融合多特征和SVM的跌倒检测方法研究
Research on Fall Detection Method Based on Multi-Feature and SVM
DOI: 10.12677/JISP.2023.122009, PDF,    科研立项经费支持
作者: 王宏睿, 陈佩江*, 马颖初：临沂大学机械与车辆工程学院，山东 临沂；奚耀昌*#：临沂大学自动化与电气工程学院，山东 临沂
关键词: 多特征；跌倒检测；支持向量机；Multi-Feature； Fall Detection； SVM
摘要: 为了及时发现老人跌倒并及时救助，对跌倒检测方法进行了研究。首先采用ViBe算法提取运动的人体，采用高斯滤波和形态学处理后，接着提取人体长宽比、角度、质心高度三个跌倒特征，组合成特征向量并添加保存至特征提取器，最后导入支持向量机模型进行训练。实验证明该方法能有效区分跌倒与非跌倒问题。
Abstract: In order to detect and rescue the elderly fall in time, the fall detection method is studied in this paper. Firstly, the Vibe method is used to extract the moving human body. After Gaussian filtering and morphological processing, three fall features such as aspect ratio, angle, centroid height are extracted, combined into a feature vector and added to the feature extractor. Finally, the support vector machine model is introduced for training. Experiments show that this method can effectively distinguish between fall and non-fall problems.
文章引用：王宏睿, 奚耀昌, 陈佩江, 马颖初. 融合多特征和SVM的跌倒检测方法研究[J]. 图像与信号处理, 2023, 12(2): 89-95. https://doi.org/10.12677/JISP.2023.122009

参考文献

[1] 吴凯文, 谭燕泉, 杨敏, 张杏雨. 智慧健康养老服务与管理专业课程体系设计探讨[J]. 科教导刊-电子版(中旬), 2021(11):121-123.
[2] Peel, N.M., Travers, C., Bell, R.A.R., et al. (2010) Evaluation of a Health service Delivery Intervention to Promote Falls Prevention in Older People across the Care Continuum. Journal of Evaluation in Clinical Practice, 16, 1254-1261.
[Google Scholar] [CrossRef] [PubMed]
[3] Pannurat, N., Thiemjarus, S. and Nantajeewarawat, E. (2014) Automatic Fall Monitoring: A Review. Sensors, 14, 12900-12936.
[Google Scholar] [CrossRef] [PubMed]
[4] Sannino, G., De Falco, I., De Pietro, G. (2015) A Supervised Approach to Automatically Extract a Set of Rules to Support Fall Detection in an mHealth System. Applied Soft Computing, 34, 205-216.
[Google Scholar] [CrossRef] 
[5] Qiang, L., John, A., Mark, A., et al. (2009) Accurate, Fast Fall Detection Using Gyroscopes and Accelerometer-Derived Posture Information. Sixth International Workshop on Wearable and Implantable Body Sensor Networks, BSN 2009, Berkeley, 3-5 June 2009, 138-143.
[6] 石欣, 张涛. 一种可穿戴式跌倒检测装置设计[J]. 仪器仪表学报, 2012, 33(3): 575-580.
[7] 程卫东, 董永贵. 利用热释电红外传感器探测人体运动特征[J]. 仪器仪表学报, 2008, 29(5): 1021-1023.
[8] Min, W.D., Wei, L.S. and An, Q. (2016) Human Fall Detection Based on Motion Tracking and Shape Aspect Ratio. International Journal of Multimedia and Ubiquitous Engineering, 11, 1-14.
[Google Scholar] [CrossRef] 
[9] Rougier, C., Meunier, J., St-Arnaud, A., et al. (2006) Monocular 3D Head Tracking to Detect Falls of Elderly People. The 28th IEEE EMBS Annual International Conference. New York, 30 August-3 September 2006, 6384-6387.
[Google Scholar] [CrossRef] 
[10] 朱晨璐, 隋超, 周翠翠, 等. 基于AR技术的手机拍摄软件的开发[J]. 现代信息科技, 2018, 2(5): 18+20.
[11] 汪鑫, 吴开志, 俞子荣, 等. 基于PoolNet显著性和SURF-VIBE模型的林火视频烟雾提取算法[J]. 南昌航空大学学报: 自然科学版, 2020, 34(2): 94-100.
[12] 刘燕德, 曾体伟, 陈洞滨, 等. 基于改进ViBe算法的运动目标检测研究[J]. 计算机仿真, 2019, 36(2): 62-68.
[13] 李晓黎, 刘继敏, 史忠植. 基于支持向量机与无监督聚类相结合的中文网页分类器[J]. 计算机学报, 2001, 24(1): 7.
[14] 邱国枢, 张翔, 刘军, 等. 基于图像处理的车辆识别系统设计[J]. 吉首大学学报: 自然科学版, 2019, 40(5): 18-24.