2022年 01期

摘要(Abstract)：

利用远红外光谱视频进行老人摔倒检测研究,提出一种基于人体骨架模型的远红外视频下老人摔倒检测算法;采用YOLOv4-Tiny算法获取远红外视频中人体目标位置,再利用COCO数据集训练的区域多人姿态估计网络模型,直接对自采集的远红外视频进行人体骨架提取,得到人体关节点序列,然后对人体骨架建立时空图卷积模型进行特征提取进而检测摔倒行为,并在自采集的远红外与可见光数据集中进行算法测试。结果表明,该算法对远红外数据集的摔倒检测准确率为87.71%,验证了算法对远红外视频下摔倒行为检测的有效性。

关键词(KeyWords)： 老人摔倒检测;远红外视频;人体骨架模型;时空图卷积模型

基金项目(Foundation): 山东省重点研发计划项目(2017CXGC0810);; 山东省高等学校科技计划项目(J18KA371)

作者(Author): 王保栋 ,江鹏飞 ,董子昊 ,李金屏

DOI: 10.13349/j.cnki.jdxbn.20210901.007

参考文献(References)：

[1] LIGHT J,CHA S,CHOWDHURY M.Optimizing pressure sensor array data for a smart-shoe fall monitoring system[C]//2015 IEEE SENSORS,November 1-4,2015,Busan,South Korea.New York:IEEE,2015:1-4.

[2] 陈天华，张小驰，许继平，等.基于三轴加速度传感器和电子罗盘的人体摔倒监测系统[J].测控技术，2015,34(2):16-19.

[3] JEFIZA A,PRAMUNANTO E,BOEDINOEGROHO H,et al.Fall detection based on accelerometer and gyroscope using back propagation[C]//2017 4th International Conference on Electrical Engineering,Computer Science and Informatics (EECSI),September 19-21,2017,Yogyakarta,Indonesia.New York:IEEE,2017:1-6.

[4] 蒋宁，杜玉晓.基于惯性传感器的穿戴式跌倒检测系统设计[J].电子世界，2016(5):147-149.

[5] KHAN S S,HOEY J.Review of fall detection techniques:a data availability perspective[J].Medical Engineering & Physics,2017,39:12-22.

[6] MAHFUZ S,ISAH H,ZULKERNINE F,et al.Detecting irregular patterns in IoT streaming data for fall detection[C]//2018 IEEE 9th Annual Information Technology,Electronics and Mobile Communication Conference (IEMCON),November 1-3,2018,Vancouver,Canada.New York:IEEE,2018:588-594.

[7] FAN X,ZHANG H,LEUNG C,et al.Robust unobtrusive fall detection using infrared array sensors[C]//2017 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI),November 16-18,2017,Daegu,South Korea.New York:IEEE,2017:194-199.

[8] FAN X,ZHANG H,LEUNG C,et al.Fall detection with unobtrusive infrared array sensors[C]//LEE S,KO H,OH S.Multisensor Fusion and Integration in the Wake of Big Data,Deep Learning and Cyber Physical System.Cham,Switzerland:Springer,2017:253-267.

[9] SHAO S,WOO J,YAMAMOTO K,et al.Elderly health care system based on high precision vibration sensor[C]//2019 International Conference on Machine Learning and Cybernetics (ICMLC),July 7-10,2019,Kobe,Japan.New York:IEEE,2019:1-6.

[10] 赵斌，鲍天龙，朱明.基于图像语义分割和CNN模型的老人跌倒检测[J].计算机系统应用，2017,26(10):213-218.

[11] 王君泽，朱小龙，瞿畅.基于Kinect骨架追踪的人体摔倒自动检测[J].上海交通大学学报，2015,49(9):1359-1365.

[12] 吴沛佶，梅雪，何毅，等.基于深度网络模型的视频序列中异常行为的检测方法[J].激光与光电子学进展，2019,56(13):131101.

[13] SIMONYAN K,ZISSERMAN A.Two-stream convolutional networks for action recognition in videos[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems,December 8-13,2014,Montreal,Canda.Cambridge,USA:MIT Press,2014:568-576.

