基于智能手机的实时跌倒检测系统研究-计算机工程与应用.PDFVIP

136 2016 ，52（11） Computer Engineering and Applications 计算机工程与应用 ⦾模式识别与人工智能⦾ 基于智能手机的实时跌倒检测系统研究 1 1 2 秦 昉 ，孙子文 ，白 勇 1 1 2 QIN Fang , SUN Ziwen , BAI Yong 1.江南大学 物联网工程学院，江苏 无锡 214122 2.无锡宏创电子有限公司，江苏 无锡 214072 1.School of Internet of Things Engineering, Jiangnan University, Wuxi, Jiangsu 214122, China 2.Wuxi Hong Chuang Electronic Co. Ltd, Wuxi, Jiangsu 214072, China QIN Fang, SUN Ziwen, BAI Yong. Research on real-time fall detection system based on smartphone. Computer Engineering and Applications, 2016, 52 （11）：136-140. Abstract ：In order to reduce the harm caused by fall in the elderly and detect the fall in real time, a fall detection system based on Android smartphone is designed and developed. The proposed algorithm combines the fall detection with gesture recognition algorithm for identifying daily activities and fall. The alarming information will be sent with the user ’s posi- tion obtained from GPS when falling is detected. The results of simulation and experiments show that the system can effec- tively distinguish between falls and daily behaviour, and the algorithm has high instantaneity, sensitivity and specificity. Key words ：fall detection; smartphone; acceleration sensor; posture recognition 摘 要：为减少跌倒对老年人造成的伤害，并对跌倒进行实时检测，提出了一种基于Android 智能手机的人体跌倒检 测系统，手机安置于腰上采集手机加速度传感器数据，利用了姿态识别和跌倒检测相结合的算法，区分出跌倒行为 和人体日正常常活动。当检测到异常跌倒时，报警信息以及从手机中GPS 获取的位置被发送。仿真及实验表明：系 统能够有效地识别出跌倒和日常行为，算法具有较高实时性、具有较高灵敏度和特异度。 关键词：跌倒检测；智能手机；加速度传感器；姿态识别 文献标志码：A 中图分类号：TP273 doi ：10.3778/j.issn. 1002-8331.1407-0296 [2] 1 引言 倒分析 ；基于地面上传感器震动信号波形区分跌倒动 [3] 意外跌倒给老年人的生理和心理带来极大危害，传 作和正常行为 。基于环境测量的方法准确性较高，但 统的跌倒检测技术在设备、场景等方面具有较大局限