All posts by ianwestmacott

A little planning goes a long way toward achieving analytics success

The odd impulse purchase aside, most people go into a buying decision with a good idea of what they want from their investment.

A couple that is expecting triplets, for instance, knows they can bypass the two-seater sports car or the pickup and look in the SUV or minivan category for a vehicle that will adequately and safely serve their family.

Similarly, a company that is putting in a new video analytics system should outline what it wants it to achieve before selecting, installing and operating it. Or at least that is what best practices would dictate.

Yet, too often the opposite happens. Eager customers and their systems integrators determine the number and styles of cameras camera, ip camera, securitythey want, maybe based on the newest technology or the best deals available, without first exploring exactly what they want to achieve in terms of analytics. So the end result is a system that is inadequate for the application and one that poorly reflects on the quality of the video analytics because it couldn’t perform the necessary functions properly.

Where and how cameras are placed is critical to achieving the most effective outcome with analytics. From camera mounts to the number and type of cameras, many factors can impact the success of video analytics.

Fortunately, you don’t have to go it alone when it comes to planning. Working in conjunction with your systems integrator, or a manufacturer’s representative, take a hard look at what your expectations are for your analytics system: Are you looking to count people coming into your store, or is your goal to read license plates in a parking lot? If you want to count customers, do you also want to measure how long they look at a display? Every activity requires careful consideration regarding the type of camera used and where it is placed.

People counting is best done on a two-dimensional scale, so a camera mounted overhead works well here. If the camera were placed at eye level, and a crowd came into the store, you might not be able to see each person because some people likely would be blocked by those in front of them.

If the goal is to determine who is lingering in a particular spot, however, then a wide-angle camera is the proper choice. And if you want to do both of these things in the same space, you’ll need multiple cameras mounted appropriately.

Lighting is another key consideration when deploying analytics. If a scene goes in and out of shadows frequently, it will affect the accuracy of the information received. Trying to read license plates? Think about how headlights could play havoc with a camera if positioned incorrectly.

Before going ahead with an analytics program, it’s important to consider all of the factors that will impact video quality. From illumination to separating assets and people to dealing with obstructions and movement, all of these can make a great analytics system an ineffective one if not handled properly.

So sit down at that computer — or if you’re old school, get out that pen and paper — and list what you want your system to do. Then go through all the factors that could influence your outcome before making a final selection with the help of an integrator or supplier on cameras and mounts.

The success of your analytics system depends on it. Watch our videos below on victor and VideoEdge video intelligence and analytics.

 

Data overload, or information you can use? | Enter Data Visualization

Security and video surveillance systems can tell us a lot about our business – when the highest number of employees come through the front door, which way they go after they enter the building, or how many times each day a specific door is opened.

The good news is that all of this information and much more – from access control and event reports, video surveillance footage, and associated analytics data – can be captured by various edge devicesand stored within the system. This wealth of data is ready to be analyzed and turned into actionable intelligence that can help to detect and prevent issues in operations, equipment, or policies.

The bad news is…well, it’s the same. Without a means to make sense of it all, this wealth of data can be overwhelming and unusable.

Retailers, for example, are now able to capture minute-by-minute video of people in their stores — moving through the aisles, standing in front of displays, and making purchases at the register. But all of this can just be more video in the recording system if it isn’t put to use.

A data visualization tool can take the vast pools of information — security’s Big Data, if you will — now at the disposal of security personnel and management and turn it into more comprehensible data such as graphs and charts that correspond to particular video clips or POS data.

Perhaps your goal as a security manager is to determine whether you need additional guard coverage within a medical facility. Even though you have a card-based access control system that tells you who is entering the building and when, you now want to look more closely at which areas of the building they are accessing so you can beef up patrols in the more highly trafficked areas.

By deploying people-counting analytics tied to your video system, you can target specific doors or hallways that are covered by cameras and record video each time someone uses that door or enters a hallway.

Data visualization can then take you to the next step, which is putting all those video clips into usable charts. You can sort the data by day, for instance, creating charts that show you days when the traffic patterns are the heaviest. But you can even drill down further, looking at the time of day when particular doors and hallways are most heavily used and chart that information as well. Once you have the data set you want, you can look at the corresponding videos to see the actual activity.

