Time to take another look at video analytics
With clear signs that Video Analytics has overcome its bad boy image and with users demanding so much more from their investment in video surveillance systems, Kevin Waterhouse, Executive Vice President of Sales of VCA Technology, offers some timely advice to businesses managers who may be taking a fresh look at what Video Analytics can do for their business.
It was not that long ago that Video Analytics, or Video Content Analysis as some prefer to call it, had acquired a ‘let the buyer beware’ reputation. It seemed that some of the companies promoting this exciting and innovative emerging technology had oversold its capabilities and in the process had understandably attracted scathing criticism from disgruntled users whose expectations had been raised far too high.
Slowly but surely however, all around the world, Video Analytics has established its credibility as a reliable and robust method of obtaining valuable management information, and is increasingly being deployed as an integral component of video surveillance systems. Retail chains in Denmark, France, Finland, Hungary and Spain, an Italian car factory, a prison in China, a University in Estonia, a London sports stadium and hospitals in Japan, are just a few examples of the environments where Video Analytics is being deployed.
In addition to offering security personnel a very powerful tool to detect and combat theft and other criminal activity, the business advantage which cameras equipped with Video Analytics can provide, is compelling. Video Analytics is capable of multi-tasking and so, depending on the field of view, a camera equipped with the technology should be able to simultaneously generate reports with supporting video to provide merchandising, human resources, security and other operational departments, with the information they need to achieve their objectives. Every retail store will, for example, have its own set of challenges, but common to all is likely to be a desire to fully understand why a particular store is performing better than others and if specific marketing activities or promotions have been effective. Video Analytics is able to make a significant and profitable contribution to finding out the answer to these crucial questions.
Recent improvements in the design and processing power of Digital Signal Processor (DSP) chipsets has made it possible for Video Analytics software to operate highly effectively at the ‘edge’, i.e. incorporated into individual cameras instead of being located on a central PC or server. This offers a major benefit to IP network based video surveillance systems in terms of network bandwidth utilisation. With edge devices running the analytics locally, they can be configured to send a video clip only when alarms are detected.
As we all know IP video streams are heavy users of a network’s bandwidth and the cost of running video over a Wide Area Network can easily mount up. A single D1-level video stream, for example, requires 300 Gigabytes (GB) per month of storage and the cost can therefore mount up fast when there is a requirement for a large number of cameras.
So here are some useful tips when considering installing cameras with built-in Video Analytics.
- Try Before you Buy - Insist that the manufacturer provides some cameras for you to test to ensure that their Video Analytics software does what it is intended to do. There are many manufacturers of Video Analytics for you to choose from, each with different strengths and weaknesses. Some manufacturers offer systems targeted at specific situations such as intrusion detection, people counting, vehicle monitoring, abandoned object detection and loitering detection. Do not rely on sales brochures but instead ask the manufacturer you have decided to work with, to seek confirmation that they can meet your client’s specific requirements.
- Every one of your clients will have differing operational requirements and their sites will present different kinds of challenges. It is important therefore that the manufacturer you choose to work with is prepared to expose their cameras to rigorous testing and to help you establish that the Video Analytics built into their cameras is able to deliver high detection and low false alarm rates in environments which match your client’s conditions.
- If the installation is outdoors, make sure the system can handle environmental phenomena such as global illumination changes, (e.g. on a windy day with fluffy clouds), wind (camera shake), rain and fog without generating false alarms. Check that the system doesn’t go “blind” in these situations and can still detect new objects.
- Ensure that sudden scene changes such as a lights-off, lights-on transition, don’t generate false alarms. Check that the system can ‘learn’ following a sudden scene change quickly. Any longer than 20 seconds or so and there is a real possibility of missed detections.
- Look for manufacturers that have had their software independently tested against the UK Home Office i-LIDS image library.
- Avoid locating cameras where nuisance alarms are likely to occur, for example where there is lots of moving foliage, waves, tidal movement, etc. If this is not possible, then problem areas should be masked out at configuration stage. If you plan to install analytics on a PTZ camera make sure it can support automatic detection of presets, since your configuration is likely to be specific to the PTZ location. Some manufacturers offer PTZ cameras with built-in edge analytics: these are the most likely type to support this feature.
- Obtain assurance that the cameras incorporating Video Analytics provide the interfaces you need. This could be anything from a simple contact closure to full metadata output stream. Be clear about how these will integrate into any legacy system or how it will be part of a new installation. Video Analytics is a difficult thing for NVR/DVR manufacturers to integrate, mainly because of the amount of graphical work involved importing user interfaces. Make sure therefore that an integrated system will meet your client’s expectations in terms of interaction between the other component part of the video surveillance system and/or other devices and systems.
- Last but by no means least - User friendliness may be an overused phrase, but it is crucial that it can be applied to Video Analytics. How it is configured can make a huge difference to the performance. When incorrectly configured, there is a serious danger that the software can ignore the activities and events which need to be detected and potentially generate false alarms or false positives. Choose a system with an intuitive interface that is free of confusing controls and engineering language that your clients will struggle to understand, if the user interface looks like you need a PhD to configure it, then you probably do. Remember that unless the software is easy to set up and operate use, it will probably fall into misuse with the users becoming disillusioned when they discover how hard it is to reconfigure, as and when their requirements change.