Our team has built a platform that allows shops, restaurants and other public venues to gather information on their visitors with cameras, connected to the cloud. The system utilizes powerful facial recognition algorithms to detect whether a person has been seen before, their age and other demographics information. Combined with a point of sale integration, the system can provide priceless real-time insights for employees, such as person's past purchases, or recommendations on their purchases. Business owners can get detailed reports on customers, their shopping profiles and various metrics. The system can operate even on consumer grade IP cameras and does not require any servers, which makes the integration easy and inexpensive. The system is optimized for performance and it can complete the full cycle of identification and recommendation faster, than it takes for a person to enter the shop.
Behind the scenes, the system runs at AWS cloud and consists of a video processing fleet, a machine learning cluster, business logic servers and a content delivery infrastructure. Its algorithms are based on cascades of machine learning models and streaming analytics. All processed data is encrypted both in transit and at rest, and depending on the local laws, the system can operate on impersonal data. Its streaming nature and reliance on the cloud allows to easily scale it up and down, which allows to drastically cut down the operational costs due to the nature of retail, that is mostly active during daytime.