Software has always been an important factor in the development and growth of the Physical Security business. PIAM, PSIM, VMS & Video Analytics have been the stalwarts for the last 20 years with VMS taking the major role and PIAM becoming more important in recent years. However we now have a new realm of software, AI Video Analytics & BlockChain, entering the Video Surveillance business that will have a major impact on the future and growth of this business.
In the Video Surveillance business AI Video Analytics should be a game changer over the next 20 years. Video Analytics has already been around for many years but it has never been capable of delivering a satisfactory solution. So what has changed?
New chip developments delivering much faster processing power together with deep learning algorithms have delivered more intelligence and understanding from data. Instead of the traditional computational architecture we’ve become accustomed to with Central Processor Units (CPU), the Graphic Processor Unit (GPU) has become the one to go for when processing rapid-fire calculations required for AI processes and this is now extending to other new architectures. Nvidia, a relatively new start in the chip business, founded in 1993 invented the GPU in 1999 and now leads the market for GPU AI chips.
By the summer of 2016, the change in chip technology was apparent. Google, Microsoft and other IT giants were building apps that could instantly identify faces in photos and recognize commands spoken into smartphones by using complex algorithms, known as neural networks to learn tasks by identifying patterns in large amounts of data and the industry began to take a new shape. This in turn has lead to machine learning & deep learning algorithms being developed; and when perfected they will be a much more accurate tool than traditional symbolic reasoning.
In the first 3 months of this year there has been a significant number of new products launched on beta trials with varying degrees of success. Neural networks are loosely designed based on the biology of our brain. It simulates how we as humans think. It mimics the interconnections between the neurons, where the neurons can connect to any other neurons within a certain physical distance. So artificial neural networks have several layers of connections and directions of data propagations.
AI Technology can and will make a direct and massive contribution to increasing the performance and value of video surveillance solutions and a significant proportion of this can be applied directly. However video surveillance is by no means an island and in many cases it will ultimately need to be connected with the wider IoT, processed by Big Data software and possibly run off a Blockchain platform. The developments of these technologies are still some way from being perfected but their interconnection will deliver “2+2=5” and intelligent video analytics solutions for complex installations.
Blockchain-based platforms are emerging as one of many options to securely connect artificial intelligence with IoT at the network edge. To fully realize the promise of IoT and the wealth of data it can provide, it's essential to connect it to AI. There are, however, several challenges associated with both running AI at the edge of networks and sharing databases securely.
Combining AI and IoT enables you to respond to changes in the environment and to the input of new information whilst Blockchain can help create marketplaces for data and their exchange and also improve data privacy and this in turn will make it much more likely that databases will be shared.
In private networks where all the data to be analyzed is sourced inhouse, it is rarely a problem provided that the network has adequate cyber security provisions.
Blockchain-based computing platforms do exist today, most notably from iExec and Golem. But there's also an open source Linux Foundation platform called Hyperledger, which IBM initiated with the open source community, as well as the Hyperledger Fabric platform beneath its umbrella. This platform allows you to easily connect the data you get from IoT via specific adapters to integrate a variety of existing sensors and protocols.
Then, you can integrate and connect the transactions that are related to these sensors with Blockchain systems that might belong to different organizations with some that maybe aren't willing to make available all of the data coming from these sensors by default. A third step is using the cognitive AI components to infer new insights from this combined data.
It’s important to keep in mind that the technology surrounding Blockchain is still in its early stages. There are many experiments underway, from AI to IoT, to new types of digital platforms, but it will take time for these solutions to develop and to reach consumers and businesses.
There is a growing demand for AI Video Analytics the main one being that current law enforcement systems are increasingly unable to cope with the sheer volume of surveillance material captured and stored every day. It is also set to rise dramatically with the population of video cameras increasing by at least 12% per year. To add to this there is a growing demand from the enterprise business to analyze video streams and realise vital information.