基于时空图神经网络的手势识别
Spatial-Temporal Graph Neural Network based Hand Gesture Recognition
查看参考文献29篇
|
文摘
|
随着感知计算以及传感器集成技术的发展,使用各种传感设备实时捕捉的手势运动数据,为人机交互提供了新的驱动力,并被广泛地应用于智能家居、远程医疗、虚拟现实等领域.由于手势动作具有时序性与空间连接性,因此在手势识别中需要考虑手势空间连接关系和手势长距离依赖特性.然而现有的手势识别方法忽略了上述两种特性,导致识别精度不高.本文提出了基于时空图神经网络的手势识别算法,该方法从传感器空间分布角度出发,基于传感器的空间位置信息,借助图神经网络(Graph Neural Networks,GNN)对手势数据之间的空间关联性进行表征,并引入门控循环单元(Gated Recurrent Unit,GRU)解决手势的时序性和长距离依赖问题,增强手势识别性能.在多种数据集上的实验结果证明本文方法可行且有效. |
|
其他语种文摘
|
With the development of perceptual computing and sensor integration technology, hand gesture motion data collected by various sensor devices provides a new data-driven way for human-computer interaction, and widely used in smart home, telemedicine, virtual reality and other fields. Due to hand gestures have temporality and spatial connectivity, it is necessary to consider spatial connection and long-distance dependence of hand gesture in gesture recognition. However, existing hand gesture recognition models ignore the aforementioned two problems, resulting in low recognition accuracy. Therefore, we propose a spatial-temporal graph neural network based hand gesture recognition model(STGNN-HGR). From the perspective of spatial distribution of sensors, based on the spatial location information of sensors, the model represents spatial correlation of hand gesture data with the help of graph neural networks(GNN), and introduces gated recurrent unit(GRU)to solve temporality and long-distance dependence in dynamic hand gestures, so as to enhance the performance of gesture recognition. The experimental results on a variety of datasets show that our model is feasible and effective. |
|
来源
|
电子学报
,2022,50(4):921-931 【核心库】
|
|
DOI
|
10.12263/DZXB.20211069
|
|
关键词
|
手势识别
;
多传感器融合
;
时空图神经网络
;
循环神经网络
|
|
地址
|
1.
矿山数字化教育部工程研究中心, 矿山数字化教育部工程研究中心, 江苏, 徐州, 221116
2.
(徐州)中国矿业大学计算机科学与技术学院, 江苏, 徐州, 221116
3.
(徐州)中国矿业大学信息与控制工程学院, 江苏, 徐州, 221116
|
|
语种
|
中文 |
|
文献类型
|
研究性论文 |
|
ISSN
|
0372-2112 |
|
学科
|
自动化技术、计算机技术 |
|
基金
|
国家自然科学基金
;
中国博士后科学基金
|
|
文献收藏号
|
CSCD:7190618
|
参考文献 共
29
共2页
|
|
1.
李艳德.
基于穿戴传感感知的手势识别模型与应用研究,2019
|
CSCD被引
1
次
|
|
|
|
|
2.
王勇. 基于FMCW雷达的双流融合神经网络手势识别方法.
电子学报,2019,47(7):1408-1415
|
CSCD被引
10
次
|
|
|
|
|
3.
冯志全. 结合手势二进制编码和类-Hausdorff距离的手势识别.
电子学报,2017,45(9):2281-2291
|
CSCD被引
3
次
|
|
|
|
|
4.
Kim M. A study on immersion and presence of a portable hand haptic system for immersive virtual reality.
Sensors,2017,17(5):1141-1158
|
CSCD被引
2
次
|
|
|
|
|
5.
Li R Q. MHealth: A smartphone-controlled, wearable platform for tumour treatment.
Materials Today,2020,40(11):91-100
|
CSCD被引
1
次
|
|
|
|
|
6.
Ison M. High-density electromyography and motor skill learning for robust long-term control of a 7-DoF robot arm.
IEEE Transactions on Neural Systems and Rehabilitation Engineering,2015,24(4):424-433
|
CSCD被引
2
次
|
|
|
|
|
7.
Fang B. A novel data glove using inertial and magnetic sensors for motion capture and robotic arm-hand teleoperation.
Industrial Robot: An International Journal,2017,44(2):155-165
|
CSCD被引
3
次
|
|
|
|
|
8.
Chou P H. Development of a smart home system based on multi-sensor data fusion technology.
Proceedings of IEEE International Conference on Applied System Innovation,2017:690-693
|
CSCD被引
1
次
|
|
|
|
|
9.
Ma B. Combat gesture classification using through-the-wall radar based on multi-domain features association.
Proceedings of IEEE Radar Conference,2020:1-5
|
CSCD被引
1
次
|
|
|
|
|
10.
李愚. 基于增量自适应学习的在线肌电手势识别.
计算机科学,2019,46(4):274-279
|
CSCD被引
1
次
|
|
|
|
|
11.
陈国良. 基于多特征HMM融合的复杂动态手势识别.
华中科技大学学报(自然科学版),2018,46(12):42-47
|
CSCD被引
2
次
|
|
|
|
|
12.
Chen W. Hand gesture recognition using sEMG signals based on support vector machine.
Proceedings of the 8th Joint International Information Technology and Artificial Intelligence Conference,2019:230-234
|
CSCD被引
1
次
|
|
|
|
|
13.
Kumar P. Coupled HMMbased multi-sensor data fusion for sign language recognition.
Pattern Recognition Letters,2017,86(1):1-8
|
CSCD被引
3
次
|
|
|
|
|
14.
Purushothaman A. Development of smart home using gesture recognition for elderly and disabled.
Journal of Computational and Theoretical Nanoscience,2020,17(1):177-181
|
CSCD被引
1
次
|
|
|
|
|
15.
Chen L. Hand gesture recognition using compact CNN via surface electromyography signals.
Sensors,2020,20(3):672-680
|
CSCD被引
7
次
|
|
|
|
|
16.
Shin S. Skeleton-based dynamic hand gesture recognition using a part-based gru-rnn for gesturebased interface.
IEEE Access,2020,8(3):50236-50243
|
CSCD被引
2
次
|
|
|
|
|
17.
Chen Y. Graph convolutional network with structure pooling and joint-wise channel attention for action recognition.
Pattern Recognition,2020,103(7):107321-103731
|
CSCD被引
2
次
|
|
|
|
|
18.
Nunez J C. Convolutional neural networks and long short-term memory for skeleton-based human activity and hand gesture recognition.
Pattern Recognition,2018,76(4):80-94
|
CSCD被引
15
次
|
|
|
|
|
19.
Chen H. A hybrid cnn-svm classifier for hand gesture recognition with surface emg signals.
Proceedings of the 17th International Conference on Machine Learning and Cybernetics,2018:619-624
|
CSCD被引
1
次
|
|
|
|
|
20.
刘肖. 基于自适应多分类器融合的手势识别.
计算机科学,2020,47(7):103-110
|
CSCD被引
2
次
|
|
|
|
|
了解气象卫星更多信息，请访问