A Fast Dynamic Gesture Recognition Method Based on 3D Trajectory

被引：0

作者：

He, Wei ^{[1
]}

Wang, Yong ^{[1
]}

Zhou, Mu ^{[1
]}

Xie, Liangbo ^{[1
]}

Long, Quan ^{[2
]}

Fu, Li ^{[3
]}

机构：

[1] Chongqing Univ Posts & Telecommun, Chongqing 400065, Peoples R China

[2] Chongqing Intelligence Network Technol Co LTD, Informat Commun branch, Chongqing 401120, Peoples R China

[3] State Grid Chongqing Beibei Power Supply Co, Chongqing 400700, Peoples R China

来源：

2022 IEEE 10TH ASIA-PACIFIC CONFERENCE ON ANTENNAS AND PROPAGATION, APCAP | 2022年

关键词：

FMCW; dynamic gesture; recognition; trajectory;

D O I：

10.1109/APCAP56600.2022.10069932

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

With the arrival of the 5G era, gesture recognition technology plays an important role in the smart home system. This paper adopts a Frequency Modulated Continuous Wave (FMCW) radar to design a fast gesture recognition system. Specifically, this paper proposes a dynamic gesture recognition method based on 3D trajectory, which is generated by fusing the range, angle, and time information, and corrected by class targets suppression through Doppler. Then the convolutional neural network (CNN) recognizes and classifies the dynamic gesture with the 3D trajectory. Finally, experiments are carried out to verify the effectiveness of the proposed method.

引用

页数：2

共 50 条

[31] Research on 3D face recognition method in cloud environment based on semi supervised clustering algorithm [J].

Li, Cuixia ;

Tan, Yingjun ;

Wang, Dingbiao ;

Ma, Peijie .

MULTIMEDIA TOOLS AND APPLICATIONS, 2017, 76 (16) :17055-17073

[32] Long-Term Human Trajectory Prediction Using 3D Dynamic Scene Graphs [J].

Gorlo, Nicolas ;

Schmid, Lukas ;

Carlone, Luca .

IEEE ROBOTICS AND AUTOMATION LETTERS, 2024, 9 (12) :10978-10985

[33] Dynamic Hand Gesture Recognition using 2D Convolutional Neural Network [J].

Liu, Yupeng ;

Yang, Mingqiang ;

Li, Jie ;

Zheng, Qinghe ;

Wang, Deqiang .

ENGINEERING LETTERS, 2020, 28 (01) :243-254

[34] Dynamic Pose Estimation Based on 3D Point Clouds [J].

Bo Ouyang ;

Yu, Qinghua ;

Xiao, Junhao ;

Yu, Shuijun .

2015 IEEE INTERNATIONAL CONFERENCE ON INFORMATION AND AUTOMATION, 2015, :2116-2120

[35] A fast algorithm for ICP-based 3D shape biometrics [J].

Yan, Ping ;

Bowyer, Kevin W. .

COMPUTER VISION AND IMAGE UNDERSTANDING, 2007, 107 (03) :195-202

[36] The Training Gesture Recognition and Early Warning Method Based on CNN Model [J].

Li, Guoqiang ;

Yang, Xue .

WIRELESS PERSONAL COMMUNICATIONS, 2023,

[37] 3D Object Recognition Based on Linear Lie Algebra Model [J].

李方兴 ;

吴平东 ;

孙华飞 ;

彭林玉 .

JournalofBeijingInstituteofTechnology, 2009, 18 (01) :46-50

[38] GAIT RECOGNITION BASED ON 3D HOLOSCOPIC GAIT ENERGY IMAGE [J].

Ozen, Hakan ;

Boulgouris, Nikolaos V. ;

Swash, Rafiq .

2017 INTERNATIONAL CONFERENCE ON 3D IMMERSION (IC3D), 2017,

[39] A Mine Intersection Recognition Method Based on Geometric Invariant Point Detection Using 3D Point Cloud [J].

Chen, Min ;

Feng, Yuan ;

Wang, Shigang ;

Liang, Qinghua .

IEEE ROBOTICS AND AUTOMATION LETTERS, 2022, 7 (04) :11934-11941

[40] Kernel-based representation for 2D/3D motion trajectory retrieval and classification [J].

Lin, Wei-Yang ;

Hsieh, Chung-Yang .

PATTERN RECOGNITION, 2013, 46 (03) :662-670

← 1 2 3 4 5 →