计算机科学 ›› 2020, Vol. 47 ›› Issue (6): 180-183.doi: 10.11896/jsjkx.200200030

• 计算机图形学&多媒体 • 上一篇    下一篇

基于改进多尺度深度卷积网络的手势识别算法

景雨, 祁瑞华, 刘建鑫, 刘朝霞   

  1. 大连外国语大学软件学院 辽宁 大连116044
  • 收稿日期:2020-02-05 出版日期:2020-06-15 发布日期:2020-06-10
  • 通讯作者: 景雨(jingyu0814@126.com)
  • 基金资助:
    国家自然科学基金(61501082);大连外国语大学科研基金项目(2018XJYB27);辽宁省教育厅科学研究一般项目(2019JYT01,2019JYT07);辽宁省自然科学基金项目(20180550018);辽宁省博士科研启动基金项目(2019BS061)

Gesture Recognition Algorithm Based on Improved Multiscale Deep Convolutional Neural Network

JING Yu, QI Rui-hua, LIU Jian-xin, LIU Zhao-xia   

  1. School of Software,Dalian University of Foreign Languages,Dalian,Liaoning 116044,China
  • Received:2020-02-05 Online:2020-06-15 Published:2020-06-10
  • About author:JING Yu,born in 1982,Ph.D,associate professor,is a member of China Computer Federation.Her main research interests include image processing,pattern recognition and computer vision.
  • Supported by:
    This work was supported by the National Natural Science Foundation of China(61501082),Scientific Research Fund Project of Dalian University of Foreign Languages (2018XJYB27),Scientific Research Project of Liaoning Province Educational Department (2019JYT01,2019JYT07),Natural Science Foundation Project of Liaoning Province(20180550018) and Doctoral Research Start Fund Project of Liaoning Province (2019BS061)

摘要: 基于传统的浅层学习网络由于过度依赖于人工选择手势特征,因此不能实时适应复杂多变的自然场景。在卷积神经网络架构的基础上,提出了一种改进的多尺度深度网络手势识别模型,该模型能够利用卷积层自动学习手势特征,进而除去人工提取特征的弊端。该方法引入自适应多尺度特性来实现同一卷积层不同尺寸卷积核生成不同尺度特征,并通过级联浅层和深层的特征来达到不同抽象程度的特征图融合。同时,为了增强模型的泛化能力,提出了基于正则化约束的损失函数。实验结果表明,所提网络模型的识别精度高于普通单尺度卷积神经网络结构的识别精度,弥补了提取特征不够精细、全面及稳定性欠佳等缺点,同时网络训练所需的时间并没有大幅度增加。

关键词: 多尺度, 卷积特征, 深度学习, 手势识别, 损失函数, 正则化

Abstract: Since the traditional shallow learning networks rely too much on manual selection of gesture features,they cannot adapt to complex and varied natural scenes in real time.Based on the convolutional neural network architecture,this paper proposes an improved multi-scale deep network gesture recognition model,which makes it possible to overcome the drawbacks of ma-nual extraction features by using the convolutional layer to automatically learn gesture features.In this method,the adaptive multi-scale features are introduced to realize that convolution kernels with different sizes at the same convolutional layer to gene-rate different scale features,and achieves feature map fusion with different levels by cascading shallow and deep features.In addition,in order to enhance the generalization ability of the model,this paper proposes a loss function based on regularization constraints.The experimental results show that the recognition accuracy of the proposed network model is higher than that of the ordinary single -scale convolutional neural network,and the shortcomings of imprecise and incomprehensive extraction as well as poor stability are overcome,and the time required for network training is not greatly increased.

