AI Smart Surveillance

In the context of Smart Surveillance applications, you can use the large number of plug-ins specifically produced by A.I. Tech and which can be used in combination according to your needs. They are designed using the most modern Artificial Intelligence methodologies and developed by optimising the code in such a way that they are much faster while providing the same functionalities and the same image resolution.

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, thanks to the support of most of the communication protocols used today, such as Modbus/TCP and HTTP, to drive Remote/IO devices, as well as about a dozen third-party VMSs.

AI-Intrusion

AI-INTRUSION-DEEP is a video analytics app based on the most advanced artificial intelligence and computer vision algorithms. It can detect intrusions, in terms of access and/or persistence in a sterile area (sterile zone detection), virtual line crossing (crossing line or tripwire detection) and multiple virtual line crossing. In addition to the real size of the object (obtained thanks to an advanced 3D reconstruction mechanism of the scene), AI-Intrusion-Deep uses a deep neural network to filter objects according to their class (human, animal, vehicle). AI-INTRUSION-DEEP places no limits on the number of virtual sensors that can be defined within the scene and can be used both in indoor and outdoor environments and in combination with both traditional and thermal cameras.

AI-INTRUSION-DEEP is the ideal video analysis solution to meet security needs. It can be installed indoors, for example in museums, shops, shopping centres and factories, but also outdoors, for perimeter protection, for example in private homes, industries, factories and airports.

AI-INTRUSION is a multi-platform application, and can be installed on more than 20 different hardware platforms including cameras (edge), small processing systems (embedded devices), workstations and servers.

Edge

Embedded

Server

If you have chosen to use a workstation or server-based solution, please connect to our system design support portal: AI-DESIGNER.

AI-Intrusion can send alarms in the following situations:

Crossing of a virtual line by an object of interest
Crossing of a virtual line sequence by an object of interest
Entry and persistence of an object of interest in a monitored area

AI-Intrusion allows to choose between the following objects of interest: people, animals and vehicles.

AI-Intrusion supports more than 20 notification protocols, including third-party VMS, standard protocols (such as HTTP, FTP, MODBUS and MQTT) and A.I. Tech proprietary protocols, which allow the notification of events to A.I. Tech dashboards. More details on the notification mechanisms are available at this link.

In particular, AI-Intrusion allows alarms to be sent to more than 10 VMS. Where no VMS is available, AI-DASH-PRO can be used with its built-in alarm management capabilities.

Installation constraints

Video tutorial

Online help

Flyer

AI-FaceDetect

AI-FACEDETECT is a video analytics app that can detect faces within an area, generating an alarm if faces are (or are not) covered by a mask. The app utilises the most advanced deep neural networks for both face detection and face analysis.

AI-FACEDETECT requires the use of a camera positioned with a frontal view at human height and can be reliably used in both indoor and outdoor environments.

AI-FACEDETECT is the ideal video analytics solution to meet the security needs in all those areas where it is necessary to verify that people are wearing face masks. Examples include shops, banks, gyms, museums, offices, universities, sports halls, stations and airports.

AI-FaceDetect is a multi-platform application, and can be installed on more than 20 different hardware platforms including cameras (edge), small processing systems (embedded devices), workstations and servers.

In addition, all functions offered by AI-FaceDetect-Deep are also available as services accessible on the cloud. For more details on the specifics of the services, see the dedicated section.

Edge

Embedded

Server

If you have chosen to use a workstation or server-based solution, please connect to our system design support portal: AI-DESIGNER.

AI-FaceDetect-Deep supports more than 20 notification protocols, including third-party VMS, standard protocols (such as HTTP, FTP, MODBUS and MQTT) and A.I. Tech proprietary protocols, which allow the notification of events to A.I. Tech dashboards. More details on the notification mechanisms are available at this link.

Installation constraints

Video tutorial

Online help

Flyer

AI-Fire

AI-FIRE is a video analytics app that uses deep neural networks to enable early flame detection. The app is particularly useful in all those environments where traditional fire detectors are ineffective or cannot be used, like large indoor and outdoor environments, such as factories, car parks, waste management areas, or even forests and woodlands; even at a great distance from the installation site of the cameras.

The app does not require the use of thermal cameras, and places no limits on the number of areas that can be configured within the framed scene.

AI-FIRE is the ideal video analysis solution to meet the needs of securing spaces. The app can be used in indoor environments (e.g. homes, museums, shopping malls, factories, warehouses), as well as in outdoor environments (e.g. parks, landfills or storage sites).

