How far are we really at with artificial intelligence?

Residential Estate Security Handbook 2019 Editor's Choice, CCTV, Surveillance & Remote Monitoring, IT infrastructure, Residential Estate (Industry)

If we look for applications of artificial intelligence (AI) in our daily lives, we can see it in autonomous vehicles, medical applications, search engines, Virtual Assistants, and image recognition. Or can we? It is argued that there is no ‘real’ AI in practice yet, and what we see is just the basics of machine learning (ML), also that it will take many years to create a true AI application.

But let’s unpack exactly how far AI has come and what it potentially can do for society and more importantly, surveillance.

How far has AI come?

Since the term was introduced in 1956, AI technology has gone from being hailed as the key to a bright new future, to a complete failure, to an interesting tool for applications, including surveillance. Since 2015, AI technology – or at least the embryo of it – has become part of our everyday lives and is currently a popular tagline in many applications.

We might be far from a truly ‘intelligent machine’, but AI is already being used in voice recognition and search engines; in healthcare to help identify indicators for cancer; voice translations – although these still have a way to go – and in prototypes for self-driving cars and service robots.

Some people expect AI to eventually become a game-changer in surveillance solutions and it’s easy to understand why. AI systems are able to analyse huge amounts of data, which of course is advantageous when you have to review hours of surveillance images. By ‘learning’ how the observed object moves, how tall or small it is, whether it has two arms and two legs and how fast it is going, the AI application ranks the information and decides whether it is probable that the object is human. This kind of functionality is common in the field of safety and security today.

Artificial intelligence, machine learning and deep learning

AI is the act of simulating an intellectual task. An essential component of AI is 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. A compute-intensive model, DL is today mostly run on servers with multiple GPU processors, but when edge devices increase their computing capacity, some applications will probably move there in the future.

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 use case is unique. Understanding the primary purpose of the system and how the footage eventually might be used is essential. Image usability can only be achieved if the system has been adapted to the specific conditions of the environment and is properly maintained.

To succeed, the primary focus therefore can’t be on the technology, but 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.

AI in surveillance – advantages

Whenever there is a need to process and analyse huge amounts of data, computers beat humans. A well-trained AI can take this to an even higher level of data and image analysis. This functionality can be of practical use in many applications.

Safety and security – An AI system can, if properly set up and configured, quickly correlate events detected in several hours of video material from several sources. A surveillance system using AI can trigger a direct alarm, where a potential burglar can be ‘told off’ before the crime has even been committed.

Business optimisation and smart cities – Surveillance systems with AI can detect unusual behaviour patterns and use the data to optimise operational efficiency in retail environments or even allow for a controlled flow of traffic and quick responses to incident reports on a highway.

AI in surveillance – challenges

It’s easy to get carried away by the potential of AI in a range of applications, such as improvement of configuration, system optimisation, site design, image configuration and device management. However, there are still fundamental challenges that need to be solved.

Human experience beats AI – An AI application can successfully detect a ‘running person’ but, unlike humans who can put the data into context, it cannot know why that person is running – to catch the bus or because he has just robbed the bank.

Quality of the data – Without ‘raw material’ in terms of high-quality footage and video, an AI system has nothing to analyse. If the cameras can’t handle challenging light or if the angles are wrong, it could jump to the wrong conclusions.

Compute-intensive technology – Memory, processing power, and power consumption are the biggest challenges within AI, especially for deep learning applications. Today’s systems require vast amounts of space to store data for learning, either in the cloud or on a server with multiple GPUs.

AI systems have developed rapidly over the past years and show potential within the field of surveillance, but we are far from having developed human-level intelligence, or ‘true’ AI. It will take some time before we see self-learning surveillance systems that can make accurate assumptions in general scenarios without risking too many false alarms or the violation of people’s integrity.

For more information contact Axis Communications, +27 11 548 6780,,


Share this article:
Share via emailShare via LinkedInPrint this page

Further reading:

Camera Selection Guide 2020
CCTV Handbook 2020 , Camera Selection Guide, CCTV, Surveillance & Remote Monitoring
The Camera Selection Guide 2020 includes a range of IP, analogue, thermal and speciality cameras aimed at a broad range of surveillance functions.

Storage Selection Guide 2020
CCTV Handbook 2020 , Storage Selection Guide, CCTV, Surveillance & Remote Monitoring
The Storage Selection Guide 2020 includes a range of video storage and management options for small, medium and large surveillance operations.

Taking a hands-on approach to community security
Issue 7 2020 , Editor's Choice
Taking a more hands-on approach to community security is definitely paying dividends for Gallo Manor residents.

Adaptors can be a danger to the South African consumer
Issue 7 2020 , Editor's Choice
The increased use of devices and appliances has resulted in the increased use of adaptors as well as adaptors-on-adaptors in South Africa.

The arms race of AI in cybersecurity
CCTV Handbook 2020, Axis Communications SA , Cyber Security
Cybersecurity goes further than network video and audio, but these are as likely to be targeted as much as any network-connected device.

The future of open standards
CCTV Handbook 2020, Milestone Systems, Technews Publishing, Avigilon , Editor's Choice
Despite the many benefits of open standards, some companies still produce proprietary solutions. Are the surveillance and broader security markets still committed to open standards?

The impact of AI on surveillance
CCTV Handbook 2020, Technews Publishing, Axis Communications SA, Hikvision South Africa, Cathexis Technologies, Dahua Technology South Africa , Editor's Choice
Artificial intelligence is a popular buzzword in the security industry that has us expecting real-life science fiction, but what is its real impact?

Evaluating AI technologies for control room operations
CCTV Handbook 2020, Leaderware , Editor's Choice
Can AI systems improve the performance of control room operators, or even replace them completely? Maybe one day they will, but not today.

The future of the VMS
CCTV Handbook 2020, Technews Publishing, Cathexis Technologies, Arteco Global, XtraVision , Editor's Choice, CCTV, Surveillance & Remote Monitoring, Integrated Solutions
Will AI-enhanced video analytic apps that can be downloaded and installed directly onto cameras take business away from the VMS market?

A fresh look at TCO
CCTV Handbook 2020, Axis Communications SA , Editor's Choice
Total Cost of Ownership is a way for strategic buyers to move beyond looking at the upfront price to understanding all costs associated with procuring, deploying and operating a system.