Key words: Convolution feature, Deep learning, Gesture recognition, Loss function, Multi-scale, Regularization

中图分类号: 

  • TP391
[1]MITRA S,ACHARYA T.Gesture Recognition:A Survey[J].IEEE Transactions on Systems,Man and Cybernetics,Part C,(Applications and Reviews),2007,37(3):311-324.
[2] WU Y,HUANG T S,MATHEWS N.Vision-Based Gesture Recognition:A Review[C]//International Gesture Workshop on Gesture-based Communication in Human-computer Interaction.Springer-Verlag,1999.
[3]WANG S B,QUATTONI A,MORENCY L P,et al.HiddenConditional Random Fields for Gesture Recognition[C]//2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2006).New York:IEEE,2006.
[4]LEE H K,KIM J H.An HMM-Based Threshold Model Approach for Gesture Recognition[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,1999,21(10):961-973.
[5]BRETZNER L,LAPTEV I,LINDEBERG T.Hand Gesture Recognition using Multi-Scale Colour Features,Hierarchical Models and Particle Filtering[C]//Face and Gesture FG’02.IEEE Computer Society,2002.
[6]SUN Y,LI C,LI G,et al.Gesture Recognition Based on Kinect and sEMG Signal Fusion[J].Mobile Networks and Applications,2018,23(4):797-805.
[7]YANG L,HU G M,HUANG D F,et al.Static Gesture Recognition Algorithm of Combinating Skin Color Segmentation with ELM[J].Journal of Guangxi University(Nat Sci Ed),2015,40(2):444-450.
[8]ZHANG Q Y,WANG D D,ZHANG M Y,et al.Hand Gesture Recognition Based on Bag of Features and Support Vector Machine[J].Journal of Computer Applications,2012,32(12):3392-3396.
[9]LATORRECARMONA P,PLA F.3D human gesture recognition using integral imaging[J].Spienewsroom,2018,12(1):15-20.
[10]CORNEANU C,NOROOZI F,KAMINSKA D,et al.Survey on Emotional Body Gesture Recognition[J/OL].IEEE Transactions on Affective Computing.https://ieeexploreieee.org/document/8493586.
[11]HAO Y,BAI Y P,ZHANG X F,et al.Application of Convolution Neural Network in SAR Target Recognition[J].Journal of Chongqing University of Technology(Natural Science),2018,32(5):204-209.
[12]HUANG G,LIU Z,VAN DER MAATEN L,et al.DenselyConnected Convolutional Networks[C]//IEEE.The IEEE Conference on Computer Vision and Pattern Recognition (CPVR).Las Vegas:IEEE,2017:4700-4708.
[13]LIU W,ANGUELOV D,ERHAN D,et al.SSD:Single ShotMultiBox Detector[C]//European Conference on Computer Vision.2016:21-37.
[14]XIE S,GIRSHICK R B,DOLLAR P,et al.Aggregated Residual Transformations for Deep Neural Networks[C]//Computer Vision and Pattern Recognition.2017:5987-5995.
[15]WU,XIAO Y.A Hand Gesture Recognition Algorithm Based on DC-CNN[J].Multimedia Tools and Applications,2019:1-13.
[16]HE Y,LI G,LIAO Y,et al.Gesture Recognition Based on An Improved Local Sparse Representation Classification Algorithm[J].Cluster Computing,2019,22(10):935-946.
[17]PI S Y,TANG H,XIAO N F.Fully Convolutional Deep Lear-ning Model Based Graspable Object etection[J].Journal of Chongqing University of Technology(Natural Science),2018,32(2):166-173.
[18]LATORRECARMONA P,PLA F.3D Human Gesture Recognition Using Integral Imaging[J].Spienewsroom,2018,12(1):15-20.
[19]GUYON I,ATHITSOS V,JANGYODSUK P,et al.ChaLearn Gesture Challenge:Design and First Results[C]//Computer Vision & Pattern Recognition Workshops.2012.
