Supervised Deep Learning Approaches for Anomaly Detection and Recognition in Crowd Scenes

Abstract

These days consciousness about public safety increases and Closed-Circuit Television (CCTV) cameras are installed at almost all public places. In general, automated smart surveillance systems are not commonly available, and most surveillance videos are monitored manually. This study emphasizes the automatic detection and classification of abnormal events in surveillance video especially in crowd environments. Abnormal event detection is a challenging task because the definition of abnormality is subjective. In the surveillance video with a dense crowd, automatic anomaly detection becomes very difficult because of clutter and severe occlusion. This research represents Convolutional Neural Network (CNN) and Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) based approaches for detection and classification of abnormal events. The CNN architecture is developed from scratch and used for spatial domains. LSTM architecture is developed for the temporal domain. Feature sequences are generated using CNN model and given as input to LSTM model. Experiments are carried out using five different publicly available benchmark datasets. The performance is measured by accuracy and Area Under the ROC (Receiver Operating Characteristic) Curve (AUC). The CNN-LSTM approach performs better than the CNN.