Abstract
While video analysis has become a standard feature of many security cameras, built audioanalytics remains relatively rare, despite the presence of both the audio channels in the devices and the available computing power to process audio data. However, audioanalytics has certain advantages over video analytics: microphones and maintenance cost is significantly less expensive than cameras; when the system is in real-time audio data stream is substantially less in volume than the flow of data from the video cameras, which imposes more loyal to the bandwidth requirements of data transmission channel. Audioanalytics systems can be especially in demand for urban surveillance, where you can automatically start to broadcast live video on the police control from the place of explosion and fire. Audioanalytics technology can also be used in the study and recording of certain events. In this study, we consider methods to identify audio event recognition, create a surveillance model using audioanalyitics methods and identify audio events by experiments.