Powiadomienia systemowe
- Sesja wygasła!
Tytuł artykułu
Wybrane pełne teksty z tego czasopisma
Identyfikatory
Warianty tytułu
Podejście oparte na rozszerzonym banku filtrów dopplerowskich do ulepszonego wykrywania celów
Języki publikacji
Abstrakty
Radar Target Detection (RTD) is considered to be one of the most essential parts of modern radar systems. In typical radars, detecting targets in noise is difficult. Conventional radar signal processing approaches such as Constant False Alarm Rate (CFAR) are adopted in an attempt to improve the Signal-to-Noise Ratio (SNR). However, due to the severity of the harsh and complex environments in the radar measurements, the target detection problem becomes extremely challenging when employing such traditional approaches. Therefore, developing a reliable and robust RTD technique is essential. In this paper, an augmented Doppler Filter Bank (DFB) based approach has been proposed to handle the associated radar drawbacks in such a complicated scenario, by incorporating the computer vision algorithms in order to separate the moving targets from the noisy background through a real radar dataset. A Frequency Modulated Continuous Wave (FMCW) radar has been mounted on an Unmanned Aerial Vehicle (UAV) for ground targets detection purposes. A real flight has been conducted in a challenging environment to assess the performance of the proposed system. The experimental results demonstrate the ability of the proposed system to enhance the estimated forward velocity to 82.8% over the conventional DFB with the CFAR detector.
Radarowe wykrywanie celu (RTD) jest uważany za jedną z najważniejszych części nowoczesnych systemów radarowych. W typowych radarach wykrywanie celów w hałasie jest utrudnione. Konwencjonalne podejścia do przetwarzania sygnału radarowego, takie jak stała częstotliwość fałszywych alarmów (CFAR), są stosowane w celu poprawy stosunku sygnału do szumu (SNR). Jednak ze względu na surowość trudnych i złożonych środowisk w pomiarach radarowych, problem wykrywania celu staje się niezwykle trudny przy stosowaniu takich tradycyjnych podejść. Dlatego niezbędne jest opracowanie niezawodnej i solidnej techniki BRT. W tym artykule zaproponowano podejście oparte na rozszerzonym banku filtrów dopplerowskich (DFB), aby poradzić sobie z powiązanymi wadami radaru w tak skomplikowanym scenariuszu, poprzez włączenie algorytmów widzenia komputerowego w celu oddzielenia ruchomych celów od hałaśliwego tła za pomocą prawdziwego radaru zestaw danych. Radar fali ciągłej z modulacją częstotliwości (FMCW) został zamontowany na bezzałogowym statku powietrznym (UAV) w celu wykrywania celów naziemnych. Aby ocenić działanie proponowanego systemu, przeprowadzono prawdziwy lot w trudnym środowisku. Wyniki eksperymentów pokazują zdolność proponowanego systemu do zwiększenia szacowanej prędkości do przodu do 82,8% w porównaniu z konwencjonalnym DFB z detektorem CFAR.
Wydawca
Czasopismo
Rocznik
Tom
Strony
67--73
Opis fizyczny
Bibliogr. 25 poz., rys., tab.
Twórcy
autor
- Electronics and Electrical Communications Engineering Dept., Air Defence Collage, Alexandria, Egypt
autor
- Electronics and Electrical Communications Engineering Dept., Air Defence Collage, Alexandria, Egyp
autor
- Department of Geomatics, University of Calgary, Calgary, Canada
autor
- Electronics and Electrical Communications Engineering Dept., Faculty of Engineering, Tanta University, Tanta 31527, Egypt
autor
- Department of Electronics and Communication, Zagazig University, Egypt
Bibliografia
- [1] T. Long, Z. Liang and Q. Liu, “Advanced technology of high-resolution radar: Target detection, tracking, imaging, and recognition,” Science China. Inf. Sci, vol. 62 (4), no. 40301 pp. 1–26,2019.
- [2] F. Gini, ‘‘Grand challenges in radar signal processing,’’ Frontiers Signal Process., vol. 1, pp. 1–6, 2021.
- [3] W. Sun, M. Sun, X. Zhang and M. Li, “Moving vehicle detection and tracking based on optical flow method and immune particle filter under complex transportation environments,” Complexity, vol. 2020, no. 16, pp. 1–15, 2020.
- [4] Aubry, A. De Maio and M. M. Naghsh, “Optimizing Radar Waveform and Doppler Filter Bank via Generalized Fractional Programming,” IEEE Journal of selected topics in signal processing, vol. 9, no. 8, pp. 1387-1399, 2015.
- [5] J. R. Machado-Fern´andez, N. Mojena-Hern´andez and J. d. l. C. Bacallao-Vidal, “Evaluation of cfar detectors performance,” Iteckne, vol. 14, no. 2, pp. 170–178, 2017.
- [6] E. Mason, B. Yonel and B. Yazici, ‘‘Deep learning for radar,’’ in Proc. IEEE Radar Conf. (RadarConf), Seattle, WA, USA, pp. 1703–1708, 2017.
