Author:
Si Haifei,Hu Xingliu,Wang Yizhi
Abstract
Abstract
Human action recognition is an important part of intelligent video processing, which has high research value and broad application prospects. This paper takes the video monitoring of the elderly living alone as an example to recognize human behavior, and chooses the video of indoor background taken by a single camera as the research object. The background subtraction method is used to extract moving objects from video, and the extracted moving objects are pretreated. Then, according to the overall outline of the object or the obvious features of a part of the object, the motion features are obtained to understand and identify the movement of the monitored object, such as walking and falling. Experiments show that the proposed algorithm has better processing effect for actual video.
Reference15 articles.
1. Research on human fall detection algorithm based on computer vision;Zhou,2013
2. Human Action Recognition Based on Deep Learning;Cai,2019
3. Intelligent video monitoring system with the functionality of online recognition of people’s behavior and interactions between people;Kulbacki,2018
4. Research on Fall Detection System Based on Pressure Sensor;Shi;Journal of Instruments and Instruments,2010
5. Human Behavior Deep Recognition Architecture for Smart City Applications in the 5G Environment;Dai,2019