基于SVM的异常行为检测在电子考场中的应用研究

Research of SVM-Based Abnormal Behavior Detection in Electronic Invigilated Examination Room

电子监考系统在我国已经得到广泛应用,本文针对考场视频分析的应用需求,以智能视频监控理论为依据,研究基于视频分析的考场异常行为有效识别方法。本文基于目标对象的皮肤特征模型,设计和生成行为模型,结合SVM支持向量机,实现在视频帧序列中检测考场异常行为。该模型可以应用于考场视频监控系统中,有助于提高系统的智能化,增强考场监控能力。

Electronic invigilating system has been widely used in China. This paper analyzes the examination room video application requirements, in accordance with the theory of intelligent video surveillance, giving a research of abnormal behavior detection based on video analysis. Based on the characteristics of the target object skin, we design and build a behavioral model, using support vector machine to detect abnormal behavior in the video frame sequence. The model helps to improve the intelligence system, and strengthen the examination room monitoring capabilities.