期刊
IEEE MULTIMEDIA
卷 29, 期 4, 页码 14-23出版社
IEEE COMPUTER SOC
DOI: 10.1109/MMUL.2022.3173335
关键词
Aging; Feature extraction; Fall detection; Sparse matrices; Visualization; Older adults; Computer vision; Accidents; Privacy; Compressed sensing; Chaotic pseudorandom mechanism; Feature enhancement; Foreground extraction; Video fall detection; Visual privacy protection
类别
资金
- Provincial Natural Science Foundation of the Science and~Technology Bureau of Jiangsu Province [BK20180088]
- China Postdoctoral Science Foundation [2019M651916]
- Postdoctoral Research Project of Zhejiang Province [zj2019025]
- Natural Science Foundation of China [61871445]
This study proposes a computer vision fall detection method to protect video privacy. By utilizing compressed sensing visual privacy protection and GAN-based feature enhancement, the method can effectively detect fall behavior with high accuracy.
Currently, falling is the primary cause of injury and death of the elderly due to accidents, which seriously threatens the health and life of the elderly. Considering the phenomenon of video privacy disclosure in recent years, this article proposes a computer vision fall detection method to meet the needs of video privacy protection. The innovation here lies in compressed sensing (CS) visual privacy protection and GAN-based feature enhancement. There are three main steps, the video frame visual privacy protection with chaotic pseudo-random CS mechanism, the foreground extraction with improved low rank sparse decomposition theory, and the temporal and spatial feature enhancement and fall detection with improved-ACGAN `architecture. The experimental results on three open fall datasets show that the method can not only effectively detect the fall behavior in video, but also has high accuracy. At the same time, the overall operation speed of the algorithm increases with the increase of the number of compression layers.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据