The design of fall detection algorithm based on multi-feature analysis

• Main Authors: Gao Miao, Zhu Sulei
• Format: Article
• Language: English
• Published: Academic Journals Center of Shanghai Normal University 2017-04-01
• Series: Journal of Shanghai Normal University (Natural Sciences)
• Subjects: fall detection; Gaussian mixture model; centroid; orientation angle; motion coefficient
• Online Access: http://qktg.shnu.edu.cn/zrb/shsfqkszrb/ch/reader/view_abstract.aspx?file_no=20180218&flag=1

In view of the shortcomings of high detection error rate of the existing fall detection algorithm,an improved fall detection algorithm is proposed.First,the Gaussian mixture model is used to detect the foreground object,and then median filtering and morphological processing are used to extract the foreground object.Based on the use of human aspect ratio and effective area ratio,the change of centroid,orientation angle and motion coefficient are taken as features to judge whether the human has fallen.Compared with traditional algorithnal,experimental results show that the proposed algorithm has higher accuracy,higher sensitivity,low algorithm complexity,and can effectively prevent misjudgment.