基于空间属性特征的毫米波雷达身体干扰识别

doi:10.12305/j.issn.1001-506X.2024.10.14

摘要/Abstract

摘要：

手势识别中, 身体的移动容易被误判为手势动作, 对手势识别造成干扰。因此, 针对存在的身体干扰问题, 提出了基于空间属性特征的身体干扰识别算法。在对毫米波雷达接收信号进行预处理后, 首先分别对一维距离像和二维距离角度谱提取一维潜在目标和二维潜在目标, 并对二维潜在目标进行连通域标记。然后, 基于潜在目标及连通域提取出用于区分身体干扰和手势目标的空间属性特征。最后, 采用支持向量机(support vector machine, SVM)分类器进行身体干扰识别。实验结果表明, 所提方法能有效区分身体干扰和手势目标, 单帧预测下准确率为97.3%, 多帧预测下准确率为98.94%。

关键词: 毫米波雷达, 手势识别, 身体干扰, 空间属性特征, 特征提取

Abstract:

In gesture recognition, the movement of the body is easily misjudged as a gesture action, which interferes the gesture recognition. Therefore, in view of the existing body interference problem, a body interference recognition algorithm based on spatial attribute features is proposed. After preprocessing the received signal of millimeter-wave radar, firstly, the one-dimensional potential targets and the two-dimensional potential targets are extracted from the one-dimensional range image and the two-dimensional range angle spectrum, and the connected domains are labeled for the two-dimensional potential targets. Then, based on the potential targets and the connected domains, the spatial attribute features used to distinguish between body interference and gesture targets are extracted. Finally, the support vector machine (SVM) classifier is used for body interference recognition. Experimental results show that the proposed method can effectively distinguish body interference from gesture targets, and the accuracy rate reaches 97.3% under single-frame prediction and 98.94% under multi-frame prediction.

Key words: millimeter-wave radar, gesture recognition, body interference, spatial attribute features, feature extraction

中图分类号:

TN959

蔡嘉怡, 初萍, 庄伦涛, 阳召成. 基于空间属性特征的毫米波雷达身体干扰识别[J]. 系统工程与电子技术, 2024, 46(10): 3365-3374.

Jiayi CAI, Ping CHU, Luntao ZHUANG, Zhaocheng YANG. Millimeter-wave radar body interference recognition based on spatial attribute features[J]. Systems Engineering and Electronics, 2024, 46(10): 3365-3374.

