Monitoring activity and detecting unexpected events in surveillance footage using Deep CNN

Security is always a primary concern in any domain, because there is an increasing in crime rate and illegal activities. Computer vision learning places a premium on abnormal detection and monitoring, which has numerous applications for dealing with a wide range of issues. We are all aware that there is a high demand for safety protection, personal properties and security, in recent years, video surveillance in systems has become a major focus in people's lives, particularly in government agencies and businesses. The technique we are employing is anomaly detection, which aids in distinguishing various patterns and identifying unusual patterns in a short period of time; these patterns are referred to as outliers. Surveillance videos provide real-time output of unusual events. Anomaly detection in video surveillance entails breaking the process down into three layers: video labelers, image processing, and activity detection. As a result, it detects abnormalities in videos for video surveillance, providing an application by providing accurate results in real-time scenarios. In this proposed work, abnormal events are detected with 98.5 percent accuracy using images and videos. To prevent virus transmissions across the world the government forced to announce the lockdown due to COVID-19 pandemic. As a result, production at manufacturing plants in most areas was halted, resulting in the cessation of all economic activity. There is an even greater need to ensure the safety of youngsters. While there is a pressing need to revive workforce production. The work helps in maintaining social distance and wearing face masks while at work clearly reduces the risk of transmission. Monitor activity decided to identify violations using computer vision (Not Wearing Mask) Real-time alerts that send a trigger and an email with a photo of a rule violation to the appropriate authority as evidence of a rule violation.