AI-Fire is a multi-platform application, and can be installed on more than 20 different hardware platforms including cameras (edge), small processing systems (embedded devices), workstations and servers.

Edge

Embedded

Server

If you have chosen to use a workstation or server-based solution, please connect to our system design support portal: AI-DESIGNER.

AI-Fire is able to send alarms when flames are detected within a monitored area.

AI-Fire supports more than 20 notification protocols, including third-party VMS, standard protocols (such as HTTP, FTP, MODBUS and MQTT) and A.I. Tech proprietary protocols, which allow the notification of events to A.I. Tech dashboards. More details on the notification mechanisms are available at this link.

AI-Fire allows alarms to be sent to more than 10 VMS, if you don’t have a VMS you can use AI-DASH-PRO with its built-in alarm management capabilities.

Installation constraints

Video tutorial

Online help

Flyer

AI-Smoke

AI-SMOKE is a video analytics app that uses deep neural networks to achieve early smoke detection. The app is particularly useful in all those environments where traditional fire detectors are ineffective or cannot be used, like large indoor and outdoor environments, such as factories, car parks, waste management areas, or even forests and woods; even at a great distance from the installation site of the cameras.

The app does not require the use of thermal cameras, and places no limits on the number of areas that can be configured within the framed scene.

AI-Smoke is the ideal video analysis solution to meet the needs of securing spaces. The app can be used in indoor environments (e.g. homes, museums, shopping malls, factories, warehouses), as well as in outdoor environments (e.g. parks, landfills or storage sites).

AI-Smoke is a multi-platform application, and can be installed on more than 20 different hardware platforms including cameras (edge), small processing systems (embedded devices), workstations and servers.

Edge

Embedded

Server

If you have chosen to use a workstation or server-based solution, please connect to our system design support portal: AI-DESIGNER.

AI-Smoke allows you to send alarms when the presence of smoke is detected within an area under monitoring.

AI-Smoke supports over 20 notification protocols, including third-party VMS, standard protocols (such as HTTP, FTP, MODBUS and MQTT) and A.I. Tech proprietary protocols, which allow the notification of events to the dashboard dashboards of A.I. Tech. You can get more details on the notification mechanisms available at the following link.

AI-Smoke allows you to send alarms to over 10 VMS, where you do not have a VMS you can use AI-DASH-PRO thanks to the integrated alarm management functionality.

Installation constraints

Video tutorial

Online help

Flyer

AI-Spill

AI-SPILL is a video analytics app that enables the detection of a person falling within an area of interest. The app combines an advanced mathematical model to analyse pose variations, and therefore falling movement, with the most advanced deep neural networks for object classification, thus allowing people to be distinguished from other objects in the scene.

AI-SPILL places no limits on the number of configurable areas within the framed scene. The app can be reliably used in both indoor and outdoor environments.

AI-SPILL is the ideal video analytics solution to meet the security needs of hospitals, nursing or retirement homes for the elderly, or more generally in all those applications in which it is essential to detect patients’ or guests’ falls in real time, in order to guarantee a prompt response from the competent personnel.

AI-SPILL is at the same time the perfect gift for the private homes of the elderly, as it allows family members to be alerted in real time in the event of a fall. AI-SPILL can also be used in schools, in order to protect students by detecting falls in corridors and unattended areas.

Other areas of application are warehouses or cold rooms in warehouses, and more generally all those areas where staff rarely enter and therefore, in the event of a fall, the risk of not being able to be quickly rescued by colleagues is very high.

AI-Spill is a multi-platform application, and can be installed on more than 20 different hardware platforms including cameras (edge), small processing systems (embedded devices), workstations and servers.

Edge

Embedded

Server

If you have chosen to use a workstation or server-based solution, please connect to our system design support portal: AI-DESIGNER.

AI-Spill allows you to send alarms when the fall of a person is detected within the area under monitoring.

AI-Spill supports over 20 notification protocols, which include third-party VMS, standard protocols (such as HTTP, FTP, MODBUS and MQTT) and A.I. Tech proprietary protocols, which allow the notification of events to the A.I. Tech dashboards. You can get more details on the notification mechanisms available at the following link.

AI-Spil allows you to send alarms to over 10 VMS, where you do not have a VMS you can use AI-DASH-PRO thanks to the integrated alarm management functionality.

