An Interview By Nurulain Mohd Suffian, Associate, AutoID & Security, Frost & Sullivan, APAC

Dr Kanga is founder and CEO of iOmniscient, the provider of the most sophisticated video analytics in the industry. Dr Kanga spent 25 years in the computer industry (eventually as Vice President for DEC and then Compaq). In the early eighties, he led the team that developed the world's first commercial Artificial Intelligence system. In 2001, along with his business partner Ivy Li he founded iOmniscient with the objective of developing the most comprehensive and most advanced intelligent video analysis system. Today with over 25000 licenses sold worldwide last year, iOmniscient's technology is well accepted in the market place.

Rustom A. Kanga,
CEO of iOmniscient

1. What is the major advance in the surveillance industry nowadays? Can you define video analytics for us and share more on what iOmniscient offers to the surveillance industry?

The major advances in the Surveillance industry relate to the addition of intelligence to the system.

As recently as a few decades ago, surveillance consisted of Man and Dog teams. Even today a physical presence can be extremely valuable as it enables the “Guard” to take immediate action if an unwanted event is detected. In some situations, as in a crowded cafeteria in an airport, a physical presence is perhaps the only way to protect the environment and to deter criminals.

Over time, it became evident that it was not possible to have sufficient guards to cover every environment that had to be secured and this led to the placement of cameras. These were essentially eyes that complemented those of the guard and allowed the Security team to watch locations that could not be covered by a physical presence.

Right through this technological evolution a human was still required to view the video footage and to understand it. The system did not do any thinking on its own and hence all these systems can be viewed as having no intelligence.

Systems with a “memory” can only recall events after they have happened and are useless in preventing an undesirable event or for reacting to it in real time.

To be preventive in nature and to be able to react in real time, the system needs Intelligence – intelligence to understand what is happening in the video itself so that the security officer can be made aware of a threat or of an incident as soon as it happens or even before it happens. Beyond adding eyes and memory to the system, the addition of Intelligence added the ability to “think”.  It could tell the Security Officer what to look for. It could advise him that a bag had been left in view of Camera 65 or that a person had fallen down on Camera 220 allowing him to focus on events as they occurred and to take immediate remedial action.

This is what iOmniscient offers. Systems can already see and remember. We add the ability to think.

In terms of the various technologies that are available for “thinking” there are simple ones such as Video Motion Detection (VMD) and more sophisticated ones and we have rated these in terms of the IQ going from about IQ 10 to IQ 180 (just as with humans). iOmniscient provides technologies across the whole spectrum but above about IQ 120, which involved the ability to operate in crowded scenes iOmniscient has, international patents and is the only supplier for that level of technology.

So if you want to find a bag left in an empty space it can be found with technology at the IQ 100 level. If however the bag was left in a busy airport and a thousand people obscured it by walking in front of it and after twenty minutes it was still there, it would require IQ 140 level technology to find it. If it was so small and dark as to be invisible to the human eye, you would need IQ 180 it detect that.

2. As you have been in the video analytics business since 2001, what are the changes or differences that you see in the market demand for intelligence for surveillance in Asia Pacific (APAC) today? Where does iOmniscient’s strength lie in this region/APAC?

The intelligence we provide will work with analog or IP systems, as it is not dependent on the mode of transmission. 

Up to even two years ago, end users were just trying out little pilot systems. Today we see them implementing major systems with thousands of cameras. Therefore, there has been a growing level of understanding in terms of what the technology is capable of and a healthy understanding of its limitations.

We now see the more sophisticated clients taking the position that they need to decide on the objective of each camera and hence the analytics they need first. If they do not have an objective for the camera, it is not worth installing that camera. This is a far cry from the old days when people put in a system and then wondered how they were going to use it.

However, this knowledge is not widespread. There is lots of scope for improving the understanding amongst users of the benefits and usage of Intelligent Surveillance technology.

In APAC, we operate in virtually every corner – from India to Australia, from Vietnam to Japan and we have a presence in every major country either directly or through our resellers.

3. Where does this video analytics application take part in APAC today?  And what is the major challenge you foresee in 2008 and coming years for this industry?

In every industry where they use video cameras, there are applications for video analytics.

In shopping centers, the focus could be counting, slip and fall detection (for public liability), theft detection, health and safety applications, crowd management and queue management.