图/表 13

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

表1

表2

表3

参考文献 31

1	GURBUZ S Z, GURBUZ A C, MALAIA E A, et al. ASL recognition based on kinematics derived from a multi-frequency RF sensor network[C]//Proc. of the IEEE Sensors, 2020.
2	CHEN F Y , LYU H H , PANG Z B , et al. Wristcam: a wearable sensor for hand trajectory gesture recognition and intelligent human-robot interaction[J]. IEEE Sensors Journal, 2019, 19 (19): 8441- 8451. doi: 10.1109/JSEN.2018.2877978
3	PLESHKOVA S G, BEKVARSKI A B, ZAHARIEV Z T. Based on artificial intelligence and deep learning hand gesture recognition for interaction with mobile robots[C]//Proc. of the 10th National Conference with International Participation, 2019.
4	OHN-BAR E , TRIVEDI M M . Hand gesture recognition in real time for automotive interfaces: a multimodal vision-based approach and evaluations[J]. IEEE Trans.on Intelligent Transportation Systems, 2014, 15 (6): 2368- 2377. doi: 10.1109/TITS.2014.2337331
5	LEITE D A T Q, DUARTE J C, OLIVEIRA J C, et al. A system to interact with CAVE applications using hand gesture recognition from depth data[C]//Proc. of the 16th Symposium on Virtual and Augmented Reality, 2014: 246-253.
6	HE W F, WU K S, ZOU Y P, et al. WiG: wifi-based gesture recognition system[C]//Proc. of the 24th International Confe-rence on Computer Communication and Networks, 2015.
7	VENKATNARAYAN R H , MAHMOOD S , SHAHZAD M . Wifi based multi-user gesture recognition[J]. IEEE Trans.on Mobile Computing, 2019, 20 (3): 1242- 1256.
8	PITTMAN C, WISNIEWSKI P, BROOKS C, et al. Multiwave: Doppler effect based gesture recognition in multiple dimensions[C]//Proc. of the Conference on Human Factors in Computing Systems Conference Extended Abstracts on Human Factors in Computing Systems, 2016: 1729-1736.
9	ZHOU F F, LI X Y, WANG Z H. Efficiently user-independent ultrasonic-based gesture recognition algorithm[C]//Proc. of the IEEE Sensors, 2019.
10	江浩. 基于智能腕表的手写识别研究[D]. 上海: 上海交通大学, 2020.
	JIANG H. Research on handwriting recognition based on smart watches[D]. Shanghai: Shanghai Jiao Tong University, 2020.
11	CHOI E S, BANG W C, CHO S J, et al. Beatbox music phone: gesture-based interactive mobile phone using a tri-axis accelerometer[C]//Proc. of the IEEE International Conference on Industrial Technology, 2005: 97-102.
12	PAUDYAL P, LEE J, BANERJEE A, et al. Dyfav: dynamic feature selection and voting for real-time recognition of fingerspelled alphabet using wearables[C]//Proc. of the 22nd International Conference on Intelligent User Interfaces, 2017: 457-467.
13	RODRIGUEZ D, PIRYATINSKA A, ZHANG X. A neural decision forest scheme with application to EMG gesture classification[C]//Proc. of the Science and Information Computing Conference, 2016: 243-252.
14	LI Y , WANG X G , LIU W Y , et al. Deep attention network for joint hand gesture localization and recognition using static RGB-D images[J]. Information Sciences, 2018, 441, 66- 78. doi: 10.1016/j.ins.2018.02.024
15	施向军, 王星尧. 基于红外传感器和隐马尔可夫模型的动态手势识别[J]. 电子器件, 2018, 41 (5): 1286- 1290. doi: 10.3969/j.issn.1005-9490.2018.05.040
	SHI X J , WANG X R . Dynamic gesture recognition based on infrared sensor and hidden Markov model[J]. Chinese Journal of Electron Devices, 2018, 41 (5): 1286- 1290. doi: 10.3969/j.issn.1005-9490.2018.05.040
16	FANG B Y, CO J, ZHANG M. DeepASL: enabling ubiquitous and non-intrusive word and sentence-level sign language translation[C]//Proc. of the 15th ACM Conference on Embedded Network Sensor Systems, 2017.
17	赵爱芳, 裴东, 王全州, 等. 复杂环境中多信息融合的手势识别[J]. 计算机工程与应用, 2014, 50 (5): 180- 184. doi: 10.3778/j.issn.1002-8331.1304-0011
	ZHAO A F , PEI D , WANG Q Z , et al. Gesture recognition with multi-information fusion in complex environments[J]. Computer Engineering and Applications, 2014, 50 (5): 180- 184. doi: 10.3778/j.issn.1002-8331.1304-0011
18	LIU K, CHEN C, JAFARI R, et al. Multi-HMM classification for hand gesture recognition using two differing modality sensors[C]//Proc. of the IEEE Dallas Circuits and Systems Conference, 2014.
19	YANG Z C , ZHENG X B . Hand gesture recognition based on trajectories features and computation-efficient reused LSTM network[J]. IEEE Sensors Journal, 2021, 21 (15): 16945- 16960. doi: 10.1109/JSEN.2021.3079564
20	DAIM T J, LEE R M A. The effect of body position on IR-UWB radar sensor-based hand gesture speed recognition and classification system[C]//Proc. of the IEEE International Conference on Automatic Control and Intelligent Systems, 2022: 158-162.
21	STADELMAVER T , SANTRA A , WEIGEL R , et al. Radar-based gesture recognition using a variational autoencoder with deep statistical metric learning[J]. IEEE Trans.on Microwave Theory and Techniques, 2022, 70 (11): 5051- 5062. doi: 10.1109/TMTT.2022.3201265
22	CHOI J , PARK C , KIM J . FMCW radar-based real-time hand gesture recognition system capable of out-of-distribution detection[J]. IEEE Access, 2022, 10, 87425- 87434. doi: 10.1109/ACCESS.2022.3200757
23	AHMED S , KIM W , PARK J , et al. Radar-based air-writing gesture recognition using a novel multistream CNN approach[J]. IEEE Internet of Things Journal, 2022, 9 (23): 23869- 23880. doi: 10.1109/JIOT.2022.3189395
24	CHEN Q, LI Y W, CUI Z Y, et al. A hand gesture recognition method for mmwave radar based on angle-range joint temporal feature[C]//Proc. of the IEEE International Geoscience and Remote Sensing Symposium, 2022: 2650-2653.
25	WANG X R , LI W L , CHEN V C . Hand gesture recognition using radial and transversal dual micromotion features[J]. IEEE Trans.on Aerospace and Electronic Systems, 2022, 58 (6): 5963- 5973. doi: 10.1109/TAES.2022.3179679
26	DONG L F , MA Z X , ZHU X C . Dynamic gesture recognition network based on vehicular millimeter wave radar[J]. Transactions of Beijing Institute of Technology, 2023, 43 (5): 493- 498.
27	TONG P P, WENG C E, BI X, et al. Micro gesture recognition of the millimeter-wave radar based on multi-branch residual neural network[C]//Proc. of the SAE Intelligent and Connected Vehicles Symposium, 2022.
28	WANG Y, ZHANG J, ZHAO X C, Research on hand gesture recognition based on millimeter wave radar[C]//Proc. of the 3rd International Conference on Consumer Electronics and Computer Engineering, 2023: 205-209.
29	SHARMA R R , KUMAR K A , CHO S H . Novel time-distance parameters based hand gesture recognition system using multi-UWB radars[J]. IEEE Sensors Letters, 2023, 7 (5): 6002204.
30	YANG Z C , HUANG X Z . Cascaded regional people counting approach based on two-dimensional spatial attribute features using MIMO radar[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19, 3508005.
31	杜鹏飞, 张祥军. 单元平均恒虚警率检测中的一个新结论[J]. 现代雷达, 2007, 29 (2): 60- 62.
	DU P F , ZHANG X J . A new conclusion in CA-CFAR detection[J]. Modern Radar, 2007, 29 (2): 60- 62.

