How could applying Artificial Intelligence to CCTV help emergency services’ control rooms?

iStock-154964174.jpg

It is nearly 80 years since CCTV first came to the UK, and in that time the prevalence of cameras, appetite for systems and the sophistication of technology has advanced immeasurably.

The shift from analogue to digital equipment and from simple image capture to augmented technology has been rapid and storing video footage in the cloud has gained serious traction in recent years. With most modern systems now featuring IP-based cameras and equipment, they can maximise this technology. Instead of sending video data to a static recorder, fixed or mobile cameras connected to an IP network send the footage directly to the cloud, giving organisations much more flexibility when it comes to storing, accessing and managing their surveillance footage.

Last year, the UK’s Surveillance Camera Commissioner reported that the most recent estimates for the total spend on video surveillance cameras was £2.25 billion. We are seeing the increasing use of automatic facial recognition (AFR), unmanned aerial vehicles (UAVs), automatic number plate recognition (ANPR) and body worn video cameras (BWVs).

Not only has CCTV gone from strength to strength in supporting and aiding the emergency services, its set to become an even bigger asset to the teams within the control rooms.

A significant opportunity exists in harnessing data from disparate sources, such as CCTV footage and digital evidence, and translating it into actionable insights. Paired with artificial intelligence, new digital technologies will enhance decision-making and automate manual processes, resulting in faster case completions. Moving forward, predicting crime and emergency situations through better data analytics and new technology, such as biometrics, coupled with platforms for enhanced community engagement will provide a more effective emergency service and create safer communities.

Benefits to the control room

  • Realtime monitoring
    By integrating AI in to CCTV enables alerts and triggers to be installed, for example when a bag in left unattended in an airport or an incident is happening on the motorway. An automatic alert or signal allows the emergency services to be proactive instead of reactive and start responding instantly.
    This changes the traditional use of CCTV for monitoring events, situations and incidents once reported and alerted.

  • Improved accuracy
    With AI, companies are developing technologies that are designed to make video search as easy as searching the internet. Tools like these can help operators quickly locate a specific person or vehicle of interest across all cameras within a site.

    When an operator is provided with physical descriptions of a person involved in an event, this technology allows them to initiate a search by simply selecting certain descriptors, such as gender or clothing colour. During critical investigations, such as in the case of a missing or suspicious person, this technology is particularly helpful as it can use those descriptions to search for a person and, within seconds, find them across an entire site.

  • Improved Efficiency
    CCTV feeds have historically been monitored by humans. Not only are humans unable to concentrate for long periods of time but monitoring multiple camera feeds at the same time is both inefficient and ineffective, as well as labour intensive.

    Modern CCTV cameras are of course equipped with motion detection software and the ability to record in the dark, but these features can be ineffective, with wildlife or even movement of vegetation causing alarm activations. This coupled with the human inability to discern significant events after a sustained period of monitoring video means that there’s a need for AI to bridge that gap, changing CCTV cameras from a passive observer to an active one.

    AI enabled CCTV is already able to discern between a vehicle, an animal or a human, making alarm activations less frequent and more reliable.

  • Integrate other useful technology

    Once we start to apply AI to CCTV, it naturally opens the door for other technologies to be used side by side – making the function even stronger.  Applications such as facial recognition or object recognition can be used to help identify suspects or objects that shouldn’t be present. 

iStock-696593420.jpg

CCTV In action

Fire and Rescue services already use CCTV on their incident command units, but the introduction of AI enables the unit to become additional eyes and ears on scene – a direct line of communication into the control room.

Integrating heat information and object recognition into the CCTV could help save lives of not only the public but the fire crew. 

Manage and evaluate emergency incidents

Proactive communication

CCTV is becoming more proactive rather than reactive. AI will be able to identify suspicious actions of individuals that look like they may be about to commit a crime. From noticing someone picking up a large number of the same item from a shelf, to spotting someone that looks like they’ve been loitering in a location for too long, AI will be able to spot these actions and alert a human, to allow further investigation of the situation.

Further still, AI will be able to recognise persistent offenders and their vehicles, perhaps even alerting staff to their presence on site before they have even entered a businesses’ premises.

