Video Anomaly Detection Using Optimization Based Deep Learning

Background: Excellence in the growing technologies enables innovative techniques to ensure the privacy and security of individuals. Manual detection of anomalies through monitoring is time-consuming and inefficient most of the time; hence automatic identification of anomalous events is necessary to cope with modern technology. Purpose: To enhance the security in public places as well as in the dwelling areas, surveillance cameras are employed to detect anomalous events. Methods: As a contribution, this research focuses on developing an anomaly detection model based on the deep neural network classifier which effectively classifies the abnormal events in the surveillance videos and is effectively optimized using the grey wolf optimization algorithm. The extraction of the features utilizing the Histogram of Optical flow Orientation and Magnitude (HOFM) based feature descriptor furthermore improves the performance of the classifier. Results: The experimental results are obtained based on the frame level and pixel levels with an accuracy rate of 92.76 and 92.13%, Area under Curve (AUC) rate of 91.76 and 92%, and the equal error rate (EER) is 7.24 and 9.37% which is more efficient compared with existing state-of-art methods. Conclusion: The proposed method achieved enhanced accuracy and minimal error rate compared to the state of art techniques and hence it can be utilized for the detection of anomalies in the video.