Expect Resurgence in Video Analytics in 2018
This post is also available in: 
עברית (Hebrew)
An increasing interest in video analytics was demonstrated in 2017 from commercial industries using the technology for business operations, yet the security industry remains interested in capturing actionable data from video analytics. The market for video analytics is anticipated to expand at a CAGR of 20.6% during the forecast period from 2015 to 2023, according to security.world.
Video analytics integration with other systems, such as access control, will continue to provide critical information for managing situations as they unfold.
In 2018, a resurgence in video analytics is expected, especially in AI and deep learning, extending to security robot and drone technology. The next step in video analytics is to dive deeper to gain very specific insights into video content, including analyzing human behavior through the use of neural network video analysis, according to an evaluation by sourcesecurity.com.
Video will not only be used to track the usual movement of cars and people or detect items left behind, but will also be relied on more frequently to bring behaviors of interest to the attention of security personnel. Like self-driving cars, analytics allow systems to make decisions on their own, which can increasingly be applied in a security setting as well — including the triggering of robots and drones to respond to specific security events.
The cloud is still an important field of interest in this respect. Although there is more talk about cloud applications than actual movement toward cloud usage, smart codecs, which most security camera manufacturers are developing and marketing as a solution that goes beyond H.264 and H.265, lend themselves to future cloud applications.
The ongoing need to better manage network bandwidth usage and to maximise video storage is further turning the emphasis toward smart codecs. This now allows extremely high-resolution video to be moved around in a fraction of the time and solves the issue of transporting many cameras over constrained WAN connections.
With the elastic computing power available in the cloud, we can now envision a time where cloud computing costs could be low enough for the masses of video security solution use cases to be solved.
