基于CNN的人体姿态识别
|
摘要
姿态识别是人机交互中重要的研究课题之一,随着机器学习与神经网络的发展,研究的方式和成果趋于多样化,姿态识别的应用价值也日趋广泛。本文通过构建卷积神经网络模型,该模型共有11层,在对采样的数据集中5种人体姿态进行卷积与池化操作,最后进入全连接层进行分类,从而完成对数据集的训练和识别。结果显示,相较于机器学习方法,该模型的识别性能更加优秀,且免去了复杂的特征提取方式设计,让网络自身提取特征进行识别分类,效果更好。
Human posture recognition is one of the important research topics in human-computer interaction. With the development of machine learning and neural networks,the research methods and results tend to be diversified,and the application value of gesture recognition is becoming more and more extensive. This paper constructs a convolutional neural network model,which has 11 layers. It convolves and pools five kinds of human poses in the sampled data set,and finally enters the fully connected layer for classification,thus completing the training and identification of the data set. The results show that compared with the machine learning method,the recognition performance of the model is more excellent,and the complex feature extraction mode design is eliminated,so that the network itself extracts features to identify and classify better.
Human posture recognition is one of the important research topics in human-computer interaction. With the development of machine learning and neural networks,the research methods and results tend to be diversified,and the application value of gesture recognition is becoming more and more extensive. This paper constructs a convolutional neural network model,which has 11 layers. It convolves and pools five kinds of human poses in the sampled data set,and finally enters the fully connected layer for classification,thus completing the training and identification of the data set. The results show that compared with the machine learning method,the recognition performance of the model is more excellent,and the complex feature extraction mode design is eliminated,so that the network itself extracts features to identify and classify better.
引文
[1]代西果.基于卷积神经网络的人体姿态识别研究[D].成都:成都理工大学,2017.
[2]李瑞峰,王亮亮,王珂.人体动作行为识别研究综述[J].模式识别与人工智能,2014,27(1):35-48.
[3]邓甜甜,王智灵,朱明清,等.基于轮廓图像空频域特征的人体姿态分层识别算法[J].模式识别与人工智能,2011,24(3):411-416.
[4]谢非,徐贵力.基于支持向量机的多种人体姿态识别[J].重庆工学院学报(自然科学版),2009,23(3):138-143.
[5]陈先昌.基于卷积神经网络的深度学习算法与应用研究[D].杭州:浙江工商大学,2014.
[6]冯健颖.基于卷积神经网络的人体姿态估计研究[D].哈尔滨:哈尔滨工业大学,2018.
[7] SZEGEDY C,VANHOUCKE V,IOFFE S,et al. Rethinking the inception architecture for computer vision[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. 2016:2818-2826.
[8] SZEGEDY C,LIU W,JIA Y Q,et al. Going deeper with convolutions[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. 2015:1-9.
[9] HE K M,ZHANG X Y,REN S Q,et al. Deep residual learning for image recognition[C]//Proceeding of the2016 IEEE Conference on Computer Vision and Pattern Recognition. 2016:770-778.
[10] SZEGEDY C,IOFFE S,VANHOUCKE V,et al. Inception-v4,Inception-ResNet and the Impact of Residual Connections on Learning[DB/OL].(2016-08-23). https://arxiv. org/pdf/1602. 07261. pdf.
[11] NEWELL A,YANG K Y,DENG J. Stacked Hourglass Networks for Human Pose Estimation[DB/OL].(2016-07-26). https://arxiv. org/pdf/1603. 06937. pdf.
[12]邱雨.基于静态图像的人体姿态估计研究[D].成都:电子科技大学,2018.
[13]张铮,王顺帆,董雷.基于深度学习的验证码识别[J].湖北工业大学学报,2018,33(2):5-8.
[14]吴芳.基于深度学习的二进制程序漏洞分析与检测方法研究[D].北京:北京交通大学,2018.
[15]朱众志.英文动词语义误用检测研究[D].北京:北京交通大学,2017.
[16] SHOTTON J,FITZGIBBON A,COOK M,et al. Real-time human pose recognition in parts from single depth images[C]//Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition. 2011:1297-1304.
[17]陈蔚.经验模态分解及深度信念网络在语音识别中的应用研究[D].杭州:浙江理工大学,2015.
