改进混合高斯模型在人体跌倒检测中的应用-计算机工程与应用.PDF

Computer Engineering and Applications 计算机工程与应用 2017 ，53（20 ） 173 改进混合高斯模型在人体跌倒检测中的应用 用 1，2 1，2 ，3 1，2 ，3 1，2 1，2 1，2 孙 朋 ，夏 飞 ，张 浩 ，彭道刚 ，马 茜 ，罗志疆 应 SUN Peng1，2 , XIA Fei1，2 ，3 , ZHANG Hao1，2 ，3 , PENG Daogang1，2 , MA Xi1，2 , LUO Zhijiang1，2 与 1. 上海电力学院 自动化工程学院，上海 200090 程 2. 上海发电过程智能管控工程技术研究中心，上海 200090 g 3. 同济大学 CMIS 中心，上海 200092 r 工 o 1.College of Automation Engineering, Shanghai University of Electric Power, Shanghai 200090, China . j 2.Shanghai Engineering Research Center of Intelligent Management and Control for Power Process, Shanghai 200090, China 机 a 3.CMIS Center, Tongji University, Shanghai 200092, China 算 e c . SUN Peng, XIA Fei, ZHANG Hao, et al. Research of human fall detection algorithm based on improved Gaussian 计 w mixture model. Computer Engineering and Applications, 2017, 53 （20 ）：173-179. w Abstract ：A hierarchical feature detection based on improved Gaussian mixture model is proposed in this paper to detect w the falls. Aiming at the drawbacks of low background updating rate and shadow interference, background model is updated by improving the Gaussian mixture model and the shadow interference is eliminated through the characteristics of shad- ows in the HSV color space. Human minimum area external rectangle and vertical external rectangle are used to detect the human body, and the characteristics of rectangle ratio, centroid height ratio and inclination angle are analyzed in the paper. A hierarchical feature detecti