Detection of Anomaly in Videos Using Convolutional Autoencoder and Generative Adversarial Network model

Anomaly in the crowds can create a threat to public security. Manual detection of abnormal crowd behavior in CCTV footage by human operators is a very difficult and time-consuming task. There is a need for automated detection of abnormal events in a video. The proposed automated method is based on the Convolutional Autoencoder and Generative Adversarial Network (GAN) model which are used to extract the features and motion patterns of the videos. The selected features are then classified by using different classifiers such as Support Vector Machine (SVM), Naïve Bayes, Decision Tree, and Linear Regression, for differentiation of various types of abnormalities in videos. The proposed method is validated on the UCF crime video dataset. Accuracy, sensitivity, specificity and loss function are the performance parameters used for the evaluation of the proposed methodology. The visual and parametric results of the proposed method showed promising results in the form of accuracy as compared with the existing techniques.