Data Visualization

The result may be that you see the area outside a newly relocated lab is generating a lot of traffic outside of regular business hours. That area may require additional checks by a security officer to monitor the activity.

Retail can definitely benefit from the conversion of information into data visualization. Not only can retailers monitor traffic, just as the security officer did in the previous scenario, but by adding in the POS data, store operators can look at how people movement corresponds with sales.

Using data visualizer technology, it’s possible to create a data set that shows how many people walk by a handbag display, how long they looked at the products, and then how many actually made a purchase. All this is possible just by dragging and dropping the results into the data visualization software — sales from POS, plus those who lingered at the display for more than 10 seconds. Based on the results, it may influence the store owner to add sales staff at certain times of day or maybe relocate a display to a more highly traveled section of the store.

Put simply, data visualization is all about recognizing patterns and trends. Once you’re able to start thinking about all that data in those terms, it is less overwhelming and much more useful. And that really is the good news.

 

Are you already using Data Visualization software with your security footage? If so, in what ways? If not, any thoughts on how it could benefit your business? Please leave your response in the comments section below.

Security Analytics Thwart Retail Theft, But Tell Us So Much More

For one department store, it seemed like business as usual as shoppers perused the racks of merchandise, picking out the latest fashions. But in the security office, the person on duty was alerted to an anomaly — on a merchandising display, an entire section of high-priced jeans had been removed quickly. Was this an overzealous shopper looking to try on multiple pairs, or someone from an organized retail theft ring sweeping up inventory?

In this specific scenario, an officer was made aware of this potential incident through the deployment of video analytics as part of the company’s overall surveillance plan and was able to respond quickly. The retailer had established a set of rules within the system’s software so an alert would be issued if more than half the inventory on that rack was removed in less than one minute —  a common scenario known as “shelf sweep” when shoplifters are at work.

The same analytics that are deployed for high-risk security settings, such as airports and government buildings, are equally at home in a retail setting. Security Analytics Retail: Tyco Security ProductsLike the shelf-sweep rule, similar guidelines can be created so a security officer can be alerted when someone enters a storeroom after hours or when an object, like a package, is left in one place for too long.

But what is equally exciting is that, because of the nature of analytics and its information-gathering abilities, its applications can go well beyond the security realm and become a boon to other store personnel.

Retailers who have included analytics in their security systems to both detect incidents as they happen and aid in forensic investigations of thefts, slip and falls and other activities, are expanding the reach of this investment and applying it to merchandising, marketing and operations.

After all, these cameras are operating 24/7 so why not take this database of information and look at it in the aggregate?

Let’s go back to that department store and see how analytics can help sell some handbags. Data supplied by the point-of-sale system will tell the store operator how many designer purses have sold, but not how many potential sales of those handbags there were on a given day.

By using the video system, the store can track how many people came through the doors (the total pool of potential buyers), and then break it down even further, using rules within the analytics to narrow down how many people walked down the aisle where the handbags were merchandised and then how many of those shoppers lingered for more than five minutes at the display. This information, teamed with the POS data, can now give that store’s manager a conversion rate on the sale of her designer handbags.

Armed with the knowledge of how many bags were sold vs. how many people stopped to look at them, it may mean that the purses are in a great spot or, if the conversion rate is poor, this is an indicator that the bags need to be displayed elsewhere or the signage improved or the price reduced. Analytics won’t read the minds of the shoppers, but the data can provide a good snapshot of what occurred within the store. Using analytics to determine traffic numbers and patterns can aid in where to locate merchandise and even help set the number of checkouts needed on a given day.

From a security standpoint, analytics in video surveillance is a necessary part of doing business, but by expanding the potential of its use, the entire retail operation can benefit — deploying the same equipment, but just tweaking the data to fit each users’ needs.  It can be win-win for both security and operations, and who doesn’t like that?

For more on the role of video analytics as part of a retail security solution, download our recent white paper on Video Analytics in Retail.


Download The Video Analytics White Paper