基于FMCW毫米波雷达的驾驶员头手动作识别
Driver’s Head-Hand Action Recognition Based on FMCW Millimeter-Wave Radar
摘要: 随着经济水平上升，汽车逐渐成为人们出行的主要选择之一。车内驾驶员的驾驶状态是影响行驶安全的重要因素，而当前的基于视觉识别的驾驶员动作和状态检测易受光照和遮挡等问题影响，且涉及用户隐私问题。毫米波雷达具有高探测精度，高集成、不受光线等因素影响、低成本等优点，已经广泛应用与体征信号、动作识别等领域，但目前对于驾驶姿态的动作识别种类较少。为此，本文基于77 GHz毫米波雷达，对驾驶员在车内动作进行信号采集，构建了包含静止、点头、左右环视、顿头(瞌睡)、前后剧烈晃动(急刹)、手部平移(抽烟)、手部抬起(打电话)七种动作的数据集。同时开发了基于VGG16-LSTM-CBAM的深度学习网络模型，对微多普勒频谱图进行分类识别。实验结果显示，本文提出的模型识别准确率达到99.16%，有效地提高了对驾驶员头手协同动作的识别精度。
Abstract: As the economic level rises, automobile gradually becomes one of the main choices for people’s traveling. The driving status of the driver in the car is an important factor that affects driving safety, and the current visual recognition-based driver action and status detection is susceptible to problems such as light and occlusion, and involves user privacy issues. Millimeter-wave radar has the advantages of high detection accuracy, high integration, insensitivity to light and other factors, and low cost, and thus has been widely used in the fields of body signals and action recognition. However, for recognition of driver’s postures, existing studies are limited to only a few actions. In this paper, using a 77 GHz millimeter wave radar, we constructed a dataset containing seven kinds of driver’s actions, including stationary, nodding head, left and right looking around, head-stopping (dozing), front and rear violent shaking (sharp braking), hand panning (smoking), hand lifting (phone call). A deep learning network model based on VGG16-LSTM-CBAM is also developed to classify and recognize micro-Doppler spectrograms. The experimental results show that the recognition accuracy of the proposed model reaches 99.16%, which effectively improves the recognition accuracy of driver actions.
文章引用：张连龙, 刁寅亮. 基于FMCW毫米波雷达的驾驶员头手动作识别[J]. 人工智能与机器人研究, 2025, 14(2): 461-470. https://doi.org/10.12677/AIRR.2025.142045

