Application of Human Body Recognition Technology in Scientific Research Sites. (September 2020)

• Record Type: Journal Article
• Authors: Liu, Yugang; Zhang, Xiaofeng
• Is Part Of: Journal of physics. Volume 1646(2020)
• Publication Date: 2020-09
• Subjects: Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/1646/1/012119
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: In schools and various scientific research institutes, there are a lot of confidential places, such places usually have a person in charge of the management of the scientific research platform. It is an effective method to detect people entering the secret place by video surveillance and give early warning and warning to outsiders. In the video monitoring in normal use, the recognition method of human body is a kind of dynamic pattern recognition, in order to be able to quickly form to the variety of the human body for effective identification, this paper uses the fuzzy clustering method to filter the static image elements in the video image, in view of the dynamic pixel area, by using convolutional neural network to identify the human form, improve the system recognition robustness for optimized recognition effect.