When it comes to situational awareness, video surveillance is an impressive tool with a wide range of benefits. However, because of concerns with privacy, the audio element is often under-used. Benchmark considers the role of audio analytics in the creation of credible solutions.
or many years, video surveillance has led the way with regard to situational awareness. The role of intelligent video analytics has pushed the boundaries, and ensured that the benefits of video are enhanced. Today, the power offered by a well designed and correctly implemented video system using IVA will be unsurpassed by most other technologies.
Whilst video surveillance continues to grow – both in terms of scale and efficiency – in the UK and other parts of the world, and is accepted by the vast majority as a tool to fight crime and enhance management, audio surveillance has not been equally embraced. This is despite it being of significant value in evaluating events.
A few years ago, Benchmark visited an educational environment and was discussing its system with the security manager. He explained that his biggest frustration was the inability to deploy audio surveillance across the site. There had been incidents when pupils had been in the grounds out of school times, and had been confrontational and at times threatening when approached by staff. However, this was not obvious when the video footage was viewed.
Such anecdotal evidence is not unusual, and does serve to highlight how some incidents can be difficult to assess if there is no audio. If a conversation takes place between a passer-by and on-site personnel, what is actually happening? Is it an innocent conversation, is a potential intruder being warned off, or is it an attempt at collusion? Without a clear and verifiable understanding of what is being said, often incidents come down to little more than one person’s word against another’s.
The issue with audio surveillance is predominantly one of privacy. People do not want to be listened to. They view such an action as snooping or eavesdropping, and as such they feel it infringes their rights. Whilst their actions and movements might be open for analysis via CCTV, their words are held as more private. For example, whilst few workers will object to the use of CCTV in the workplace, resistance to audio surveillance remains high.
Whilst audio surveillance might be limited in its applications, there are still many benefits that audio information can offer. One example is the ability to detect audio exceptions via intelligent analytics, allowing automated responses to unusual, unexpected or predefined sounds.
Audio analytics predominantly appear in the surveillance sector in one of two guises. The most basic form is as an edge option, where a camera equipped with a microphone features an audio detection function. Such functionality is often basic, and generally allows the detection of any sound above a defined volume threshold.
This might initially appear to be limited, and whilst specific noises cannot be identified, general exceptions can be used to trigger alarms.
For example, if you consider an office environment where interactions with the public take place, an exception might include someone shouting at staff, a door being slammed, a screen or desk being banged, etc.. All these incidents might represent a cause for concern. However, analytics based solely on volume would also generate an alarm if a baby was crying, or if an item was dropped, or during thunder storms!
Whether this is acceptable or not very much depends upon the operational requirements of the system. If the role of the analytics is to alert an operator or security personnel to an event, with an onus on them then verifying the situation, it may be acceptable. Such alerts could be sent to a handheld device. However, if the rate of nuisance alarms is high, the effectiveness of the system may suffer as alarms are ignored.
If a more intelligent solution is required, a system should be sought which can differentiate specific sounds whilst ignoring others, regardless of their volume.
With the ability to differentiate specific sound signatures, the power of audio analytics becomes more obvious. The ability to filter and identify whether an alert is created by breaking glass, a gun shot, a crying baby, an impact, aggressive behaviour, fire or smoke alarms, keywords, machinery malfunctioning (or even stopping) makes audio analytics a powerful tool for both security and business management.
Some providers of audio analytics can offer software-based sensors, and claim that these will work with standard cost-effective microphones. Many of the providers come from the world of call centres, where software-based audio analytics has been used for many years to track fraud patterns and for keyword targeting. Now they are teaming up with VMS providers as the potential for audio analytics as a security tool grows.
A platform for success
A growing number of camera manufacturers are now utilising pare processing power in modern chipsets to allow installers and integrators to run Apps on devices. As solid state storage is implemented in camera, and application platforms expand, so the industry will see significant growth in this sector. A number of the major manufacturers have already taken this approach.
Higher level audio analytics is one tool which is tailor-made for such an approach, allowing installers and integrators to select the specific audio software sensors required for any given application. This reduces costs, as there will often not be a requirement for a full suite of sensors.
As with all App-based functionality, installers and integrators can take a ‘mix and match’ approach to ensure they maximise the potential on offer from what is a very significant and powerful detection option.
As with many things in surveillance today, there exists something of a debate over whether analytics are better served by being executed centrally or at the edge. Some will argue that the process is better deployed centrally by a dedicated server running multi-channel software. Others believe that analytics at the edge sits better with modern system design, which can also deploy recording at the edge to enhance system design and leverage cost savings.
Many audio analytic providers will stress that their sensors are compatible with low cost microphones, and given that many camera are equipped for two-way audio – using either integral or optional discreet microphones – it makes sense to minimise installation time and use existing devices.
Often the decision will be based upon existing equipment, and if IVA is deployed then the audio analytic element will typically mimic the video analytics set-up.
Most audio analytic providers can support either approach, thereby allowing installers and integrators to treat the addition of audio analytics as something of an ‘up-sell’ rather than a significant change to legacy solutions.
Audio analysis for alarm triggering is currently widely available as an integral feature of cameras and encoders. Whilst the majority of options are limited by the fact they are volume-based, they can still deliver benefits in a wide range of applications. However, in terms of reliability, they must be considered in a similar way to contrast-based VMD.
For those seeking a higher degree of intelligence, then systems using advanced processing and filtering are become more common.
For many seeking such solutions, the two possible paths are seeking out an advanced camera with the capability to run third party applications, or ensuring that the VMS being used offers support for the audio element as a plug-in or device.
Whichever route is taken, audio analytics can significantly enhance a modern solution.