Protection to assets, people and public

Cumbria Constabulary published their 2017 statistics of CCTV usage over a year, and these statistics show the value of CCTV. 4,070 incidents were tagged for CCTV, 467 missing person CCTV incidents, 545 incidents where an arrest was made, and 465 incidents retained for evidence. Interestingly, an area which would support the requirement for applying AI to CCTV is 185 intelligence reports submitted by operators – this is a low number in comparison to the other statistics and shows the room for improvement of auto alert and triggers to incidents, as well as highlighting that this is still a manual activity which could be enhanced.

Public concern

In all cases of public recording, there will always be complaints over privacy and how intrusive CCTV could potentially become, and the management of privacy policies will need to be tightly monitored.

Many of the issues that may raise public concerns in the future will be related not simply to the cameras themselves but to the advanced analytics technologies to which these cameras could be connected. Practically this suggests that there is a need for new standards and guidance to cover the operation and use of some of these technologies. Current standards such as BS EN 62676 are good at setting standards for and guiding the installation of traditional CCTV systems, but do not cover the use of more advanced technologies such as automatic facial recognition and video analytics. They don’t address issues of cybersecurity either, which are increasingly relevant as surveillance camera systems become part of larger data networks.

GDPR and CCTV

The GDPR (General Data Protection Regulation) came into effect across Europe on 25th May 2018. Its introduction enforced stricter rules in the way businesses process personal data, ultimately giving individuals greater control of how their information is handled.

As surveillance via CCTV involves the recording of personal data i.e. images of identifiable individuals captured in the footage, it falls under the GDPR regulations. And whilst the ICO (Information Commissioners Office) are still to publish any definitive guidance on what a GDPR-compliant CCTV system must include, there are several clear requirements within the existing Data Protection Act 1998 which are already established practice. These include:

- Displaying appropriate signage informing people CCTV is in operation and for what? purpose.
- Ensuring recorded images are not retained for longer than necessary.

The surveillance camera systems operated by police forces in England and Wales that typically fall within the Surveillance Camera Commissioner’s remit are CCTV, automatic number plate recognition, body worn video cameras, unmanned aerial vehicles, helicopter borne cameras and indeed other systems such as dashboard mounted cameras. Emerging technologies such as facial recognition systems are also specifically included within the Surveillance Camera Code.

After recent consultation with Chief Officers in the emergency services the following recommendations have been made:

  • All police forces in England and Wales identify a senior responsible officer who has strategic responsibility for the integrity and efficacy of the processes in place within the relevant authority to ensure compliance with the Protection of Freedoms Act.

  • Police forces conduct a review of all surveillance camera systems operated by them to establish whether those systems fall within the remit of the Protection of Freedoms Act. Where systems are so identified there should be processes in place that enable the police to discharge their responsibilities effectively

  • It is recommended that the National Police Chiefs’ Council (NPCC) representative for CCTV considers the workstream being conducted under the umbrella of the National Surveillance Camera Strategy to deliver a national service level agreement framework for CCTV between the police and local authorities with a view to providing support to its delivery.

iStock-1139860444.jpg

There’s no denying it, the role of AI in the emergency services today is becoming transformative. AI-powered CCTV is helping to reduce the amount of time spent on surveillance, making operators more efficient and effective at their jobs. By removing the need to constantly watch video screens and automating the “detection” function of surveillance, AI technology allows operators to focus on what they do best: verifying and acting on critical events.

Enforcing Britain's laws and protecting the public is ultimately still a human process, but there can be little doubt that these practices will increasingly be enhanced by emerging technologies. These bring with them new challenges of regulation and ethics, that is bound to lead to new tasks for the College of Policing and Her Majesty's Inspectorate of Constabulary and Fire & Rescue Services (HMICFRS).

Find out more

If you'd like to find out more about how we can help your control room take advantage of the latest technology, let us know at hello@apdcomms.com or call us on 01482 808300.

Sources:

Surveillance Camera Commissioner Annual Report 2017/18 - https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/772440/CCS207_CCS1218140748-001_SCC_AR_2017-18_Web_Accessible.pdf