期刊
IEEE TRANSACTIONS ON MULTIMEDIA
卷 23, 期 -, 页码 3684-3699出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMM.2020.3029904
关键词
Feature extraction; Privacy; Senior citizens; Nonhomogeneous media; Visualization; Cameras; Fall detection; privacy-preserving; multilayer compressed sensing; LBP-TOP; information embedded
资金
- Provincial Natural Science Foundation of the Science and Technology Bureau of Jiangsu Province [BK20180088]
- China Postdoctoral Science Foundation [2019M651916]
- Scientific Research Foundation of Nanjing University of Posts and Telecommunications [NY218066]
- Natural Science Foundation of China [61871445]
The study proposes a fall detection system with visual shielding to ensure the safety of elderly people at home while preserving their personal privacy. Through multilayer compressed sensing and feature extraction, accurate identification of fall behaviors is achieved.
Falls are the main cause of accidental injuries, and even death among elderly people, especially those who live alone in their homes. The absence of a reliable fall detection system has long been a serious problem for home health monitoring. A video surveillance system can be used to monitor elderly people at home to detect falls, but the traditional implementation of such intelligent detection falls short of personal privacy-related considerations; additionally, many people do not want to be watched in their homes. To solve this problem, we propose a fall detection system with visual shielding that can ensure the safety of elderly people in their homes while preserving their personal privacy. Multilayer compressed sensing is first used to achieve visually shielded video frames. By combining low-rank sparse decomposition theory with the improved local binary pattern on the three orthogonal planes, the object features are extracted from the shielded video frames. Finally, to compensate for the information lost in the compressed video to a certain extent, a private information-embedded classification model is proposed to identify fall-related behavior. The experimental results on two public fall datasets show that the proposed method delivers impressive accuracy and a low error rate while effectively distinguishing between fall- and nonfall-related behaviors in videos.
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