计算机科学 ›› 2024, Vol. 51 ›› Issue (2): 182-188.doi: 10.11896/jsjkx.230400184
张宏旺, 周瑞, 程宇, 刘辰旭
ZHANG Hongwang, ZHOU Rui, CHENG Yu, LIU Chenxu
摘要: 毫米波雷达能够用于各种感知任务,如活动识别、手势识别、心率感知等。手势识别作为其中的研究热点,可实现无接触人机交互。目前大多数手势识别研究使用点云或距离多普勒图通过神经网络进行识别感知,但是这些方法存在一些问题。首先,这些方法鲁棒性较差,被感知人员或其位置发生变化都会影响接收到的毫米波信号,降低感知精度。其次,这些方法将完整的距离多普勒图输入神经网络进行识别,由于图中存在较多与感知任务无关的区域,模型复杂且难以专注于感知任务。为解决这些问题,首先从连续多帧点云数据中建立手势轨迹,然后将连续多帧距离多普勒图进行局部切割并压缩获得二维局部多普勒图,最后将点云轨迹和二维局部多普勒图分别经过神经网络特征提取后,对特征进行拼接,通过全连接神经网络进行分类。实验结果表明,所提方法专注于手势,能够达到98%的识别准确率,在人员变化和位置变化情况下对新用户和在新位置的识别准确率分别能够达到93%和92%,高于现有方法。
中图分类号:
[1]SHU Y,WANG Y,YANG X.et al.An improved denoisingmethod for eye blink detection using automotive millimeter wave radar[J/OL].EURASIP J.Adv.Signal Process.2022,9.https://asp-eurasipjournals.springeropen.com/articles/10.1186/s13634-022-00841-y. [2]ZHAO P,LU C,WANG B,et al.Heart Rate Sensing with a Robot Mounted mmWave Radar[C]//IEEE International Confe-rence on Robotics and Automation.2020:2812-2818. [3]LING Z,ZHOU W,REN Y.Non-Contact Heart Rate Monitoring Based on Millimeter Wave Radar[J].IEEE Access,2022,10:74033-74044. [4]ZHAO P,LU X,WANG J,et al.Human tracking and identification through a millimeter wave radar[J].Ad Hoc Networks,2021,116(5):102475.1-102475.11. [5]WANG S,SONG J,LIEN J,et al,Interacting with soli:Exploring fine-grained dynamic gesture recognition in the radio-frequency spectrum[C]//Proceedings of 29th Annual ACM Symposium on User Interface Software and Technology.2016:851-860. [6]LIU H,DONG Z,SUN Y,et al.M-Gesture:Person-Independent Real-Time In-Air Gesture Recognition Using Commodity Millimeter Wave Radar[J].IEEE Internet of Things Journal,2022,9(5):3397-3415. [7]LIU H,WANG Y,ZHOU A,et al.Real-time Arm Gesture Re-cognition in Smart Home Scenarios via Millimeter Wave Sensing[C]//Proceedings of ACM on Interactive,Mobile,Wearable and Ubiquitous Technology.2020. [8]WEI H,LI Z,GALVAN A,et al.IndexPen:Two-Finger TextInput with Millimeter-Wave Radar[C]//Proceedings of ACM Interactive,Mobile,Wearable and Ubiquitous Technology.2022. [9]SINGH L,YOU S,JEONG B J,et al.Remote Estimation ofBlood Pressure Using Millimeter-Wave Frequency-Modulated Continuous-Wave Radar[J].Sensors,2023,23(14):6517. [10]MAOW,HE J,QIU L.CAT:High-precision acoustic motion tracking[C]//Proceedings of the 22nd Annual International Conference on Mobile Computing and Networking.2016:69-81. [11]WATANABE H,TERADA T.Improving ultrasound-based gesture recognition using a partially shielded single microphone[C]//Proceedings of the 2018 ACM International Symposium on Wearable Computers.2018:9-16. [12]GAO R,ZHANG M,ZHANG J,et al.Towards Position-Independent Sensing for Gesture Recognition with Wi-Fi[J].Proceedings of the ACM on Interactive,Mobile,Wearable and Ubiquitous Technologies,2021,5(2):1-28. [13]XIAO R,LIU J,HAN J,et al.OneFi:One-Shot Recognition for Unseen Gesture via COTS WiFi[C]//Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems.2021:206-219. [14]DOAN H G,VU H,TRAN T H.Recognition of hand gestures from cyclic hand movements using spatial-temporal features[C]//Proceedings of the 6th International Symposium on Information and Communication Technology.2015:260-267. [15]PIGOU L,VAN DEN OORD A,DIELEMAN S,et al.Beyond temporal pooling:Recurrence and temporal convolutions for gesture recognition in video[C]//International Journal of Computer Vision.2018:430-439. [16]ZHAO W,WANG T,TAN A.Nighttime Pedestrian Detection Based on a Fusion of Visual Information and Millimeter-Wave Radar[J].IEEE Access,2023,11:68439-68451. [17]XIA Z,DING G,WANG H.Person Identification With Millimeter-Wave Radar in Realistic Smart Home Scenarios[J].IEEE Geoscience and Remote Sensing Letters,2022,19:1-5. [18]GAO Z,ALI L,WANG C.Real-Time Non-Contact MillimeterWave Radar-Based Vital Sign Detection[J].Sensors,2022,22(19):7560. [19]ZHANG Y,PENG L.Dynamic Gesture Recognition ModelBased on Millimeter-Wave Radar With ResNet-18 and LSTM [J].Frontiers in Neurorobotics,2022,16:903197. |
|