基于HMM监控视频的异常事件检测

针对智能监控系统中的行为分析与识别，将隐马尔可夫模型（Hidden Markov model，HMM）应用到智能视频监控系统的异常事件检测中。首先应用背景差法将运动目标提取出来。其次将运动目标的形状、颜色和帧间变化度等特征编码，生成特征向量。训练时将特征向量送入HMM训练得到隐马尔可夫模型需要的参数[WTHX]A和B[WTBZ]，检测时将特征向量送入HMM检测系统检测是否有异常事件发生。最后的实验结果表明，该方法能快速有效地检测监控视频中的异常事件的发生。

Abnormal Event Detection of Surveillance Based on HMM

Aiming at the analysis and the recognization in intelligent surveillance system. Hidden Markov model (HMM) is applied to analyze abnormal events detection in surveillance system. The method extracts motive object by background substraction, encodes shape features, color and changes rate of frames for feature vector. In training, feature vector is applied to HMM to obtain parameters A and B. In detecting, the feature vector is input into the HMM to detect abnormal events. The experiment shows that the method can detect abnormal events quickly and accurately.