The efficient and intelligent management of cities is a challenging and requires advanced technological solutions that enable informed decision-making and proactive actions to make the city a safe and livable place for citizens.

AI-Smart-City is A.I. Tech’s solution for turning surveillance cameras installed in a city into smart sensors that can collect data on vehicles and people flows and behaviors, but also identify potentially dangerous situations such as the presence of fire.

The video analytics applications composing this solution are based on the latest Artificial Intelligence technologies and optimized to be installed not only on servers, but also on board of cameras or integrated systems. In addition, thanks to the support of different standard network protocols, they can communicate with most of the systems already present in operations centers as well as with the most popular Video Management Systems (VMS).

To complete the solution there is AI-DASH an interactive web dashboard to collect, visualize, and analyze statistical and historical data, alarms, and perform forensic research (where necessary).

The entire solution is designed to ensure the privacy of citizens, so it does not require the transmission of images or video to external systems, and all transmitted information is anonymized preventing it from being used directly to identify people and/or vehicles.

AI-SmartCity

AI-SMART-CITY is a video analytics application that includes all the features needed to collect data to manage a modern smart city, through the analysis of vehicles and people with advanced deep learning algorithms. The software includes the functionality found in AI-TRAFFIC-DEEP and AI-CROWD-DEEP to provide a comprehensive and configurable solution. Regarding vehicles, the solution enables counting and classification of vehicles crossing a virtual sensor in a given direction.
The classes of vehicles detected: motorcycles, cars, trucks, buses, and bicycles.
AI-SMART-CITY also makes it possible to estimate the color and average speed of vehicles, generating an alert where that speed is above a configurable threshold, determine traffic density in real time, and monitor vehicular flows using the origin-destination matrix. The application can also be used to detect dangerous behavior or abnormal situations on the road in real time, such as wrong-way vehicles, stopped vehicles, reversing vehicles, pedestrians lingering in prohibited areas, or queuing.
AI-SMART-CITY enables advanced analysis of people’s behavior in both indoor and outdoor environments. The solution makes it possible to estimate the number of people within one or more areas of interest and performs a count of people crossing a virtual line. In addition, it is possible to generate an alarm in case of situations of overcrowding, assemblages of people, loitering, or excessive stay of people in an area.

AI-Traffic

AI-TRAFFIC is the video analytics solution based on the most advanced artificial intelligence algorithms that includes all the features found in the AI-ROAD3D and AI-INCIDENT apps, such that it can meet all kinds of needs in the smart road environment.
Specifically, AI-ROAD3D enables counting and classification of vehicles crossing a virtual sensor in a given direction. Three classes of vehicles are detected: motorcycles, cars, and trucks. The application is also capable of estimating the color and average speed of vehicles, generating an alert where that speed is above a configurable threshold. It also allows real-time determination of traffic density and monitoring of vehicular flows using the origin-destination matrix.
AI-INCIDENT is the solution for detecting abnormal situations on the road, such as vehicles driving on contra-roads, stopped vehicles, reversing, or pedestrians lingering in prohibited areas. Finally, it is able to determine any queuing in real time. Image analysis is performed in AI-TRAFFIC by combining an advanced 3D calibration and reconstruction mechanism of the 3D scene along with the most advanced computer vision and artificial intelligence algorithms.
As well as the AI-ROAD3D and AI-INCIDENT apps, AI-TRAFFIC also uses advanced deep learning algorithms to detect and classify objects in the scene (distinguishing vehicles and people); ensuring high accuracy even in extremely complex scenarios, such as in tunnels or crowded city streets, at night or in adverse weather conditions.

AI-Road3D

AI-ROAD3D is the video analytics application for counting and classifying vehicles, in real time, passing through a virtual sensor. The classes of vehicles detected are motorcycles, cars, buses, trucks and bicycles. The application can estimate the color and average speed of identified vehicles, generating an alert where the speed is above a configurable threshold. It is also possible to estimate traffic density, and through advanced calibration AI-ROAD3D can perform a 3D reconstruction of the scene. Finally, it is possible to monitor the flow of vehicles at traffic circles and intersections through the constriction of an origin-destination matrix directly on the application.
AI-ROAD3D uses advanced deep learning algorithms to detect and classify moving objects ensuring high accuracy even in complex scenarios, such as tunnels or in crowded city streets, at night or in adverse weather conditions.

