广东工业大学学报 ›› 2023, Vol. 40 ›› Issue (04): 53-59.doi: 10.12052/gdutxb.220078

• 计算机科学与技术 • 上一篇    下一篇

基于TSSI和STB-CNN的跌倒检测算法

黄晓湧, 李伟彤   

  1. 广东工业大学 信息工程学院, 广东 广州 510006
  • 收稿日期:2022-04-25 出版日期:2023-07-25 发布日期:2023-08-02
  • 通信作者: 李伟彤 (1969–)，男，副教授，主要研究方向为图像处理，E-mail：liweitong@gdut.edu.cn
  • 作者简介:黄晓湧 (1996–)， 男，硕士研究生，主要研究方向为计算机视觉
  • 基金资助:
    广东省科技计划项目(2017A010101016)

Fall Detection Algorithm Based on TSSI and STB-CNN

Huang Xiao-yong, Li Wei-tong   

  1. School of Information and Engineering, Guangdong University of Technology, Guangzhou 510006, China
  • Received:2022-04-25 Online:2023-07-25 Published:2023-08-02

HTML

PDF (PC)

834

摘要： 跌倒行为会给老人特别独居老人带来严重伤害，准确识别跌倒并及时报警可以有效降低这种危险。本文提出一种基于树结构骨架图像(Tree Structure Skeleton Image，TSSI) 和可学习时空块卷积神经网络 (Spatio-temporal Block Convolution Neural Network，STB-CNN) 的跌倒检测方法。首先使用三维姿态估计算法提取人体关节点，进而获得骨架序列；然后利用基于深度优先搜索(Depth First Search，DFS) 算法将骨架序列编码为TSSI；最后构建由时空差分模块、可学习时空框架和时空多分支卷积模块组成的可学习STB-CNN网络，实现跌倒检测。该方法在公开数据集和自建数据集上进行仿真实验分别取得98.6%和98.3%的准确率，优于其他相关算法。

关键词: 跌倒检测, 树结构骨架图像, 可学习时空块卷积神经网络, 姿态估计

Abstract: Falling behavior will bring serious injury to the elderly, especially to the elderly living alone. How to correctly identify the falling behavior and issue a warning is an important factor for reducing the injury. A fall detection algorithm is proposed, which is based on TSSI (tree structure skeleton image) and learnable STB-CNN (spatio-temporal block convolutional neural network). Firstly, human joint point is extracted by the three-dimensional pose estimation algorithm, and the corresponding skeleton sequence can be obtained. Secondly, the skeleton sequence is encoded into TSSI by the algorithm based DFS (depth first search) method. Finally, a learnable STB-CNN is proposed to classify TSSI and detect the fall behavior, which consists of spatio-temporal difference module, learnable spatio-temporal framework and spatio-temporal multi-branch convolution module,. Experiments are carried out on the public datasets UR FALL Detection Datasets and the simulation datasets. Experimental results are shown that our fall detection algorithm is more accurate than other related algorithms, especially the accuracy to 98.6% and 98.3% respectively.

Key words: fall detection, tree structure skeleton image (TSSI), learnable spatio-temporal block convolution neural network, pose estimation

中图分类号: 

