KALLEPALLI ROHIT KUMAR,2DR.NISARG GANDHEWAR 04 4 There has been a recent uptick in the installation of hightech video surveillance equipment in public areas One of the primary uses for gathered video features is safety monitoring made possible by the implementation of deep learning and machine learning techniques In this work our primary focus is on anomaly detection in situations with a large number of people both indoors and outdoors In this study we describe the VGG 16 architecture for the detection of abnormalities occurring in surveillance cameras using classifiers The VGG 16 architecture was implemented with stateoftheart classifiers like random forest J48 decision tree and SVM Experiments revealed that the suggested model of using VGG 16 has a relatively low computational burden while still producing satisfactory results with an accuracy of 8086 for the random forest classifier Copyright (c) World Journal of Pharmaceutical Seiences. All rights reserved 2026