王平;丁浩;李佳丽;

• 1:南昌大学信息工程学院

摘要(Abstract)：

为了及时、准确地对老年人跌倒行为进行检测,保障老年人的养老安全,提出一种基于人体姿态的跌倒检测方法。首先将视频图像送入到OpenPose算法中获取图像中人体的姿态信息,再利用三维卷积神经网络提取视频中人体姿态变化的时空特征。通过对局部特征的重新组合,得到抽象的全局特征进行跌倒检测。实验结果表明,所提出的跌倒检测方法计算复杂度低,对跌倒行为的平均正确检测率为98.32%,对其他日常行为的平均误检率为2.84%,兼顾了准确性和实时性的要求。

关键词(KeyWords)： 跌倒检测;人体姿态;时空特征提取;局部特征重组;姿态估计;模型分析

Abstract:

Keywords:

基金项目(Foundation): 江西省科技厅科技支撑项目(20151BBG70057);; 江西省教育厅科学资助项目(GJJ14137)

作者(Author): 王平;丁浩;李佳丽;

Email:

DOI: 10.16652/j.issn.1004-373x.2021.04.021

参考文献(References)：

• [1]李文阳，马行，穆春阳.基于Kinect V2的跌倒行为检测与分析[J].现代电子技术，2019,42(6):142-145.
• [2]IGUAL R,MEDRANO C,PLAZA I.Challenges,issues and trends in fall detection systems[J].Biomedical engineering online,2013,12(1):66.
• [3]QUADROS T D,LAZZARETTI A E,SCHNEIDER F K.Amovement decomposition and machine learning-based fall detection system using wrist wearable device[J].IEEE sensors journal,2018,18(12):5082-5089.
• [4]YUN Y,GU Y H.Human fall detection in videos via boosting and fusing statistical features of appearance,shape and motion dynamics on Riemannian manifolds with applications to assisted living[J].Computer vision and image understanding,2016,148:111-122.
• [5]EL KAID A,BA?NA K,BA?NA J.Reduce false positive alerts for elderly person fall video-detection algorithm by convolutional neural network model[J].Procedia computer science,2019,148:2-11.
• [6]CAO Z,SIMON T,WEI S E,et al.Realtime multi-person 2d pose estimation using part affinity fields[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Honolulu:IEEE,2017:7291-7299.
• [7]DAI J F,HE K M,SUN J.Convolutional feature masking for joint object and stuff segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Boston:IEEE,2015:3992-4000.
• [8]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.ImageNet classification with deep convolutional neural networks[J].Communications of the ACM,2017,60(6):84-90.
• [9]JI S W,YANG M,YU K.3D convolutional neural networks for human action recognition[J].IEEE transactions on pattern analysis and machine intelligence,2012,35(1):221-231.
• [10]BIANCHINI M,SCARSELLI F.On the complexity of neural network classifiers:A comparison between shallow and deep architectures[J].IEEE transactions on neural networks and learning systems,2014,25(8):1553-1565.
• [11]SUN S Z,CHEN W,WANG L W,et al.On the depth of deep neural networks:a theoretical view[C]//Thirtieth AAAIConference on Artificial Intelligence.Phoenix,Arizona:ACM,2016:2066-2072.
• [12]SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[J].Computer science,2014(7):201-210.
• [13]TRAN D,BOURDEV L,FERGUS R,et al.Learning spatiotemporal features with 3D convolutional networks[C]//Proceedings of the IEEE International Conference on Computer Vision.Santiago:IEEE,2015:4489-4497.
• [14]AUVINET E,ROUGIER C,MEUNIER J,et al.Multiple cameras fall dataset[EB/OL].[2019-06-01].http：//www.iro.umontreal.ca/~labimage/Dataset/.
• [15]CHARFI I,MITERAN J,DUBOIS J,et al.Optimized spatiotemporal descriptors for real-time fall detection:comparison of support vector machine and Adaboost-based classification[J].Journal of electronic imaging,2013,22(4):041106.
• [16]郑娱，鲍楠，徐礼胜，等.跌倒检测系统的研究进展[J].中国医学物理学杂志，2014(4):5071-5076.
• [17]CHARFI I,MITERAN J,DUBOIS J,et al.Robust spatiooral descriptors for real-time SVM-based fall detection[C]//2014World Symposium on Computer Applications&Research.Sousse:IEEE,2014:1-6.
• [18]FAN Y,LEVINE M D,WEN G,et al.A deep neural network for real-time detection of falling humans in naturally occurring scenes[J].Neurocomputing,2017,260:43-58.
• [19]WANG S K,CHEN L,ZHOU Z,et al.Human fall detection in surveillance video based on PCANet[J].Multimedia tools and applications,2016,75(19):11603-11613.
• [20]DEBARD G,MERTENS M,DESCHODT M,et al.Camerabased fall detection using real-world versus simulated data:How far are we from the solution?[J].Journal of ambient intelligence and smart environments,2016,8(2):149-168.