With the proliferation of cameras in our households for security purposes, the task of evaluating anomalies occurring within their field of view has become increasingly complex. An anomalous event refers to an occurrence deviating from the norm, exhibiting unusual behavior that happens infrequently. To bolster public safety, surveillance cameras are deployed in high-traffic areas, hospitals, banks, and shopping malls. However, challenges arise due to camera placement limitations and the insufficient number of cameras compared to human monitors. The detection of abnormal events such as crimes, illegal activities, and traffic accidents is a crucial objective in video surveillance. In response, our proposed system harnesses the power of computer vision and deep learning to accurately detect anomalous events in real time. By leveraging advanced algorithms, our solution offers improved precision in identifying and flagging unusual activities, thus enhancing overall security and enabling prompt response measures.