Abstract: In today's modern world, security and safety are major concerns. To be economically strong, a country must provide a safe and secure environment for investors and tourists. Closed Circuit Television (CCTV) cameras, on the other hand, are used for surveillance and monitoring activities. A large number of surveillance cameras are available in various locations, but all of them only record footage. To analyse these videos, a large amount of manpower is required, which is always undesirable due to time and labour waste. As a result, having a system that detects crime in real time and alerts the user is advantageous. This paper proposes a system for automatically detecting crime from surveillance camera footage. The system has been pre-trained to detect crimes in real time and provide both remote and offline alerts, which is useful in reducing the possibility of criminals escaping and quickly arrest them. If the missing person enters the premises, the system detects him or her.
Keywords: IoT, CCTV, CNN, MBF.
| DOI: 10.17148/IJARCCE.2021.101258