|This article needs additional citations for verification. (April 2015)|
A people counter is a device used to measure the number and direction of people traversing a certain passage or entrance, often used at buildings, so that the total number of visitors can be recorded.
- 1 Use cases
- 2 Business intelligence metrics
- 3 Technologies
- 4 References
In retail stores, people counters are part of their essential business intelligence metrics.
Conversion Rate - The use of people counting systems in the retail environment is necessary to calculate the conversion rate, i.e., the percentage of a store's visitors that makes purchases. This is the key performance indicator of a store's performance and is superior to traditional methods, which only take into account sales data. Together, traffic counts and conversion rates how a store arrived at sales, e.g., if year-over-year sales are down, did fewer people visit the store, or did fewer people buy?
Marketing Effectiveness - Shopping mall marketing professionals rely on visitor statistics to measure their marketing. Often, shopping mall owners measure marketing effectiveness with sales, and also use visitor statistics to scientifically measure marketing effectiveness. Marketing metrics such as CPM (Cost Per Thousand) and SSF (Shoppers per Square Foot) are performance indicators that shopping mall owners monitor to determine rent according to the total number of visitors to the mall or according to the number of visitors to each individual store in the mall.
Staff Planning - Accurate visitor counting is also useful in the process of optimizing staff shifts; Staff requirements are often directly related to density of visitor traffic and services such as cleaning and maintenance are typically done when traffic is at its lowest.
Stadiums and venues
For safety, public locations are often rated to hold a certain number of people. Accurate people counting is used to ensure that the building is below the safe level of occupancy. Although, no people counting system is 100% accurate and therefore must not be entirely relied upon for the purposes of health & safety, an electronic people counting system offers a relatively accurate means of managing capacity.
People counting system is gaining popularity in smaller grocery stores due to its falling prices. Small shop can benefit most of the functions that large retailers used to have few years ago.
Museums and libraries
Many non-profit organizations use visitor counts as evidence when making applications for finance. In cases where tickets are not sold, such as in museums and libraries, counting is either automated, or staff keep a log of how many clients use different services.
Business intelligence metrics
People counters can offer businesses more than just the people walking in and out of the stores. By combining Video counting and WiFi counting, the new generation people counters can offer other business metrics that could potentially offer new insights; especially for the retail industry.
The number of people coming in and out of the venue.
Window conversion rate
Window Conversion Rate is the percentage of shoppers who came into the store over the people of people who walk passed the outside of the store. With WiFi counting shops can estimate the number of people walked passed the store. A more accurate method is video counting. While revenue and footfall are important, the number of people who walked pass the store often reflects the true potential of the store location. The Window Conversion Rate often depends on the attractiveness of the shop window design and the effectiveness of marketing campaigns.
Visit Duration is the amount of time visitors stay in the venue. WiFi counting has the ability to track the time when a person carrying a smartphone has entered the venue and when that same person has left the venue. This is an important metric for retailers as many shoppers tend to buy more if they stay longer inside the shop. Visit Duration is often reflects the type of customers are coming into the store and the level of customer service the shoppers are receiving.
The number of people came into the store who had visited the store previously. WiFi counting has the ability to remember the Unique WiFi beacon signal id emitted by shoppers, so if a shopper had previously visit the store, the counter would flag the person as a Returning Customer.
The number of shoppers who came into the store had previously visited other stores of the same chain.
Counts the number of people waiting in line such as people waiting to checkout at a store. 
1st Generation - Beam Counters
The simplest form of counter is a single, horizontal infrared beam across an entrance which is typically linked to a small LCD display unit at the side of the doorway. Such a beam counts a 'tick' when the beam is broken, therefore it is normal to divide the 'ticks' by two to get visitor numbers. Beam Counters usually require a receiver or a reflector mounted opposite the unit with a typical range from 2.5 metres (8 ft 2 in) to 6 metres (20 ft). Despite its limitations, infrared counters are still widely used, primarily due to its low cost and simplicity of installation.
- Non-directional counts
- Can't discern people walking side-by-side
- Can be blocked by people standing in an entrance
2nd Generation: Networked Footfall Counters
Thermal imaging systems use array sensors which detect heat sources. These systems are typically implemented using embedded technology and are mounted overhead for high accuracy. A well tuned thermal counter can achieve accuracy exceeding 98%. Thermal systems may be preferable where privacy concerns are applicable, since they do not capture any identifiable images for counting purposes.
- Cannot differentiate people based on height
- May have difficulty detecting stationary people
Computer vision carries out its processes inside an embedded device. This reduces network bandwidth requirements as only the counting data has to be sent over the network. Robust and adaptive algorithms has been developed to provide excellent counting accuracy for both outdoor and indoor counting using computer vision. Multilayer Background Subtraction, based on colour and texture, is considered the most robust algorithm available for varying shadows and lighting conditions. With the advances in image processing, video count can achieve 98% in various lighting environments. The use of artificial intelligence and pattern recognition functions can further enhance its accuracy.
Stereoscopic vision can help to identify the height of the person coming into the store; e.g. child or pets. Whilst there is no evidence stereoscopic vision does improve the accuracy of the counter, it is often used in queue counting and studying customer behaviours inside the shops.
- Cannot count accurately in dark environments such as nightclubs
- May have difficulty differentiating between people and objects under certain conditions
3rd Generation: Networked Counters + WiFi counting
The third generation of counters collect WiFi probe request signals from shoppers' smartphones and add a number of important metrics for businesses, especially for the retail industry.
WiFi Counting uses WiFi receiver to pick up unique WiFi management frames emitted from the smartphones with a range of up to 100 metres. While not all people carry a smartphone, WiFi counting can produce statistically significant metrics due to the large sample size available. Apple iOS8 attempts to randomise MAC address, however it is making little impact on the effectiveness of WiFi counting.  WiFi counting gained popularity in the retail industry due to the additional business metrics it could offer to retailer: store front conversion, visit duration, returning customers and cross shopping however its future is uncertain due to new anonymity measures being adopted by smartphone vendors.
- Dillon, Chris (30 July 2015). "Sunder Sandher’s tech game changer".
- Paul C. Box, Joseph C. Oppenlander (1976), Manual of traffic engineering studies, Institute of Transportation Engineers, p. 17, retrieved December 21, 2010
- "How the CCTV People Counting System Works". Retail Sensing. Retail Sensing. Retrieved 18 September 2015.
- Technologies, Zebra (2015). "Analysis of iOS 8 MAC Randomization on Loca tioning" (PDF).