In the present-day context, security has emerged as a matter of utmost significance, particularly for individuals and businesses striving to safeguard their assets and people. While conventional video surveillance systems have long been relied upon, they come with inherent limitations.
The higher the accuracy of video analytics, the lower the load on communication channels and cloud storage. Therefore, if the accuracy indicators of video analytics are known, the service provider or consumer can easily calculate the economic benefits of using video analytics. Consider an example. To protect the perimeter of a large company, 300 cameras with a resolution of 1.2 MP are used. Under normal weather conditions, the total video stream is 1.8 Gb / s. Under adverse conditions, that is, when the signal is noisy, for example, at night, the flow increases almost twice to 3.5 Gb / s. The use of a conventional motion detector can reduce the amount of video data by an average of 80%, that is, to 0.7 Gb / s. Unfortunately, the peak load is sometimes many times greater than this range due to the fact that the motion detector responds to global changes in light and weather conditions immediately on all cameras. The use of professional video analytics to detect people on the territory allows reducing the average load to 0.02 Gbit / s, and the peak load to 0.05 Gbit / s. Thus, in comparison with a conventional motion detector, video analytics can reduce the load on the communication channel and cloud storage by more than 40 times.