Design and Implementation of Human and Object Classification System Using FMCW Radar Sensor
Keywords:
BNN accelerator, Embedded system, Frequency-modulated continuous wave (FMCW) radar, Field-programmable gate array (FPGA), Multi-target trackingAbstract
This paper proposes the design and implementation results for human and object classification systems utilizing frequency-modulated continuous wave (FMCW) radar sensors. 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 humans and objects. Since deep learning requires such a great amount of computation and data processing, the lightweight process is of utmost essential. Therefore, a 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 the field-programmable gate array (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 5 ms are achieved.
References
Jalil A, Matalangi M, 2021, Object Motion Detection in Home Security System Using the Binary-Image Comparison Method Based on Robot Operating System 2 and Raspberry Pi. ILKOM Jurnal Ilmiah, 13(1): 1–8. https://doi.org/10.33096/ilkom.v13i1.686.1-8
Desnanjaya IGMN, Arsana INA, 2021, Home Security Monitoring System with IoT-Based Raspberry Pi. Indonesian Journal of Electrical Engineering and Computer Science, 22(3): 1295–1302. https://doi.org/10.11591/ijeecs.v22.i3
Wang G, Muñoz-Ferreras J-M, Gu C, et al., 2014, Application of Linear-Frequency-Modulated Continuous-Wave (LFMCW) Radars for Tracking of Vital Signs. IEEE Transactions on Microwave Theory and Techniques, 62(6): 1387–1399. https://doi.org/10.1109/TMTT.2014.2320464
Lee H, Kim B-H, Yook J-G. 2018 IEEE Asia-Pacific Conference on Antennas and Propagation (APCAP), August 5–8, 2018: Path Loss Compensation Method for Multiple Target Vital Sign Detection with 24-GHz FMCW Radar. 2018, Auckland, 100–101. https://doi.org/10.1109/APCAP.2018.8538182
Rohling H, Kronauge M. 2014 International Radar Conference, October 13–17, 2014: New Radar Waveform Based on a Chirp Sequence. 2014, Lille, 1–4. https://doi.org/10.1109/RADAR.2014.7060246
Kronauge M, Rohlin H, 2013, Fast Two-Dimensional CFAR Procedure. IEEE Transactions on Aerospace and Electronic Systems, 49(3): 1817–1823. https://doi.org/10.1109/TAES.2013.6558022
Rohlin H, 1983, Radar CFAR Thresholding in Clutter and Multiple Target Situations. IEEE Transactions on Aerospace and Electronic Systems, AES-19(4): 608–621. https://doi.org/10.1109/TAES.1983.309350
Rohling H. 12th International Radar Symposium (IRS), September 7–9, 2011: Ordered Statistic CFAR Technique – An Overview. 2011, Leipzig, 631–638.
Zheng Q, Yang L, Xie Y, et al., Q. Zheng et al., 2021, A Target Detection Scheme with Decreased Complexity and Enhanced Performance for Range-Doppler FMCW Radar. IEEE Transactions on Instrumentation and Measurements, 70: 1–13. https://doi.org/10.1109/TIM.2020.3027407
Ester M, Kriegel H-P, Sander J, et al., 1996, A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise. Proceedings of the Second International Conference on Knowledge Discovery and Data Mining (KDD-96), 1996: 226–231.
Chauhan NS. DBSCAN Clustering Algorithm in Machine Learning. https://www.kdnuggets.com/2020/04/dbscanclustering-algorithm-machine-learning.html
Hyun E, Lee J-H. 17th International Radar Symposium (IRS), Mat 10–12, 2016: Multi-Target Tracking Scheme Using a Track Management Table for Automotive Radar Systems. 2016, Krakow, 1–5. https://doi.org/10.1109/IRS.2016.7497283
Quang HV, Kim LW, Hong CS, 2021, A Deep Learning Accelerator for a Typical Binary Neural Network Layer. KCC, 2021: 597–599.
Jang D, Kim H, Jung Y, 2020, Design and Implementation of Human-Detecting Radar System for Indoor Security Applications. Journal of Institute of Korean Electrical and Electronics Engineers, 24(3): 783–790. https://doi.org/10.7471/ikeee.2020.24.3.783
Nam J, Kang C, Kook J, et al., 2021, Design and Implementation of CW Radar-Based Human Activity Recognition System. Korea Citation Index (KCI), 25(5): 415–425.
Kong Y-J, Woo S-K, Park S, et al., 2018, OS CFAR Computation Time Reduction Technique to Apply Radar System in Real Time. The Journal of Korean Institute of Electromagnetic Engineering and Science, 29(10): 791–798. https://doi.org/10.5515/KJKIEES.2018.29.10.791
Hossain MA, Hossain MI, Hossain MD, et al., 2019, Performance Assessment of Background Subtraction Algorithm. Korea Software Congress, 2019: 1049–1051.
Infineon Technologies. DEMO-DISTANCE2GO. https://www.infineon.com/cms/en/product/evaluation-boards/demo-distance2go/
Raspberry-Pi. raspberry-pi-4-model-b. https://www.raspberrypi.com/products/raspberry-pi-4-model-b/
Terasic Technologies. DE1-SoCBoard. https://www.terasic.com.tw/cgi-bin/page/archive.pl?Language=English&No=836.