红外技术, 2017, 39 (12): 1131, 网络出版: 2018-01-09
红外图像中基于多特征提取的跌倒检测算法研究
Fall Detection Algorithm Based on Multi Feature Extraction in Infrared Image
摘要
研究表明跌倒是我国老年人伤害的主要原因,而且超过一半的跌倒发生在家中。如果我们能及时发现老人跌倒并进行有效处理,就会降低跌倒对老人的伤害。因此为了检测老年人室内跌倒行为,本文从低分辨率的红外图像中,提取出4 种对跌倒敏感的特征,同时使用K 近邻算法进行分类来判断是否发生跌倒。另外,本文还设计了一套基于该算法的老年人跌倒检测系统,它具有保护隐私、准确度高、安装方便的优点。最后通过实验测试表明该跌倒检测算法的准确率高达91.25%。
Abstract
Falling is reported to be the major cause of injury in the elderly population in China. More than half of the falls this population experienced occurred at home. If we can get timely messages during the event of a fall, and process these effectively, we can reduce the potential for harm. Therefore, in order to detect indoor falls of the elderly, this study extracts four fall-sensitive features in low-resolution infrared images, after which the k-nearest neighbor algorithm is used to determine whether a fall has occurred or not. Moreover, this paper also designs a complete fall detection system for the elderly based on the proposed algorithm, which offers the advantages of privacy protection, high accuracy, and convenient assembly. Results of experiments show that the accuracy of the fall detection system is as high as 91.25%.
杨任兵, 程文播, 钱庆, 章强, 钱俊, 潘宇骏. 红外图像中基于多特征提取的跌倒检测算法研究[J]. 红外技术, 2017, 39(12): 1131. YANG Renbing, CHENG Wenbo, QIAN Qing, ZHANG Qiang, QIAN Jun, PAN Yujun. Fall Detection Algorithm Based on Multi Feature Extraction in Infrared Image[J]. Infrared Technology, 2017, 39(12): 1131.