[18]张俊,李鑫. Tensor Flow平台下的手写字符识别[J].电脑知识与技术,2016,12(16):199-201.
[19]曹大有,胥帅.基于Tensor Flow预训练模型快速、精准的图像分类器[J].汉江师范学院学报,2017,37(3):27-32.
[20]周博翔,李平,李莲.改进随机森林及其在人体姿态识别中的应用[J].计算机工程与应用,2015,51(16):86-92.
[21] SCHULDT C,LAPTEV I,CAPUTO B. Recognizing human actions:A local SVM approach[C]//Proceedings of the 17th International Conference on Pattern Recognition.2004,3:32-36.
[22]郑莉莉,黄鲜萍,梁荣华.基于支持向量机的人体姿态识别[J].浙江工业大学学报,2012,40(6):670-675.
[23]林海波,王浩,张毅.改进高斯核函数的人体姿态分析与识别[J].智能系统学报,2015,10(3):436-441.
[2]李瑞峰,王亮亮,王珂.人体动作行为识别研究综述[J].模式识别与人工智能,2014,27(1):35-48.
[3]邓甜甜,王智灵,朱明清,等.基于轮廓图像空频域特征的人体姿态分层识别算法[J].模式识别与人工智能,2011,24(3):411-416.
[4]谢非,徐贵力.基于支持向量机的多种人体姿态识别[J].重庆工学院学报(自然科学版),2009,23(3):138-143.
[5]陈先昌.基于卷积神经网络的深度学习算法与应用研究[D].杭州:浙江工商大学,2014.
[6]冯健颖.基于卷积神经网络的人体姿态估计研究[D].哈尔滨:哈尔滨工业大学,2018.
[7] SZEGEDY C,VANHOUCKE V,IOFFE S,et al. Rethinking the inception architecture for computer vision[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. 2016:2818-2826.
[8] SZEGEDY C,LIU W,JIA Y Q,et al. Going deeper with convolutions[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. 2015:1-9.
[9] HE K M,ZHANG X Y,REN S Q,et al. Deep residual learning for image recognition[C]//Proceeding of the2016 IEEE Conference on Computer Vision and Pattern Recognition. 2016:770-778.
[10] SZEGEDY C,IOFFE S,VANHOUCKE V,et al. Inception-v4,Inception-ResNet and the Impact of Residual Connections on Learning[DB/OL].(2016-08-23). https://arxiv. org/pdf/1602. 07261. pdf.
[11] NEWELL A,YANG K Y,DENG J. Stacked Hourglass Networks for Human Pose Estimation[DB/OL].(2016-07-26). https://arxiv. org/pdf/1603. 06937. pdf.
[12]邱雨.基于静态图像的人体姿态估计研究[D].成都:电子科技大学,2018.
[13]张铮,王顺帆,董雷.基于深度学习的验证码识别[J].湖北工业大学学报,2018,33(2):5-8.
[14]吴芳.基于深度学习的二进制程序漏洞分析与检测方法研究[D].北京:北京交通大学,2018.
[15]朱众志.英文动词语义误用检测研究[D].北京:北京交通大学,2017.
[16] SHOTTON J,FITZGIBBON A,COOK M,et al. Real-time human pose recognition in parts from single depth images[C]//Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition. 2011:1297-1304.
[17]陈蔚.经验模态分解及深度信念网络在语音识别中的应用研究[D].杭州:浙江理工大学,2015.
[18]张俊,李鑫. Tensor Flow平台下的手写字符识别[J].电脑知识与技术,2016,12(16):199-201.
[19]曹大有,胥帅.基于Tensor Flow预训练模型快速、精准的图像分类器[J].汉江师范学院学报,2017,37(3):27-32.
[20]周博翔,李平,李莲.改进随机森林及其在人体姿态识别中的应用[J].计算机工程与应用,2015,51(16):86-92.
[21] SCHULDT C,LAPTEV I,CAPUTO B. Recognizing human actions:A local SVM approach[C]//Proceedings of the 17th International Conference on Pattern Recognition.2004,3:32-36.
[22]郑莉莉,黄鲜萍,梁荣华.基于支持向量机的人体姿态识别[J].浙江工业大学学报,2012,40(6):670-675.
[23]林海波,王浩,张毅.改进高斯核函数的人体姿态分析与识别[J].智能系统学报,2015,10(3):436-441.