People counter has evolved from beam counter to networked people counter over the years. With the rising popularity of Wi-Fi enabled smartphones, the new generation of counters are able to use Wi-Fi counting to measure the metrics more than just the INs and OUTs of the store.
First generation: Beam counters
Infrared beams. 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.
Despite its limitations, infrared counters are still widely used, primarily due to its low cost and simplicity of installation. It counts when a person or object passes and breaks its beam. It’s low cost, but cannot discern people walking side-by-side and is adversely affected by direct sunlight.
Second generation: Networked People Counters with Advanced Image Processing Algorithm
Video counting. 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. Multilayer Background Subtraction, based on color 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 90-95% in various lighting environments. The use of artificial intelligence and pattern recognition functions can further enhance its accuracy. For example, identifying the object size to distinguish non-human objects (trolley, pushchair, etc.) and tracking the object movement (whether it is going in or out).
Third generation: Video Counting + Wi-Fi Counting
Wi-Fi counting. FootfallCam is the first in the world to combine video and Wi-Fi counting technologies into one device. It uses Wi-Fi receiver to pick up unique Wi-Fi beacon signals emitted from the smartphones. While not all people carry a smartphone, Wi-Fi counting can produce statistically significant metrics due to the large sample size available. Wi-Fi counting is gaining 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.
Stereo vision (3D) people counting. Counter is embedded with a powerful 1GHz processor, specifically to run its complex and computationally intensive video processing algorithm. It has the ability to see an object in 3D form; with height, width and depth by viewing a scene from two slightly different angles. Information capture from the two differing views will be combined and interpreted into depth data, which are inversely proportional to the differences in distance to the objects. Depth information allows camera to distinguish a group of people as separate objects, such as one person in front of another. It can count accurately even when more than 10 people come in and out of the store at the same time.
Benefits to Retailers
Comparing with other people counters, RetailCam counter is available at a very competitive price. We are mainly focusing on the traffic analytics for retailers where hardware and system are designed specifically to offer the Wi-Fi metrics for retail industry. That is why we can have predefined reports that are directly applicable to retailers. We aims to provide a specific function that are applicable to many retailers and for many of their stores so that we can offer a cost effective price to all retailers.