Open AccessResearch on Detection and Recognition of Abnormal Behavior in Video
Author(s) -
Yanli Fu,
Rui Deng,
Bei Xue,
Shuyao Li
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1601/3/032042
Subject(s) - computer science , artificial intelligence , computer vision , preprocessor , grayscale , image processing , edge detection , image (mathematics) , video processing , pattern recognition (psychology)
In order to solve the problems of low detection efficiency and long working time in traditional video surveillance systems for abnormal behavior detection and recognition methods, a new method for abnormal behavior detection and recognition in video surveillance systems is proposed. This method first completes image preprocessing through four steps: video image noise filtering, image grayscale correction, binarization processing, and image edge detection; then, based on the characteristics of the image abnormal target, the key frame of the abnormal image is detected and the data is dissected to complete the abnormal behavior detection of the video monitoring system; finally analyze the video image rules through adaptive algorithms, and use the computer’s visual detection principle to change with the scene environment to identify the abnormal behavior of the video surveillance system. In order to detect the effect of the method, a comparative experiment was set up. The experimental results show that the new method can accurately detect abnormal behavior in a short time and has a strong working ability.