基于特征融合的视频异常事件检测方法

为有效对视频数据进行降维并去除特征集合中的冗余信息, 以提高异常事件的检测效率, 从特征提取和选择的角度提出了融合特征区分度和相关性的视频异常事件检测方法。利用视频数据的时空邻域信息进行特征提取。通过分析特征的判别力和相关性进行特征选择, 从而去除特征集合中的冗余信息, 提高异常事件检测的效率和准确性。实验结果表明, 该方法的检测准确率都优于其他传统方法, 能有效地对场景中发生异常事件的区域进行准确定位。

Video Abnormal Event Detection Method Based on Feature Fusion

In order to effectively reduce the data dimension and remove the information of video data and improve the efficiency of abnormal event detection, the video abnormal event detection method based on the distinction and correlation is proposed. The method extracts features of the video data by analyzing the temporal and spatial neighborhood information of data, removes redundant information in the feature set and improves the efficiency of abnormal event detection by analysis of the distinction and correlation of feature. The method is compared with the traditional method in the simulation. The experimental results show that the detection accuracy of video abnormal event detection method based on feature fusion is higher than other methods, the method can accurately locate the abnormal area in the scene.