分类器	混合干扰下的准确率/%	模型大小/kB	预测时间/ms
线性判别	95.5	21	3
KNN	96.8	4 863	21
朴素贝叶斯	92.7	7	3
决策树	96.4	8	2.3
SVM	97.3	122	3

参数	手势目标+正前方身体干扰			手势目标+侧向身体干扰			手势目标+混合干扰
参数	静止状态	微动状态	运动状态	静止状态	微动状态	运动状态	手势目标+混合干扰
样本帧数	33 000	33 000	33 000	33 000	33 000	33 000	83 000
准确率/%	96.8	97.5	97.9	96.3	96.7	96.9	97.3

参数	单帧预测	多帧预测/帧
参数	单帧预测	5	10	15	20
延时/ms	0	125	250	375	500
准确率/%	97.3	98.22	98.42	98.94	99.07

[1]	张明龙, 吴雨林, 魏文强, 沈园杰, 郭世盛, 崔国龙. 基于稀疏矩阵填充的级联毫米波雷达高分辨测角方法[J]. 系统工程与电子技术, 2024, 46(8): 2629-2640.
[2]	张冬, 邢福逸, 徐允鹤, 钱鹏. 基于双模式切换的机载惯性/雷达组合导航方法[J]. 系统工程与电子技术, 2024, 46(8): 2770-2778.
[3]	汪强龙, 高晓光, 吴必聪, 胡子剑, 万开方. 受限玻尔兹曼机及其变体研究综述[J]. 系统工程与电子技术, 2024, 46(7): 2323-2345.
[4]	阳鹏飞, 何羚, 王茜, 王睿笛, 张明志. 基于混合信号多域特征和Transformer的干扰识别[J]. 系统工程与电子技术, 2024, 46(6): 2138-2145.
[5]	杨德贵, 许道峰. 基于时频域特征融合的IR-UWB穿墙雷达人体行为识别方法[J]. 系统工程与电子技术, 2024, 46(3): 849-858.
[6]	张春杰, 王冠博, 陈奇, 邓志安. 基于纯自注意力机制的毫米波雷达手势识别[J]. 系统工程与电子技术, 2024, 46(3): 859-867.
[7]	郑晶月, 吴佩仑, 陈家辉, 郭世盛, 崔国龙. 车载毫米波雷达多径假目标分析与消除方法[J]. 系统工程与电子技术, 2024, 46(1): 88-96.
[8]	赵晓枫, 牛家辉, 刘春桐, 夏玉婷. 基于三维注意力与混合卷积的高光谱图像分类[J]. 系统工程与电子技术, 2023, 45(9): 2673-2680.
[9]	方伟, 梁静雯, 陆恒杨. 基于聚类锦标赛与父代匹配的遗传规划算法[J]. 系统工程与电子技术, 2023, 45(8): 2405-2414.
[10]	王湖升, 陈伯孝, 叶倾知. 基于箔条干扰实测数据的对抗方法研究[J]. 系统工程与电子技术, 2023, 45(7): 2010-2021.
[11]	杨帆, 马萍, 李伟, 杨明. 基于孪生网络的仿真模型智能排序评估方法[J]. 系统工程与电子技术, 2023, 45(7): 2060-2068.
[12]	刘丹阳, 吴堃, 朱永锋, 张永杰, 周剑雄. 地面目标HRRP识别的稳健性特征选择方法[J]. 系统工程与电子技术, 2023, 45(12): 3726-3733.
[13]	李波, 胡哿郗, 石剑钧, 刘恒畅, 洪涛. 基于多惩罚因子优化VMD的滚动轴承故障特征提取方法[J]. 系统工程与电子技术, 2023, 45(11): 3690-3698.
[14]	刘佳, 徐群玉, 陈唯实. 无人机雷达航迹运动特征提取及组合分类方法[J]. 系统工程与电子技术, 2023, 45(10): 3122-3131.
[15]	马泽煊, 李进, 路艳丽, 陈晨. 融合WaveNet和BiGRU的网络入侵检测方法[J]. 系统工程与电子技术, 2022, 44(8): 2652-2660.