摘要
独居老人摔倒已成为一个备受关注的问题。为快速有效获取摔倒信息从而使老人得到及时救助,提出一种基于双目标定的独居老人摔倒检测算法。该算法通过色彩不变性分割前景目标(老人),采用双目视觉标定计算人体在三维坐标中高度作为特征信息,能够有效区分易混淆动作,防止误判,提高检测准确率。实验结果表明:该算法易于实现,具有较好的鲁棒性和实时性。
Failing down of solitary elderly person has become a concerned problem. In order to get information of falling down of elderly person quickly and efficiently, a method for falling down detection of solitary elderly person based on binocular vision calibration is proposed. The algorithm segments foreground objects (elderly person) by color variation;uses binocular vision calibration to calculate person height in 3 D coordinate as feature information, which can effectively distinguish confused behavior, prevent misjudgments and increase accuracy of detection. Experimental results show that the proposed algorithm is easy to implement with good robustness and real-time.
出处
《传感器与微系统》
CSCD
北大核心
2014年第10期100-103,共4页
Transducer and Microsystem Technologies
关键词
双目标定
色彩不变性
摔倒检测
binocular vision calibration
color invariant
falling down detection