FARKLI ÖZELLİK ÇIKARMA YÖNTEMLERİNİ KULLANARAK RADAR TABANLI EL HAREKETİ TANIMA İÇİN MAKİNE ÖĞRENİMİ YAKLAŞIMI

Abstract

Bu çalışmada, 24 GHz'de çalışan sürekli dalga radar sensörü kullanılarak temassız insan-makine etkileşimi için yedi farklı el hareketi sınıflandırılmıştır. Gürültüyü azaltmak ve anlamlı frekans bileşenlerini korumak için I (eş fazlı) ve Q (karesel) bileşenlerinden oluşan radar sinyallerine ön işleme uygulanır. Ön işleme adımını takiben, zaman, frekans ve istatistiksel alanlarda kapsamlı özellikler çıkarılır. Welch yöntemi kullanılarak elde edilen güç spektral yoğunluğu (PSD) özellikleri sonuçlara önemli ölçüde katkıda bulunur. Elde edilen yüksek boyutlu özellik kümesi daha sonra geleneksel makine öğrenmesi metodolojilerinin kullanımıyla sınıflandırmaya tabi tutulur. Topluluk öğrenme yaklaşımına dayanan Bagged Tree algoritmasının diğer geleneksel yöntemlerden daha iyi performans gösterdiği gösterilmiştir. Geliştirilen sistemin %90'ı aşan doğrulukta el hareketleri tespit oranına ulaştığı gösterilmiştir. Hem malzeme hem de işlem gücü açısından düşük maliyetli olan bu uygulama, insan-makine arayüzlerinde radar tabanlı temassız kontrol sistemlerinin etkinliğini ortaya koymaktadır. Bu çalışmanın bulguları, geleneksel makine öğrenmesi yöntemlerinin bu bağlamda tercih edilen yaklaşım olmaya devam ettiğini göstermektedir.

Keywords

• Sürekli Dalga
• Özellik Çıkarma
• El Hareketi Algılama
• Makine Öğrenimi
• Radar

MACHINE LEARNING APPROACH FOR RADAR-BASED HAND GESTURE RECOGNITION USING DIFFERENT FEATURE EXTRACTION METHODS

Abstract

In this study, seven different hand gestures are classified using a continuous wave radar sensor operating at 24 GHz for contactless human-machine interaction. Pre-processing is applied to the radar signals, consisting of I (in-phase) and Q (quadrature) components, to reduce noise and preserve meaningful frequency components. Subsequent to the preprocessing step, comprehensive features are extracted in the time, frequency, and statistical domains. The power spectral density (PSD) features obtained using the Welch method contribute significantly to the results. The resulting high-dimensional feature set is then subjected to classification through the utilization of conventional machine learning methodologies. The Bagged Tree algorithm, which is based on an ensemble learning approach, has been shown to outperform other traditional methods. The developed system has been demonstrated to achieve a detection rate of hand movements that exceeds 90% accuracy. This application, which is low-cost in terms of both material and processing power, demonstrates the efficacy of radar-based contactless control systems in human-machine interfaces. The findings of this study demonstrate that traditional machine learning methods continue to be a preferred approach in this context.

Keywords

• Continuous Wave
• Feature Extraction
• Hand Gesture Detection
• Machine Learning
• Radar.

References

1. L. Liu, S. Niu and S. McCrickard, “Non-contact Human Computer Interaction System Design and Implementation,” in Proc. 2017 IEEE/ACM Int. Conf. Connected Health: Applications, Systems and Engineering Technologies (CHASE), Philadelphia, PA, USA, 2017, pp. 312–320, doi: 10.1109/CHASE.2017.114.
2. L. Liao, Y. Liang, H. Li, Y. Ye and G. Wu, “A systematic review of global research on natural user interface for smart home system,” International Journal of Industrial Ergonomics, vol. 95, 2023, Art. no. 103445, doi: 10.1016/j.ergon.2023.103445.
3. G. Du, S. Long and H. Yuan, “Non-Contact Emotion Recognition Combining Heart Rate and Facial Expression for Interactive Gaming Environments,” IEEE Access, vol. 8, pp. 11896–11906, 2020, doi: 10.1109/ACCESS.2020.2964794.
4. Z. Ren, J. Meng and J. Yuan, “Depth camera based hand gesture recognition and its applications in Human-Computer-Interaction,” in Proc. 2011 8th Int. Conf. Information, Communications & Signal Processing (ICICS), Singapore, 2011, pp. 1–5, doi: 10.1109/ICICS.2011.6173545.
5. C. Wang, Z. Liu and S.-C. Chan, “Superpixel-Based Hand Gesture Recognition With Kinect Depth Camera,” IEEE Trans. Multimedia, vol. 17, no. 1, pp. 29–39, Jan. 2015, doi: 10.1109/TMM.2014.2374357.
6. H.-I. Lin, M.-H. Hsu and W.-K. Chen, “Human hand gesture recognition using a convolution neural network,” in Proc. 2014 IEEE Int. Conf. Automation Science and Engineering (CASE), New Taipei, Taiwan, 2014, pp. 1038–1043, doi: 10.1109/CoASE.2014.6899454.
7. Y. Fang, K. Wang, J. Cheng and H. Lu, “A Real-Time Hand Gesture Recognition Method,” in Proc. 2007 IEEE Int. Conf. Multimedia and Expo (ICME), Beijing, China, 2007, pp. 995–998, doi: 10.1109/ICME.2007.4284820.
8. S. Zhang, G. Li, M. Ritchie, F. Fioranelli and H. Griffiths, “Dynamic hand gesture classification based on radar micro-Doppler signatures,” in Proc. 2016 CIE Int. Conf. Radar (RADAR), Guangzhou, China, 2016, pp. 1–4, doi: 10.1109/RADAR.2016.8059518.