参考文献

[1] 陈婉. 《2019中国主要城市交通分析报告》发布城市交通呈现向好趋势[J]. 环境经济, 2020(6): 48-51.
[2] 徐佩玉. 高阶智驾正走向大众化[N]. 人民日报海外版, 2024-09-11(011).
[3] 陈妍妍, 田大新, 林椿眄, 等. 端到端自动驾驶系统研究综述[J]. 中国图象图形学报, 2024, 29(11): 3216-3237.
[4] 蔡婷，孙云霞. 智慧驾驶应用场景下的新能源汽车导航交互设计策略[J]. 汽车与新动力, 2024, 7(2): 28-31.
[5] 穆高原. 基于深度学习的危险驾驶行为识别研究[D]: [硕士学位论文]. 杭州: 杭州电子科技大学, 2020.
[6] 王子睿. 基于视频的驾驶员行为检测方法研究[D]: [硕士学位论文]. 北京: 华北电力大学, 2022.
[7] 刘玉焘. 基于可穿戴式传感器的人体动作捕获与识别研究[D]: [博士学位论文]. 哈尔滨: 哈尔滨工业大学, 2020.
[8] 熊群芳, 林军, 岳伟, 等. 基于深度学习的驾驶员打电话行为检测方法[J]. 控制与信息技术, 2019(6): 53-56, 62.
[9] 陈思佳, 罗志增. 基于长短时记忆和卷积神经网络的手势肌电识别研究[J]. 仪器仪表学报, 2021, 42(2): 162-170.
[10] 秦康, 张小俊, 张明路, 等. 基于3DCNN的驾驶员细微动作识别[J]. 电子测量技术, 2023, 46(8): 51-58.
[11] 李春贺, 陶帅. 基于多模态信息联合判断的驾驶员危险行为监测系统[J]. 科学技术与工程, 2021, 21(21): 9012-9019.
[12] Liu, J., Tang, Z., Sun, N., Han, G. and Kwong, S. (2020) Visual Privacy-Preserving Level Evaluation for Multilayer Compressed Sensing Model Using Contrast and Salient Structural Features. Signal Processing: Image Communication, 89, Article 115996. [Google Scholar] [CrossRef] 
[13] Lara, O.D. and Labrador, M.A. (2013) A Survey on Human Activity Recognition Using Wearable Sensors. IEEE Communications Surveys & Tutorials, 15, 1192-1209. [Google Scholar] [CrossRef] 
[14] Ali, A., Parida, P., Va, V., Ni, S., Nguyen, K.N., Ng, B.L., et al. (2022) End-to-End Dynamic Gesture Recognition Using Mmwave Radar. IEEE Access, 10, 88692-88706. [Google Scholar] [CrossRef] 
[15] Govindaraj, V. (2021) Forward Collision Warning System with Visual Distraction Detection in Bikes. University of Twente.
[16] Bresnahan, D.G., Koziol, S. and Li, Y. (2024) Investigation of Patellar Deep Tendon Reflex Using Millimeter-Wave Radar and Motion Capture Technologies. IEEE Access, 12, 9220-9228. [Google Scholar] [CrossRef] 
[17] Arsalan, M., Santra, A. and Issakov, V. (2022) Radarsnn: A Resource Efficient Gesture Sensing System Based on Mm-Wave Radar. IEEE Transactions on Microwave Theory and Techniques, 70, 2451-2461. [Google Scholar] [CrossRef] 
[18] Arab, H., Ghaffari, I., Chioukh, L., Tatu, S.O. and Dufour, S. (2022) A Convolutional Neural Network for Human Motion Recognition and Classification Using a Millimeter-Wave Doppler Radar. IEEE Sensors Journal, 22, 4494-4502. [Google Scholar] [CrossRef] 
[19] Gharamohammadi, A., Khajepour, A. and Shaker, G. (2023) In-Vehicle Monitoring by Radar: A Review. IEEE Sensors Journal, 23, 25650-25672. [Google Scholar] [CrossRef] 
[20] Nguyen, H.N., Lee, S., Nguyen, T. and Kim, Y. (2022) One‐Shot Learning‐Based Driver’s Head Movement Identification Using a Millimetre‐Wave Radar Sensor. IET Radar, Sonar & Navigation, 16, 825-836. [Google Scholar] [CrossRef] 
[21] Chen, H., Han, X., Hao, Z., Yan, H. and Yang, J. (2023) Non-Contact Monitoring of Fatigue Driving Using FMCW Millimeter Wave Radar. ACM Transactions on Internet of Things, 5, 1-18. [Google Scholar] [CrossRef] 
[22] Chae, R., Wang, A. and Li, C. (2019) FMCW Radar Driver Head Motion Monitoring Based on Doppler Spectrogram and Range-Doppler Evolution. 2019 IEEE Topical Conference on Wireless Sensors and Sensor Networks (WiSNet), Orlando, 20-23 January 2019, 1-4. [Google Scholar] [CrossRef] 
[23] Jung, J., Lim, S., Kim, B. and Lee, S. (2021) CNN-Based Driver Monitoring Using Millimeter-Wave Radar Sensor. IEEE Sensors Letters, 5, 1-4. [Google Scholar] [CrossRef] 
[24] Bresnahan, D.G. and Li, Y. (2021) Classification of Driver Head Motions Using a mm-Wave FMCW Radar and Deep Convolutional Neural Network. IEEE Access, 9, 100472-100479. [Google Scholar] [CrossRef] 
[25] 陈爱武. 微多普勒效应分析与应用研究[D]: [硕士学位论文]. 南京: 南京理工大学, 2007.
[26] Simonyan, K. and Zisserman, A. (2014) Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv: 1409. 1556. [Google Scholar] [CrossRef] 
[27] 杨巨成, 魏峰, 林亮, 等. 驾驶员疲劳驾驶检测研究综述[J]. 山东大学学报(工学版), 2024, 54(2): 1-12.

为你推荐