Analyze and Highlight the Abnormal Activities While Recording in CCTV
D. Sathish Kumar, P. Tejaswini, S. Abirame, Namratha Gopinath, M. Meena, S. Gurusubramani · 2024
More and more settings, including workplaces, hotels, and public areas, are installing closed circuit television systems (CCTV). There have been several installations of monitoring systems in American and European cities. Due to human limitations, the number of camera views that a single chairman can screen is restricted, making this a massive mountain for the CCTV directors to climb. The task of computerized area and affirmation of dangerous conditions for CCTV systems is the focus of this study. Our proposed computations can detect when a cut or weapon is obvious in the picture and alert the human director accordingly. In order to enable the system's practical implementation, we have focused on reducing the number of dishonest warnings in the orchestra. There has been a substantial improvement over previously released cuts in terms of both specificity and affectability. We have also been supervising the proposal of a weapon area calculation that provides an almost-zero rate of dishonest warnings. To reduce the number of possible victims and increase response times, we demonstrated that it is possible to create a system capable of early warning in a dangerous situation.