AI-Incident

AI-INCIDENT is the video analysis application for detecting abnormal and dangerous situations on the road in real time, such as vehicles passing on the wrong side of the road, stopped vehicles, U-turns, lane changes, pedestrians lingering in prohibited areas and queuing.
AI-INCIDENT combines an advanced three-dimensional 3D scene calibration and reconstruction mechanism together with the most advanced computer vision and artificial intelligence algorithms.
The application uses deep neural networks to detect and classify objects in the scene (distinguishing vehicles and people), ensuring high accuracy even in extremely complex scenarios, such as in tunnels or crowded city streets, at night or in adverse weather conditions.

AI-Crowd-Deep

Using the most advanced vision and artificial intelligence algorithms, combined with a deep neural network capable of detecting the people within the scene, AI-CROWD-DEEP can estimate the number of people within an area. It also can fire an alarm in case of overcrowding situations (i.e., the number of people within an area is above a certain threshold), in case of gatherings, or where the social distance between people is not respected.
AI-CROWD-DEEP can be used in both indoor and outdoor environments, providing 90% accuracy and recall.

AI-Crowd-Counting

AI-CROWD-COUNTING is a video analytics application that leverages cutting-edge artificial intelligence technologies to accurately estimate the number of people present in highly crowded settings. This solution can operate effectively even in extremely crowded situations.
AI-CROWD-COUNTING complements the functionality found in AI-CROWD-DEEP by providing an additional tool for managing highly crowded situations, such as concerts, sporting events, or street events. In addition, it can be used in conjunction with AI-DASH to store and analyze historical and aggregate information.

AI-Weather

AI-WEATHER is the video analytics application, based on artificial intelligence, designed to monitor the state of the road surface (whether dry, wet or flooded) and the weather conditions of the environment, identifying the presence of sun, rain, snow, clouds, fog and low visibility situations.
AI-WEATHER is the ideal solution for using cameras installed on roads, both in urban and suburban environments, to collect data to be used for statistical purposes, intelligently drive poles with adaptive lighting, or even to generate alerts in case of potential dangerous situations (e.g., flooded tunnel or low visibility on the road).

AI-Rail

AI-RAIL is the video analytics application for detecting obstacles on tracks. The software, based on deep neural networks, can distinguish the following categories of obstacles: people, vehicles and rocks.
The application also can identify the presence of passing trains on the tracks and deactivate itself dynamically; it is also possible to activate and deactivate the application dynamically via software (API) or via hardware (via I/O device), for example, to prevent it from generating alarms while the level crossing is open, and thus allow unrestricted vehicle passage.
AI-RAIL can be used both for monitoring level crossings, in order to verify that they are clear, and in the proximity of tunnels or rocky ridges, where the danger of rockfall is substantial.

AI-Fire+

AI-FIRE+ is the video analytics application that, through the use of deep neural networks, enables early detection of flames and smoke.
The app is especially useful in all those environments where traditional fire sensors are ineffective or cannot be used, such as large indoor environments, or outdoor environments, such as factories, parking lots, waste management areas, or even forests and woodlands, even located at a great distance from the camera installation site.
The app does not require the use of thermal cameras, and places no limits on the number of configurable areas within the framed scene.

AI-Lost

AI-LOST is the video analytics app, based on the most advanced computer vision algorithms, that can detect the presence of abandoned or removed objects in areas of interest.
The app places no limits on the number of virtual sensors that can be defined within the framed scene and can be used in both indoor and outdoor environments and in combination with both traditional and thermal cameras.

AI-Violation

AI-VIOLATION is a video analytics app that makes it possible to detect traffic light violations, i.e. vehicles that cross the stop line when the light is red.

The application also allows the identification of the vehicle that has committed this infraction, its vehicle type among the categories of car, motor vehicle and motorbike as well as average speed and the time elapsed since the red was turned on.

The detection and tracking of vehicles is based on the use of deep neural networks, as well as the analysis of the traffic light status. In fact, the application is able to determine the status of the traffic light (red, yellow, green) automatically, with only artificial intelligence applied to the processing of the video acquired by the camera, without the need for any physical connection with the traffic light.

AI-Detection

AI-DETECTION is a video anlytics application based on advanced artificial intelligence and deep learning algorithms to detect objects (motorcycles, bicycles, cars, trucks, buses, and people) crossing virtual lines for counting, classification, and alerts.

Menu