  • TP391.4
[1] FOX J A, FOX M A. Falls in older people–an overview for the acute physician[J]. Acute Med, 2011, 10(2): 99-102.
[2] MUBASHIR M, SHAO L, SEED L. A survey on fall detection: principles and approaches[J]. Neurocomputing, 2013, 100: 144-152.
[3] LIU K C, HSIEH C Y, HUANG H Y, et al. An analysis of segmentation approaches and window sizes in wearable-based critical fall detection systems with machine learning models[J]. IEEE Sensors Journal, 2019, 20(6): 3303-3313.
[4] CHEN X, XUE H, KIM M, et al. Detection of falls with smartphone using machine learning technique[C]//20198th International Congress on Advanced Applied Informatics. Toyama: IEEE, 2019: 611-616.
[5] DROGHINI D, FERRETTI D, PRINCIPI E, et al. A combined one-class SVM and template-matching approach for user-aided human fall detection by means of floor acoustic features[J]. Computational Intelligence and Neuroscience, 2017, 2017(8): 1512670.
[6] WU J, WANG K, CHENG B, et al. Skeleton based fall detection with convolutional neural network[C]//2019 Chinese Control And Decision Conference (CCDC). Nanchang: IEEE, 2019: 5266-5271.
[7] YAO L, YANG W, HUANG W. A fall detection method based on a joint motion map using double convolutional neural networks[J]. Multimedia Tools and Applications, 2020, 81(4): 4551-4568.
[8] LI C, ZHONG Q, XIE D, et al. Co-occurrence feature learning from skeleton data for action recognition and detection with hierarchical aggregation[C]// Proceedings of the 27th International Joint Conference on Artificial Intelligence. Stockholm: ACM, 2018: 786-792.
[9] SU H, CHANG Z, YU M, et al. Convolutional neural network with adaptive inferential framework for skeleton-based action recognition[J]. Journal of Visual Communication and Image Representation, 2020, 73: 102925.
[10] LIU J, ROJAS J, LI Y, et al. A graph attention spatio-temporal convolutional network for 3D human pose estimation in video[C]//2021 IEEE International Conference on Robotics and Automation (ICRA). Xi'an: IEEE, 2021: 3374-3380.
[11] KE Q, BENNAMOUN M, AN S, et al. A new representation of skeleton sequences for 3D action recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE, 2017: 3288-3297.
[12] KIM T S, REITER A. Interpretable 3D human action analysis with temporal convolutional networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Honolulu: IEEE, 2017: 1623-1631.
[13] YANG Z, LI Y, YANG J, et al. Action recognition with spatio–temporal visual attention on skeleton image sequences[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2018, 29(8): 2405-2415.
[14] SZEGEDY C, VANHOUCKE V, IOFFE S, et al. Rethinking the inception architecture for computer vision[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 2818-2826.
[15] KWOLEK B, KEPSLI M. Human fall detection on embedded platform using depth maps and wireless accelerometer[J]. Neurocomputing, 2015, 168(3): 637-645.
[16] TAN T H, HUS J H, LIU S H, et al. Using direct acyclic graphs to enhance skeleton-based action recognition with a linear-map convolution neural network[J]. Sensors, 2021, 21(9): 3112-3118.
[1] 钟耿君, 李东. 基于通道分离机制的双分支点云处理网络[J]. 广东工业大学学报, 2023, 40(04): 18-23.
[2] 林哲煌, 李东. 语义引导下自适应拓扑推理图卷积网络的人体动作识别[J]. 广东工业大学学报, 2023, 40(04): 45-52.
[3] 陈晓荣, 杨雪荣, 成思源, 刘国栋. 基于改进Unet网络的锂电池极片表面缺陷检测[J]. 广东工业大学学报, 2023, 40(04): 60-66,93.
[4] 曹智雄, 吴晓鸰, 骆晓伟, 凌捷. 融合迁移学习与YOLOv5的安全帽佩戴检测算法[J]. 广东工业大学学报, 2023, 40(04): 67-76.
[5] 谢国波, 林立, 林志毅, 贺笛轩, 文刚. 基于YOLOv4-MP的绝缘子爆裂缺陷检测方法[J]. 广东工业大学学报, 2023, 40(02): 15-21.
[6] 邹恒, 高军礼, 张树文, 宋海涛. 围棋机器人落子指引装置的设计与实现[J]. 广东工业大学学报, 2023, 40(01): 77-82,91.
[7] 易闽琦, 刘洪伟, 高鸿铭. 电商平台产品共同购买网络的影响因素研究[J]. 广东工业大学学报, 2022, 39(03): 16-24.
[8] 丘展春, 费伦科, 滕少华, 张巍. 余弦相似度保持的掌纹识别算法[J]. 广东工业大学学报, 2022, 39(03): 55-62.
[9] Gary Yen, 栗波, 谢胜利. 地球流体动力学模型恢复的长短期记忆网络渐进优化方法[J]. 广东工业大学学报, 2021, 38(06): 1-8.
[10] 邓杰航, 袁仲鸣, 林好润, 顾国生. 协同超像素和视觉显著性的图像质量评价[J]. 广东工业大学学报, 2021, 38(05): 33-39.
[11] 张国生, 冯广, 李东. 基于姿态表示的航空影像旋转目标检测网络[J]. 广东工业大学学报, 2021, 38(05): 40-47.
[12] 叶培楚, 李东, 章云. 基于双目强约束的直接稀疏视觉里程计[J]. 广东工业大学学报, 2021, 38(04): 65-70.
[13] 蔡昊, 刘波. 半监督两个视角的多示例聚类模型[J]. 广东工业大学学报, 2021, 38(03): 22-28,47.
[14] 刘洪伟, 詹明君, 高鸿铭, 朱慧, 梁周扬. 基于消费者行为流视域的产品竞争市场结构分析[J]. 广东工业大学学报, 2021, 38(02): 26-33.
[15] 夏皓, 蔡念, 王平, 王晗. 基于多分辨率学习卷积神经网络的磁共振图像超分辨率重建[J]. 广东工业大学学报, 2020, 37(06): 26-31.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 2017 《广东工业大学学报》编辑部
地址：广州市东风东路729号广东工业大学 邮编：510090
电话：020-37626653,020-37626139,020-37626396
邮箱：xbzrb@gdut.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发