The plugins that you can use in Smart Retail applications are designed to meet the need for great versatility so that you can combine them according to your needs. They are designed using the most modern Artificial Intelligence methods and developed by optimising the code in such a way that, for the same functionality provided and image resolution, they are much faster.

One of their special features is that they can be used on multiple hardware platforms: edge side (on cameras), server side, or on the AI Appliance platform. Their integrability is practically unlimited, as they support most of the communication protocols used today, such as MTTQ, FTP, MQTT and many others.

AI-Bio

AI-BIO is a video analytics application that is capable of detecting faces using a detector based on deep neural networks, and analysing them in order to recognise features for each face that are both static (such as gender, age and ethnicity) and dynamic (such as the emotion at any given moment). Face classification is performed by using an advanced artificial intelligence technique based on multitask learning. AI-Bio also allows to evaluate the time a person stays in front of the camera.
The app requires the use of a camera positioned at a height of about 1.80 metres, so that people’s faces are framed frontally.

AI-Crowd-Deep

AI-CROWD-DEEP allows to estimate the number of people present within an area; this is done by using the most advanced vision and artificial intelligence algorithms, combined with a deep neural network capable of detecting people within the scene. It can also generate an alarm in case of overcrowding situations (i.e. the number of people in an area is above a certain threshold), in case of gatherings or when the social distance between people is not respected. AI-CROWD-DEEP can be used both indoors and outdoors, and guarantees accuracy and recall of more than 90%.

AI-Retail-Deep

AI-RETAIL-DEEP makes it possible to estimate the number of people present within an area and to count the number of people crossing a virtual line; this is achieved by using the most advanced vision and artificial intelligence algorithms, combined with a deep neural network capable of detecting the people within a scene. It also allows an alarm to be generated in the event of overcrowding situations (i.e. the number of people in an area exceeds a certain threshold), in the event of gatherings or where the social distance between people is not respected. AI-RETAIL-DEEP can be used both in indoor and outdoor environments, guaranteeing accuracy and recall of 90%.

AI-People

Using the most advanced computer vision algorithms, AI-People is able to count people at gates by detecting people passing through fully configurable virtual sensors. AI-People requires the use of a camera positioned with an overhead view and guarantees 95% accuracy and 85% recall in indoor environments and 85% accuracy and recall in outdoor environments.

AI-People places no limits on the number of virtual sensors and can work with multiple people passing by, both if they walk in the same or if they walk different directions, as well as in the presence of backpacks, luggage or shopping trolleys.

AI-Heat

Thanks to the use of the most advanced artificial vision algorithms, AI-HEAT analyses the movement of objects moving within the scene and identifies the areas of greatest interest (hot spots) and the areas of least interest (dead areas), this is achieved thanks to a heatmap-based visualisation. AI-HEAT can be used in both indoor and outdoor environments.

AI-Occupancy

AI-OCCUPANCY is a video analytics application that uses advanced artificial vision algorithms to assess the movement of objects within an area and estimate the relative occupancy rate. AI-OCCUPANCY can also generate an alarm as soon as the occupancy rate becomes higher (or lower) than a threshold set by an operator during the setup phase.

AI-OCCUPANCY can be used both indoors and outdoors. The app sets no limits on the number, shape and position of virtual sensors that can be placed in the scene.

AI-Crowd

Thanks to the use of advanced artificial vision algorithms, AI-CROWD can estimate the number of people moving within an area. AI-CROWD can also generate an alarm as soon as this number exceeds a threshold set by the operator during the configuration phase.
AI-CROWD requires the use of a camera positioned with an overhead view, so its use is recommended in indoor environments. The app places no limits on the number of areas that can be configured in which to perform the analysis.
Menu