11

Video analytics

What is it?

Video analytics is the process of extracting information, meaning and insights from video footage. Of course video analytics can do everything that image analytics can do plus a bit more.

Whereas image analytics looks at a still image – either that of a photograph or medical scan and seeks to find patterns, anomalies or identify faces in the pictures – video analytics can also measure and track behaviour.

Traditionally, video data was only really gathered on CCTV for security purposes to monitor retail or business premises for shoplifting, malicious damage or employee wrongdoing. The purpose of the video footage was to protect the business and provide evidence if something happened. If nothing happened the recordings would be erased so the tape or digital hard drive could be re-used over and over again. All that data wasn’t saved because a) there was too much of it and b) there was no way to use it.

But again all that has changed. Increases in storage capability and analytics techniques mean that all that video footage is now very useful.

Video analytics can now be used for:

  • identification (face recognition);
  • behaviour analysis;
  • situation awareness.

When do I use it?

You may want to consider using video analytics if you want to know more about who is visiting your store or premises and what they are doing when they get there.

Face recognition can maintain security and also you can use face recognition (see Chapter 10) to find out more about your customers. But because video data is dynamic, not static like image data, you can also use it to monitor your customers’ behaviour and learn more about how they react to offers, etc. It is, for example, now possible to collect data from different CCTV cameras in a retail environment, upload that data to a cloud server without additional infrastructure costs and analyse the footage to see how your customers behave and how they move through the store.

This data can help you to see how many people stop at a particular product display or offer for example, how long they engage with it and whether or not it is working and converting into sales.

You could also use video analytics to reduce costs, risk and assist decision making. For example, there is now software that allows you to automatically monitor a location 24/7; that video footage is then analysed using video and behavioural analytics solution and alerts you in real time to any abnormal and suspicious activity. Once installed and provided with the initial video feed, the software observes its environment, learns to distinguish normal behaviour from abnormal behaviour and sends relevant, real-time alerts to security personnel. The system is also self-correcting, which means that it continuously refines its own assumptions about behaviour and no human effort is required to define its parameters.

What business questions is it helping me to answer?

Video analytics can be incredibly useful in business to increase security and understand more about customer behaviour. It can help you to answer:

  • Who is using our product (e.g. brand scanning in YouTube videos)?
  • How effective is our shop/warehouse/airport/etc., layout?
  • How can we analyse the behaviour and performance of our employees?
  • How can we improve security?

How do I use it?

In order to use video analytics you need video footage. Most businesses, especially in a retail environment, already have this data but they don’t use it behind the basic security backup should something go wrong.

If you already have this data then you may want to consider applying some analytics so you can use it more effectively. Plus because of advances in data storage and technology like cloud computing you don’t need to invest a great deal more in order to yield some really powerful insights. Data from multiple CCTV cameras can easily be uploaded to a cloud server for analysis and insight that can help you to deliver better service and provide more enticing offers that your customers respond to.

If, for example, you have a display in your store but no one is stopping at it or picking up the product, you can see this within a matter of days and change the display until it does work.

If you want to know more about video analytics and how to use them you can explore the links at the end of this chapter. Alternatively there are many commercially available video analytics tools and providers on the market that can help you.

Practical examples

I worked with a global retailer to help them utilise video analytics more effectively. Originally they approached me to help them discover how long their customers waited in a queue because they wanted to reduce the waiting time at the till.

We were able to answer this question by using the CCTV footage that was already being recorded. Prior to our involvement each CCTV camera in every store had its own database and it would record the images for a week and then overwrite those images with new footage. Realising that this data held far greater value than simply preventing theft, the retailer decided to connect all the cameras in all its stores to one big cloud database that holds all the CCTV camera data. Specialist software then puts it all together to recognise movement and patterns as well as face recognition. Not only was the retailer able to identify how long people were waiting to queue and reduce that wait time, it was also able to combine all the images from different cameras to see how individuals walked through the store, which aisles they visited and which promotions were working and which ones were not.

Another customer of mine is Prozone, a leader in sports analytics. They collect data gathered from a number of cameras placed around a football or hockey pitch, for example, and track players. The system creates over 10 data-points per second for each player on the field and allows coaches to analyse all activities, on and off the ball, to answer questions like: miles covered by each player, successful and unsuccessful passes or tackles for each player, and even which players best attract opposition players away thus creating new spaces and attacking opportunities?

Video analytics can also assist decision making in complex, highly fluid situations such as aviation, air traffic control, ship navigation, power plant operation and emergency services. Using technology and video footage to alert personnel to changes or anomalies can also help to save lives and prevent crime.

Tips and traps

This type of analytics where it can all happen without a person’s permission is currently a grey area in law. But there will come a time when it won’t be, so always deliver best practice, treat all data with respect and privacy and ensure that if you are using your customers’ video data then you are making sure the outcome is ethical and adds value to them not just your business.

The traps, as with image data, are the privacy issues and you need to make extra sure you stay on the right side of the law and use the data wisely and ethically.

Further reading and references

To understand more about video analytics see for example:

..................Content has been hidden....................

You can't read the all page of ebook, please click here login for view all page.
Reset
52.15.57.3