, and A. Amamra, “New SAR target recognition based on YOLO and very deep multi-canonical correlation analysis,” Int. J. Remote Sens., vol. 43, no. 15–16, pp. 5800–5819, 2022.
  • [10] Z. Baird, M. K. Mcdonald, S. Rajan, and S. J. Lee, “A cnn-lstm network for augmenting target detection in real maritime wide area surveillance radar data,” IEEE Access, vol. 8, pp. 179281–179294, 2020.
  • [11] M. Bharat Kumar and P. Rajesh Kumar, “Deep Convolutional Neural Network driven Neuro-Fuzzy System for Moving Target Detection Using the Radar Signals,” J. Inf. \& Knowl. Manag., vol. 21, no. 01, p. 2250010, 2022.
  • [12] Y. Zhang and Y. Hao, “A survey of SAR image target detection based on convolutional neural networks,” Remote Sens., vol. 14, no. 24, p. 6240, 2022.
There are 12 citations in total.

Details

Primary Language English
Subjects Deep Learning, Machine Vision , Signal Processing
Journal Section Makaleler
Authors

İbrahim Rıza Hallaç 0000-0003-0568-3114

Deniz Akbaba This is me 0009-0002-4729-0888

Gökhan Gökce This is me 0009-0002-4689-7514

S. Gokhun Tanyer This is me 0000-0001-9506-2391

Peter F. Driessen This is me 0000-0003-1112-3738

Publication Date August 30, 2024
Submission Date May 23, 2024
Acceptance Date June 5, 2024
Published in Issue Year 2024

Cite

APA Hallaç, İ. R., Akbaba, D., Gökce, G., Tanyer, S. G., et al. (2024). Adapting Object Detection Models for Multi-Target Detection Utilizing Radars. ALKÜ Fen Bilimleri Dergisi, 6(2), 165-173. https://doi.org/10.46740/alku.1486054
AMA Hallaç İR, Akbaba D, Gökce G, Tanyer SG, Driessen PF. Adapting Object Detection Models for Multi-Target Detection Utilizing Radars. ALKÜ Fen Bilimleri Dergisi. August 2024;6(2):165-173. doi:10.46740/alku.1486054
Chicago Hallaç, İbrahim Rıza, Deniz Akbaba, Gökhan Gökce, S. Gokhun Tanyer, and Peter F. Driessen. “Adapting Object Detection Models for Multi-Target Detection Utilizing Radars”. ALKÜ Fen Bilimleri Dergisi 6, no. 2 (August 2024): 165-73. https://doi.org/10.46740/alku.1486054.
EndNote Hallaç İR, Akbaba D, Gökce G, Tanyer SG, Driessen PF (August 1, 2024) Adapting Object Detection Models for Multi-Target Detection Utilizing Radars. ALKÜ Fen Bilimleri Dergisi 6 2 165–173.
IEEE İ. R. Hallaç, D. Akbaba, G. Gökce, S. G. Tanyer, and P. F. Driessen, “Adapting Object Detection Models for Multi-Target Detection Utilizing Radars”, ALKÜ Fen Bilimleri Dergisi, vol. 6, no. 2, pp. 165–173, 2024, doi: 10.46740/alku.1486054.
ISNAD Hallaç, İbrahim Rıza et al. “Adapting Object Detection Models for Multi-Target Detection Utilizing Radars”. ALKÜ Fen Bilimleri Dergisi 6/2 (August 2024), 165-173. https://doi.org/10.46740/alku.1486054.
JAMA Hallaç İR, Akbaba D, Gökce G, Tanyer SG, Driessen PF. Adapting Object Detection Models for Multi-Target Detection Utilizing Radars. ALKÜ Fen Bilimleri Dergisi. 2024;6:165–173.
MLA Hallaç, İbrahim Rıza et al. “Adapting Object Detection Models for Multi-Target Detection Utilizing Radars”. ALKÜ Fen Bilimleri Dergisi, vol. 6, no. 2, 2024, pp. 165-73, doi:10.46740/alku.1486054.
Vancouver Hallaç İR, Akbaba D, Gökce G, Tanyer SG, Driessen PF. Adapting Object Detection Models for Multi-Target Detection Utilizing Radars. ALKÜ Fen Bilimleri Dergisi. 2024;6(2):165-73.