In railways, it could range from security and safety on the platform to queue management for customer service, level crossing systems, applications for preventing people from crossing the yellow line on the platform, graffiti detection and a host of others.

I foresee the education as a major challenge. The traditional user of CCTV systems does not have the opportunity to evaluate all the available technologies in the market. In any growing field, there are often hundreds of players very often offering very limited software and making unsustainable claims.

The market will only mature when people properly understand the strengths and limitations of the technology. They will then be able to make decisions from a position of knowledge and strength.

4. In your opinion what are some of the market drivers propelling the Video Analytics industry today?

The primary market driver is the need for better information. Up to now security systems were used primarily for post mortems after a major event. The management of organizations want their system to respond to their environment in real time and this has resulted in more and more applications being developed using video analysis.

Therefore, with Video Analytics, an organization can know how many people walked through their shops, where they stopped and which routes they followed. In road systems, it can tell them if the traffic is being congested in a certain area. It can tell them if there are vehicles stopped where they should not be, whether there is a fire in a tunnel or whether a car has crossed a red light at a traffic signal.

These and other applications are all driven by the need for better information.

6. Security is seen as one of the key application for video analytics. Can you share your opinion about where you feel this application is heading? Which are the other applications your company focuses on?

Security is certainly a key application for the use of video analytics. Other applications are equally important. For instance in the area of Marketing, counting is a very important application as it allows management to understand people and vehicular traffic flows. It is used for Health and Safety to detect slips and falls and to identify things like fire exits being blocked.

It is used to improve customer service through better queue management.

These other applications are becoming at least as important as security for the organizations themselves.

8. Currently what developments in the market do you think may potentially hinder your company’s growth for its IP Video Surveillance business?

At this stage I don’t see any significant hindrances to growth. Users are becoming more knowledgeable on the technology and that is always goodness as they then use the technology as it should be used.

9. Which areas do you think your company needs to work on to accelerate the company’s growth rate in the video analytics business, taking into consideration the increasing competition?

We are comfortable with our growth rate and we do not focus on growth as such (this is a luxury we have as we are not funded by Venture Capital). We focus on having the best technology and on providing good service. If we can do that then growth is a consequence. So far, our technology is many years ahead of the competition and our customers have been sufficiently happy with what we provide them to bless us with the growth we currently have.

We continue to invest heavily in our R&D, as we want to ensure that we maintain our technological lead, which is our primary differentiation against the very large number of new competitors in the market.

10. What are some of the critical success factor/key must-have factors to compete in the APAC region?

APAC countries are mainly developing countries but most pride themselves on ensuring they have the best state-of-the- art technology. Very often, the systems they have put in place are far more advanced than any one would see in the USA. Therefore, the first thing we have to do is ensure that we are offering world class technology to them.

Second, though we are a global company we understand the need to meet local needs. Almost our software can operate in most local languages.

Third, we recognize that organizations in APAC expect more than just products – they expect good service. For that reason, we have established the infrastructure to provide 24x7 supports in every corner of APAC.

Finally, a key critical success factor for us has been the architecture that we developed from the beginning aimed at large complex environments. Today people talk about IP versus analog and they talk of distributed networking and so on. From the start, our systems have been designed to be totally OPEN, totally distributed and totally scalable. The system can handle any mode of transmission, any type of cameras, any location of storage and so on. It does not matter whether the client system is in a control room or on a wireless PDA.  It does not matter whether the network is local or worldwide. The system is designed to cope. This has been a major strength of ours for the larger sophisticated customers in APAC.

11. The IQ Series solution from iOmniscient Pty Ltd. is interoperable with other existing video surveillance infrastructure. What would you like to say about this? How does this benefit your potential customers and your organization as well?

Our philosophy has always been to operate on an OPEN platform. It is a design objective that our systems must take input from any cameras, work on any computer and provide metadata to any DVR/NVR or other equipment in the network. We can operate with older cameras that may have very poor quality images, low resolution and frame rates and still provide top level detection.

This ensures that the customer’s legacy investment is protected and he does not have to waste money upgrading his infrastructure just to be able to implement video analytics.

12. What are your personal targets for iOmniscient in the APAC market within the next five years?

I would like to have every major serious user of video cameras using our technology for Video Analytics. This may sound overly ambitious. However the fact that only we can provide some of the more complex technologies (namely for operating in crowded scenes) puts us in a position where certainly all the serious users should consider us.