Installation constraints

Video tutorial

Online help

Flyer

AI-Masking

AI-MASKING is a video analytics app that allows you to guarantee people’s privacy, thanks to the ability to mask in real time specific areas of interest, statically identified, or in general any moving object within one or more areas of interest within the scene framed by the camera.

AI-MASKING can be used both indoors and outdoors and there is no limit to the number of areas to be defined, whether these are areas where masking should always be performed, areas where masking should never be performed or areas where only moving objects should be masked.

AI-MASKING is the ideal solution for all those contexts in which it is important, in order to ensure compliance with privacy regulations, to allow the visualisation of masked video streams on monitors visible to people passing by (i.e. not security personnel), while recording the video stream in unmasked mode on a VMS or NVR.

Examples of such contexts are shops, shopping centres, museums, hospitals, airports, stations, factories, car parks or cities.

In a shop, for example, it is possible to display the video streams of all the cameras installed in the point of sale on the monitors installed near the cash desks. Furthermore, in a city, AI-MASKING allows the masking of the video stream acquired by the cameras located in the various areas, allowing citizens to view it publicly on the Internet without the need for special access credentials.

AI-Masking is a multi-platform application, and can be installed on more than 20 different hardware platforms including cameras (edge), small processing systems (embedded devices), workstations and servers.

Edge

Embedded

Server

If you have chosen to use a workstation or server-based solution, please connect to our system design support portal: AI-DESIGNER.

Unlike the other apps, AI-Masking does not generate events, but it exports the masked video stream over http protocol, encoded in MJPEG.

Short configuration video showing the different masking modes.

Flyer

AI-Lost

AI-LOST is a video analytics app, based on the most advanced computer vision algorithms, that allows you to 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 for indoor and outdoor environments and in combination with both traditional and thermal cameras.

AI-LOST is the ideal video analysis solution to meet security needs. It can be installed to detect suspicious abandoned objects such as luggages in public places like train stations, universities, squares, shopping malls, museums or for the automatic detection of wastes in streets and parks.

AI-LOST can also be a useful tool for detecting theft in museums, through the detection of removed objects such as paintings or statues.

AI-Lost is a multi-platform application, and can be installed on more than 20 different hardware platforms including cameras (edge), small processing systems (embedded devices), workstations and servers.

Edge

Embedded

Server

If you have chosen to use a workstation or server-based solution, please connect to our system design support portal: AI-DESIGNER.

AI-Lost allows alerts to be sent in the following situations:

An object is placed in the area being monitored and is left there for longer than a configurable time interval.
An object in the monitored area is removed from the scene.

AI-Lost supports more than 20 notification protocols, including third-party VMS, standard protocols (such as HTTP, FTP, MODBUS and MQTT) and A.I. Tech proprietary protocols, which allow the notification of events to A.I. Tech dashboards. More details on the notification mechanisms are available at this link.

AI-Lost allows alarms to be sent to more than 10 VMS, if you don’t have a VMS you can use AI-DASH-PRO with its built-in alarm management capabilities.

Installation constraints

Video tutorial

Online help

Flyer

AI-PPE

AI-PPE is the video analytic app, based on the most advanced artificial intelligence algorithms, designed to detect the presence of workers inside the monitored areas and rising alarms in case some of them are not using Personal Protective Equipments (PPE) like helmets and reflective vest.
There are no restrictions on the number of workers and areas to be monitored; the app is able to deal with multiple workers and areas simultaneously and can be used both indoors and outdoors.

AI-PPE is the video analytic solution that meets safety and privacy to guarantee a constant monitoring of workers in environments where using PPE is mandatory.
Typical use cases are public and private construction sites or industries, where wearing PPE is required by law to ensure workers’ safety.

AI-PPE is essential for safety managers as well as for workers, the real-time continuous monitoring allows to immediately notify wrong behaviors and forgetfulness. Thanks to the possibility of masking the video stream, the app also ensures full compliance with current privacy regulations.

AI-PPE is a multi-platform application, and can be installed on more than 20 different hardware platforms including cameras (edge), small processing systems (embedded devices), workstations and servers.

Edge

Embedded

Server

If you have chosen to use a workstation or server-based solution, please connect to our system design support portal: AI-DESIGNER.

Events can be sent to external servers using over 20 different mechanisms, which include third-party VMSs, standard protocols (such as HTTP, FTP, MODBUS and MQTT) and also A.I. Tech proprietary protocols, which allow the notification of events to the dashboards of A.I. Tech. You can get more details on the notification mechanisms available at the following link.

Flyer