The future of artificial intelligence in surveillance
Today we find artificial intelligence (AI) in autonomous vehicles, medical applications, search engines, virtual assistants and image recognition. Even though many say there is no “real” AI yet and that it will take many years to create a true AI application, the potential for this technology is undeniable.
Since 2015, AI technology has become part of our everyday lives and is currently a popular tagline in many applications. Artificial intelligence and deep learning technologies are coming out of the shadows of engineering labs and military applications and finding their way into commercial security deployments.
Some people expect AI to eventually become a game-changer in surveillance solutions and it’s easy to understand why. AI systems can analyse huge amounts of data, which of course is advantageous when you need to review hours of surveillance images. This type of system could also be programmed to tell you in what direction the object is moving and whether there is more than one object.
Artificial intelligence, machine learning and deep learning
AI is the act of simulating any intellectual task. An essential component of AI is machine learning (ML) and sometimes the two expressions are used interchangeably. AI uses algorithms to go through data, learn from it, and then make predictions.
However, to mimic the complex human brain, a computer needs lots of training. So-called deep learning (DL) is an advanced way of implementing ML, but it requires lots of data, advanced classifications and serval layers of analysis to produce “deeper” knowledge.
“Realistically, in security we can now only see a huge impact in the utilisation of machine learning,” states Craig Turner, Surveillance Specialist at Duxbury Networking. “We don’t yet see enough awareness of AI technology abilities in the surveillance industry. We should expect that unlocking the full capabilities of AI technology, and making it easily available to customers, in turn, will open up a whole new chapter of innovation and opportunity.”
The ability to house enormous image libraries and process from edge devices is now the trend. Deep learning models on the server side allow data collection and access in real-time to make safer, smarter and more efficient sites.
Milestone XProtect video management software (VMS) is based on a true open platform, which means it has a published application programming interface (API), allowing developers to alter the functionality of XProtect. The Milestone open platform enables you to add custom, best-in-class security solutions to your surveillance, such as access control, cameras and video analytics.
AI in surveillance – design with a purpose
A surveillance solution – with or without AI – is rarely an off-the-shelf solution since every business and every premises are unique. Understanding the primary purpose of the system and how the footage eventually might be used is essential. And image usability can only be achieved if the system has been adapted to the specific conditions of the premises and if it’s properly maintained.
To succeed, the primary focus can’t be on the technology, but always on the solution of a particular use case. Only as part of a complete and well-designed solution, where human expertise has taken all kinds of considerations into account, can AI offer great opportunities within surveillance.
A recent report from Research and Markets notes AI will be a key driver of growth in the global physical security market. It projects a compound annual growth rate of 7.3% from 2018 to 2023. “AI-enabled software delivers insights and intelligence that streamline business processes and provide business intelligence to improve the whole operation, optimise operator response to events and grow the business,” says Turner.
“Today we see video analytic solutions that work very well. Colour, direction, correlation, object identification, facial recognition and synopsis are all examples that we see successfully in use already.”
Axis Communications offers smarter solutions that address shoplifting, internal shrinkage and suspicious behaviour in real-time to prevent retail shrinkage before it happens. With optimised staff allocation, improved store layouts and proactive in-store campaigns, you can act on insights to enhance the customer experience every hour of every business day.
Quality of the data
Image usability is as always of the greatest importance. Without “raw material” in terms of high-quality footage and video, an AI system cannot analyse anything. An active environment with trees blowing in the wind, or a person carrying something that the AI system considers irregular, can trigger many false alarms. Therefore, the AI can be used to roughly determine how relevant an incident is and then alert a human being who then decides the response.
In conclusion, AI systems have developed quickly over the past years and show great potential within the field of surveillance, but unfortunately, public awareness of these capabilities still has a way to go. With Milestone’s open platform integration, you can access the latest AI surveillance technology and customise your surveillance solutions.
One thing it doesn’t take advanced analytics to figure out: AI technologies will only continue to evolve and take a predominant place in the video surveillance market.