9. T. Sakamoto, X. Gao, E. Yavari, A. Rahman, O. Boric-Lubecke and V. M. Lubecke, “Hand Gesture Recognition Using a Radar Echo I–Q Plot and a Convolutional Neural Network,” IEEE Sensors Lett., vol. 2, no. 3, pp. 1–4, Sept. 2018, Art. no. 7000904, doi: 10.1109/LSENS.2018.2866371.
10. P. Molchanov, S. Gupta, K. Kim and K. Pulli, “Short-range FMCW monopulse radar for hand-gesture sensing,” in Proc. 2015 IEEE Radar Conf. (RadarCon), Arlington, VA, USA, 2015, pp. 1491–1496, doi: 10.1109/RADAR.2015.7131232.
11. M. G. Amin, Z. Zeng and T. Shan, “Hand Gesture Recognition based on Radar Micro-Doppler Signature Envelopes,” in Proc. 2019 IEEE Radar Conf. (RadarConf), Boston, MA, USA, 2019, pp. 1–6, doi: 10.1109/RADAR.2019.8835661.
12. J.-W. Choi, C.-W. Park and J.-H. Kim, “FMCW Radar-Based Real-Time Hand Gesture Recognition System Capable of Out-of-Distribution Detection,” IEEE Access, vol. 10, pp. 87425–87434, 2022, doi: 10.1109/ACCESS.2022.3200757.
13. R. R. Sharma, K. A. Kumar and S. H. Cho, “Novel Time-Distance Parameters Based Hand Gesture Recognition System Using Multi-UWB Radars,” IEEE Sensors Lett., vol. 7, no. 5, pp. 1–4, May 2023, Art. no. 6002204, doi: 10.1109/LSENS.2023.3268065.
14. Y. Kim and B. Toomajian, “Application of Doppler radar for the recognition of hand gestures using optimized deep convolutional neural networks,” in Proc. 2017 11th European Conf. Antennas and Propagation (EUCAP), Paris, France, 2017, pp. 1258–1260, doi: 10.23919/EuCAP.2017.7928465.
15. S.-J. Ryu, J.-S. Suh, S.-H. Baek, S. Hong and J.-H. Kim, “Feature-Based Hand Gesture Recognition Using an FMCW Radar and its Temporal Feature Analysis,” IEEE Sensors J., vol. 18, no. 18, pp. 7593–7602, 15 Sept. 2018, doi: 10.1109/JSEN.2018.2859815.
16. X. Dang, W. Ke, Z. Hao, P. Jin, H. Deng and Y. Sheng, “mm-TPG: Traffic Policemen Gesture Recognition Based on Millimeter Wave Radar Point Cloud,” Sensors, vol. 23, 2023, Art. no. 6816, doi: 10.3390/s23156816.
17. T. T. Trinh, H. V. Pham, T. D. Le and M. Le, “Hand Gesture Recognition With Uncertainty Awareness via FMCW Radar Sensing and Deep Learning,” IEEE Sensors J., vol. 25, no. 13, pp. 24517–24524, 1 July 2025, doi: 10.1109/JSEN.2025.3573743.
18. W. Bai, S. Chen, J. Ma, Y. Wang and C. Han, “Gesture Recognition with Residual LSTM Attention Using Millimeter-Wave Radar,” Sensors, vol. 25, no. 2, p. 469, 2025, doi: 10.3390/s25020469.
19. RF beam Microwave, “K-LD7 Datasheet,” 2022. [Online]. Available: https://rfbeam.ch/wp-content/uploads/dlm_uploads/2022/10/KLD7_Datasheet.pdf [Accessed: Jan.19,2025].
20. B. Sarada, S. C. Ch, I. B. Sri and S. U. Sri, “Heart Beat Sound Signals Classification Using Spectral Roll Off,” in Proc. 2023 Int. Conf. Self Sustainable Artificial Intelligence Systems (ICSSAS), Erode, India, 2023, pp. 654–658, doi: 10.1109/ICSSAS57918.2023.10331653.
21. İ. Şeflek, “Radar-based Elderly Fall Detection Using Power Spectral Density Features Obtained by Different Methods,” in Proc. 2024 8th Int. Symp. Innovative Approaches in Smart Technologies (ISAS), İstanbul, Türkiye, 2024, pp. 1–5, doi: 10.1109/ISAS64331.2024.10845545.
22. F. Huang, G. Xie and R. Xiao, “Research on Ensemble Learning,” in Proc. 2009 Int. Conf. Artificial Intelligence and Computational Intelligence, Shanghai, China, 2009, pp. 249–252, doi: 10.1109/AICI.2009.235.
23. J.-T. Yu, L. Yen and P.-H. Tseng, “mmWave Radar-based Hand Gesture Recognition using Range-Angle Image,” in Proc. 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring), Antwerp, Belgium, 2020, pp. 1–5, doi: 10.1109/VTC2020-Spring48590.2020.9128573.
24. Y. Wang, D. Wang, Y. Fu, D. Yao, L. Xie and M. Zhou, “Multi-Hand Gesture Recognition Using Automotive FMCW Radar Sensor,” Remote Sens., vol. 14, 2022, Art. no. 2374, doi: 10.3390/rs14102374.
25. A. Ronco, P. Schilk and M. Magno, “TinyssimoRadar: In-Ear Hand Gesture Recognition with Ultra-Low Power mmWave Radars,” in Proc. 2024 IEEE/ACM Ninth Int. Conf. Internet-of-Things Design and Implementation (IoTDI), Hong Kong, 2024, pp. 192–202, doi: 10.1109/IoTDI61053.2024.00021