[20]XIN S,HEE-SEUNG K,KOMATSU S,et al.Spatial-temporal Human Gesture Recognition Under Degraded Conditions Using Three-dimensional Integral Imaging[J].Optics Express,2018,26(11):13938.
[1] 饶志双, 贾真, 张凡, 李天瑞.
基于Key-Value关联记忆网络的知识图谱问答方法
Key-Value Relational Memory Networks for Question Answering over Knowledge Graph
计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277
[2] 汤凌韬, 王迪, 张鲁飞, 刘盛云.
基于安全多方计算和差分隐私的联邦学习方案
Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy
计算机科学, 2022, 49(9): 297-305. https://doi.org/10.11896/jsjkx.210800108
[3] 徐涌鑫, 赵俊峰, 王亚沙, 谢冰, 杨恺.
时序知识图谱表示学习
Temporal Knowledge Graph Representation Learning
计算机科学, 2022, 49(9): 162-171. https://doi.org/10.11896/jsjkx.220500204
[4] 李瑶, 李涛, 李埼钒, 梁家瑞, Ibegbu Nnamdi JULIAN, 陈俊杰, 郭浩.
基于多尺度的稀疏脑功能超网络构建及多特征融合分类研究
Construction and Multi-feature Fusion Classification Research Based on Multi-scale Sparse Brain Functional Hyper-network
计算机科学, 2022, 49(8): 257-266. https://doi.org/10.11896/jsjkx.210600094
[5] 王剑, 彭雨琦, 赵宇斐, 杨健.
基于深度学习的社交网络舆情信息抽取方法综述
Survey of Social Network Public Opinion Information Extraction Based on Deep Learning
计算机科学, 2022, 49(8): 279-293. https://doi.org/10.11896/jsjkx.220300099
[6] 王馨彤, 王璇, 孙知信.
基于多尺度记忆残差网络的网络流量异常检测模型
Network Traffic Anomaly Detection Method Based on Multi-scale Memory Residual Network
计算机科学, 2022, 49(8): 314-322. https://doi.org/10.11896/jsjkx.220200011
[7] 郝志荣, 陈龙, 黄嘉成.
面向文本分类的类别区分式通用对抗攻击方法
Class Discriminative Universal Adversarial Attack for Text Classification
计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077
[8] 姜梦函, 李邵梅, 郑洪浩, 张建朋.
基于改进位置编码的谣言检测模型
Rumor Detection Model Based on Improved Position Embedding
计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046
[9] 魏恺轩, 付莹.
基于重参数化多尺度融合网络的高效极暗光原始图像降噪
Re-parameterized Multi-scale Fusion Network for Efficient Extreme Low-light Raw Denoising
计算机科学, 2022, 49(8): 120-126. https://doi.org/10.11896/jsjkx.220200179
[10] 孙奇, 吉根林, 张杰.
基于非局部注意力生成对抗网络的视频异常事件检测方法
Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection
计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061
[11] 胡艳羽, 赵龙, 董祥军.
一种用于癌症分类的两阶段深度特征选择提取算法
Two-stage Deep Feature Selection Extraction Algorithm for Cancer Classification
计算机科学, 2022, 49(7): 73-78. https://doi.org/10.11896/jsjkx.210500092
[12] 程成, 降爱莲.
基于多路径特征提取的实时语义分割方法
Real-time Semantic Segmentation Method Based on Multi-path Feature Extraction
计算机科学, 2022, 49(7): 120-126. https://doi.org/10.11896/jsjkx.210500157
[13] 孟月波, 穆思蓉, 刘光辉, 徐胜军, 韩九强.
基于向量注意力机制GoogLeNet-GMP的行人重识别方法
Person Re-identification Method Based on GoogLeNet-GMP Based on Vector Attention Mechanism
计算机科学, 2022, 49(7): 142-147. https://doi.org/10.11896/jsjkx.210600198
[14] 侯钰涛, 阿布都克力木·阿布力孜, 哈里旦木·阿布都克里木.
中文预训练模型研究进展
Advances in Chinese Pre-training Models
计算机科学, 2022, 49(7): 148-163. https://doi.org/10.11896/jsjkx.211200018
[15] 周慧, 施皓晨, 屠要峰, 黄圣君.
基于主动采样的深度鲁棒神经网络学习
Robust Deep Neural Network Learning Based on Active Sampling
计算机科学, 2022, 49(7): 164-169. https://doi.org/10.11896/jsjkx.210600044
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!