[1] [1] Fan Y, Wen G, Li D, et al. Video anomaly detection and localization via Gaussian mixture fully convolutional variational autoencoder［J］. Computer Vision and Image Understanding,2018,195(01):1—12.

[2] [2] Wang F, Huang H, Liu J. Variational-based mixed noise removal with CNN deep learning regularization［J］. IEEE Transactions on Image Processing,2019,29:1246—1258.

[5] [5] Xuan Q, Li F, Liu Y, et al. MV-C3D: A spatial correlated multi-view 3D convolutional neural networks［J］. IEEE Access,2019,7(01):2169—3536.

[8] [8] Qian H M, Mao Y B, Wang Z Q. SVM-based abnormal activity detection for home care［C］∥2008 7th World Congress on Intelligent Control and Automation.China,Chongqing:IEEE,2008:3766—3771.

[11] [11] Guo S, Bai Q, Gao S, et al. An analysis method of crowd abnormal behavior for video service robot［J］. IEEE Access,2010,07(01):169577—169585.

[15] [15] Direkoglu C. Abnormal crowd behavior detection using motion information images and convolutional neural networks［J］. IEEE Access,2020,08(01):80408—80416.

[18] [18] Hu X, Dai J, Huang Y P, et al. A weakly supervised framework for abnormal behavior detection and localization in crowded scenes［J］. Neurocomputing,2020,383(01):270—281.

[23] [23] Pinter M. Toward more realistic pathfinding［EB/OL］. (2001-03)/［2001-09］.http:∥www.gamasutra.com/view/feature/3096/toward_more_realistic_pathfinding.php.

[24] [24] Ferryman J, Ellis A L. Performance evaluation of crowd image analysis using the PETS2009 dataset［J］. Pattern Recognition Letters,2014,44(15):3—15.