- [7] L. Wang, J. Tang and Q. Liao, “A study on radar target detection based on deep neural networks,” IEEE Sensors Letters, vol. 3, no. 3, pp. 1–4, 2019.
- [8] P. Lang, X. Fu, M. Martorella, J. Dong, R. Qin et al., ‘‘A comprehensive survey of machine learning applied to radar signal processing,’’ arXiv :2009.13702, 2020.
- [9] A. Jalil, H. Yousaf and M. Baig. “Analysis of CFAR techniques”. In: 2016 13th International Bhurban Conference on Applied Sciences and Technology (IBCAST). IEEE, Islamabad, Pakistan, pp. 654–659, 2016.
- [10] Q. Qi and W. Hu, “One efficient target detection based on neural network under homogeneous and non-homogeneous background,” Inter-national Conference on Communication Technology Proceedings, ICCT, Chengdu, China, vol. 2017, pp. 1503–1507, 2018.
- [11] H. Khalid, S. Pollin, M. Rykunov, A. Bourdoux and H. Sahli, “Convolutional Long Short-Term Memory Networks for Doppler-Radar based Target Classification,” In Proceedings of the 2019 IEEE Radar Conference, Boston, MA, USA, pp. 22– 26, 2019.
- [12] J. Akhtar and K. E. Olsen, “Go-cfar trained neural network target detectors,” in 2019 IEEE Radar Conference (RadarConf), Boston, MA, USA, pp. 1–5, 2019.
- [13] C. E. Thornton, M. A. Kozy, R. M. Buehrer, A. F. Martone and K. D. Sherbondy, ‘‘Deep reinforcement learning control for radar detection and tracking in congested spectral environments,’’ IEEE Trans. Cognit. Commun. Netw., vol. 6, no. 4, pp. 1335–1349, 2020.
- [14] X. X. Zhu, D. Tuia, L. Mou, G.-S. Xia, L. Zhang, F. Xu and F. Fraundorfer, ‘‘Deep learning in remote sensing: A comprehensive review and list of resources,’’ IEEE Geosci. Remote Sens. Mag., vol. 5, no. 4, pp. 8–36, 2017.
- [15] L. Zhang, L. Zhang and B. Du, ‘‘Deep learning for remote sensing data: A technical tutorial on the state of the art,’’ IEEE Geosci. Remote Sens.Mag., vol. 4, no. 2, pp. 22–40, 2016.
- [16] L. Wang, J. Tang and Q. Liao, "A Study on Radar Target Detection Based on Deep Neuranbl Networks," in IEEE Sensors Letters, vol. 3, no. 3, pp. 1-4, 2019.
- [17] H. Deng, Z. Geng and B. Himed, “Radar Target Detection Using Target Features and Artificial Intelligence,” 2018 Int. Conf. on Radar (RADAR), Brisbane, QLD, pp. 1-4, 2018.
- [18] F. Yavuz and M. Kalfa, “Radar Target Detection via Deep Learning,” 2020 28 th IEEE Conf. on Signal Processing and Communications Applications (SIU), Gaziantep, Turkey, pp. 1- 4, 2020.
- [19] J. Akhtar and K. Olsen “A Neural Network Target Detector with Partial CA-CFAR Supervised Training,” International Conference on Radar (RADAR), Brisbane, QLD, Australia, pp. 1-6, 2018.
- [20] M. Mostafa, S. Zahran, A. Moussa, N. El-Sheimy and A. Sesay, “Radar and visual odometry integrated system aided navigation for UAVS in GNSS denied environment,”. Sensors, vol. 18(9), no. 2776, 2018.
- [21] S. Zahran, M. Mostafa, A. Moussa and N. El-Sheimy, “Augmented Radar Odometry by Nested Optimal Filter Aided Navigation for UAVS in GNSS Denied Environment,”in 2021 International Telecommunications Conference, ITC-Egypt, Alexandria, Egypt, pp. 1-5, 2021.
- [22] K. L. Yuan, “Wavelet denoising based on threshold optimization method,” Engineering Journal of Wuhan University, vol.48, no.1, pp.74-80, 2015.
- [23] H. Masood, A. Zafar, M. U. Ali, M. A. Khan, S. Ahmed et al., “Recognition and tracking of objects in a clustered remote scene environment,” Computers, Materials & Continua, vol. 70, no. 1, pp. 1699–1719, 2022.
- [24] E. Katz and Y. Barness, “Comparison of SNR and Peak-SNR (PSNR) as performance measures and signals for peak-limited two-dimensional (2D) pixelated optical wireless communication,” in: Conference on Signals, Systems & Computers. IEEE, Pacific Grove, CA, USA, pp. 1880–1884, 2015.
- [25] E. B. Quist, P. C. Niedfeldt and R. W. Beard, “Radar odometry with recursive-RANSAC,” IEEE Transactions on Aerospace and Electronic System, vol. 52, no. 4, pp. 1618–1630, 2016
Uwagi
Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).
Typ dokumentu
Bibliografia
Identyfikator YADDA
bwmeta1.element.baztech-536611fd-aeaf-4a54-bd24-96b345d7f53e