The scientific community is paying more attention to the highly developed field of anomaly detection in video surveillance. Intelligent systems that can automatically spot unusual events in streaming videos are in high demand. This survey article gives a thorough summary of the several methods for spotting irregularities in surveillance videos. Both conventional methods—such as statistical modeling and motion analysis—and more current strategies—such as deep learning and artificial intelligence—are included in these methodologies. The study also identifies each technique's advantages and disadvantages as well as prospective uses in real-world situations. It also covers the difficulties in developing efficient anomaly detection algorithms for surveillance movies and points out potential future research topics. Overall, it is a useful tool for academics and professionals involved in the study of violent behavior detection (VioBD). It proposes a road map for future research on anomaly identification in surveillance films and provides insights into the state of the field now. To ensure the best possible performance of the anomaly detection system, it is crucial to keep in mind that the success of anomaly identification in surveillance videos significantly depends on the availability and quality of training data. As a result, future studies should concentrate on creating reliable feature extraction methods and enhancing the readability of anomaly detection models. The survey also says that in order for large-scale video data to be used in real-world applications that use anomaly detection systems, future studies should look into new ways to make these systems more scalable and effective.