Dictionary of terms used to describe people counting, queue management, passenger counting, footfall systems, smart city counting and related topics. Any questions get in touch.
Gathers data from Internet-of-Things devices (like smart counters) and serves the information to top level applications seen by people. Merges data from many different sources.
A computer control and automation system for buildings, managing such things as heating and lighting. People counting systems are sometimes part of the Building Management System.
A technology-driven process for collecting and analysing data, and presenting actionable information to help managers make more informed business decisions.
The number of people who make a purchase divided by the number of people who enter the store. If 100 people visit a store, and 5 of them buy something, the conversion rate is 5%.
There are times when two people side-by-side may at first look like one person. Diagonal Split watches for this “one” person splitting into two. This happens, for example, when people enter through narrow doors before spreading out when more space is available.
Records in and out counts: video and thermal counters do this automatically. Some infra-red beam systems rely on you dividing the count by two, although the more expensive beam counters are directional.
Doppler microwave detection devices transmit a continuous signal of low-energy microwave radiation at a target area and then analyze the reflected signal. The detector registers a change in the frequency of waves occurring when the microwave source and the vehicle are in motion relative to one another. This allows the device to detect moving vehicles.
Comparing the number of people entering an area, shop or building over two different time periods – year-on-year or on different days for example. It is also used to compare footfall across different areas or shops.
A video counting system detects people moving through a counting zone. It may be, though, that a person enters the counting zone and then stands still. If they stand still for long enough, the system will consider them to be part of the background. The length of time a person can stand still and yet be counted is called the Freeze Time.
Shows the most popular area of a store or room. The most well-travelled paths through the store are represented by colours overlaying a photo of the area.
An inductive loop may be used in vehicle counting. It is a square of wire embedded into or under the road. The loop utilizes the principle that a magnetic field introduced near an electrical conductor causes an electrical current to be induced. In the case of traffic monitoring, a large metal vehicle acts as the magnetic field and the inductive loop as the electrical conductor. A device at the roadside records the signals generated.
A sensor sends a beam to a reflector on the the opposite side of the doorway. As someone passes through the beam breaks and a person is counted. Accuracy tends to decrease with wide or busy entrances. If two people cross a beam together, for instance, only one count will be recorded. Direct sunlight onto the beam will also affect the system.These were in demand some years ago – now higher accuracy and more comprehensive information is generally demanded.
When a person first enters the counting zone, it may be that two parts of a person enter with a gap between them. For example a person carrying a briefcase might enter first by the case and then with an opposite foot or hand. To prevent this causing two separate people being “seeded”, you can specify a Minimum Separation number of pixels. (Seeding is the first sign of a person.)
Point-of-Sale. The place where a customer completes a transaction, such as a checkout counter. Integrating point-of-sale data with people counts allows conversion rate and other parameters to be calculated.
Radar is capable of detecting distant objects and determining their position and speed of movement. With vehicle detection, a device directs high frequency radio waves at the roadway to determine the time delay of the return signal, thereby calculating the distance to the detected vehicle.
Studying past data to improve decision making and test assumptions. Includes indicators such as conversion rate, average shopping time, number of items per transaction and average spend.
The number of people making a purchase divided by the number of people entering the store. Also known as conversion rate and customer conversion. More…
Hand-held tally counters are the least sophisticated of solutions. A person stands clicking the tally counter whenever anyone passes through the entrance. Tally counters were once used in nightclubs and bars to monitor occupancy, but are now being replaced by automatic counting systems.
Positioned above an entrance, they detect people’s body heat. Quoted accuracies are between 96 and 98%. Accuracy, though, can be affected by the ambient temperature within the counting area being above or below a certain value. Low ceilings can also reduce the accuracy.
When two people are following one another closely it is sometimes not possible to see the gap between them. This may be because the gap is bridged by shadows or perhaps a swinging arm or leg. Tailgating is more likely when the camera is low. A system like Video Turnstile can split people even when there is no clear gap, by simply altering the tailgating or, as it is sometimes known, the mid split setting.
This is the value against which brightness changes in the picture are compared to detect moving people. Decreasing it will make the system more sensitive and may enable the detection of hard-to-see people. Increasing it will tend to remove any shadows and reflections which surround people. This makes it easier to see the gaps between people. On systems like Video Turnstile you can alter the threshold to suit your location.
We define the expected size and shape of a person by two parameters: Typical Width and Typical Area. These are both measured in pixels. The system compares each person with the expected shape and allocates them a score. When people walk so closely together that it is difficult to tell them apart, these parameters help decide whether to count them as two people.