[14] TRAN D,BOURDEV L,FERGUS R,et al.Learning spatiotemporal features with 3D convolutional networks[C]//2015 IEEE International Conference on Computer Vision,December 7-13,2015,Santiago,Chile.New York:IEEE,2015:4489-4497.

[15] WANG L,XIONG Y,WANG Z,et al.Temporal segment networks:towards good practices for deep action recognition[C]//LEIBE B,MATAS J,SEBE N,et al.Computer Vision:ECCV 2016.Cham,Switzerland:Springer,2016:20-36.

[16] QIU Z,YAO T,MEI T.Learning spatio-temporal representation with pseudo-3D residual networks[C]//2017 IEEE International Conference on Computer Vision(ICCV),October 22-29,2017,Venice,Italy.New York:IEEE,2017:5533-5541.

[17] YAN S,XIONG Y,LIN D,et al.Spatial temporal graph convolutional networks for skeleton-based action recognition [EB/OL].(2020-02-13)[2021-02-18].https://arxiv.org/pdf/1801.07455.pdf

[18] LI M,CHEN S,CHEN X,et al.Actional-structural graph con-volutional networks for skeleton-based action recognition[C]//2019 IEEE Conference on Computer Vision and Pattern Recognition,June 15-20,2019,Long Beach,CA,USA.New York:IEEE,2019:3590-3598.

[19] SHI L,ZHANG Y,CHENG J,et al.Skeleton-based action re-cognition with directed graph neural networks[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition,June 16-20,2019,Long Beach,CA,USA.New York:IEEE,2019:7904-7913.

[20] GAO C Q,DU Y H,LIU J,et al.A new dataset and evaluation for infrared action recognition[C]//ZHA H,CHEN X,WANG L,et al.Computer Vision:CCCV 2015.Berlin,Heidelberg:Springer,2015:302-312.

[21] BOCHKOVSKIY A,WANG C Y,LIAO H Y M.YOLOv4:optimal speed and accuracy of object detection[EB/OL].(2020-04-23)[2020-08-18].http://arxiv.org/abs/2004.10934.

[22] FANG H S,XIE S,TAI Y W,et al.RMPE:Regional multi-person pose estimation[C]//2017 IEEE International Conference on Computer Vision (ICCV),October 22-29,2017,Venice,Italy.New York:IEEE,2017:2353-2362.

[23] DEFFERRARD M,BRESSON X,VANDERGHEYNST P.Convolutional neural networks on graphs with fast localized spectral filtering[C]//Proceedings of the 30th International Conference on Neural Information Processing Systems,December 5-10,2016,Barcelona,Spain.Cambridge,USA:MIT Press,2016:3844-3852.

[24] KIPF T N,WELLING M.Semi-supervised classification with graph convolutional networks[EB/OL].(2020-01-17)[2021-02-18].https://arxiv.org/pdf/1609.02907.pdf.

[25] LIU W,ANGUELOV D,ERHAN D,et al.SSD:single shot multiBox detector[C]//LEIBE B,MATAS J,SEBE N,et al.Computer Vision:ECCV 2016.Cham,Switzerland:Springer,2016:21-37.

[26] REDMON J,FARHADI A.YOLOv3:an incremental improvement[EB/OL].(2018-04-08)[2020-08-18].https://arxiv.org/abs/1804.02767.

[27] ZHAO Q,SHENG T,WANG Y,et al.M2Det:a single-shot object detector based on multi-level feature pyramid network[C]//Proceedings of the 2019 33th AAAI Conference on Artificial Intelligence,January 27-February 1,2019,Honolulu,Hawaii,USA.Palo Alto,CA,USA:AAAI Press,2019,33:9259-9266.

[28] LIU S,HUANG D,WANG Y.Receptive field block net for accurate and fast object detection[C]// Computer Vision:ECCV 2018,September 8-14,2018,Munich,Germany.Berlin:Springer,2018:385-400.