• Enrolment of the Identities Database by:
o real time acquisition from camera or video streaming devices
o manual entry of images or off-line videos
o importing of face images and data coming from external databases (i.e. police mugshots,
personnel archives, …), by custom project
• Ability to create and manage unlimited groups of identities (white, black, stolen, employees,
authorized, …), among the ones enrolled in the Identities Database
• Ability to configure real time alarm notifications in case of:
o Person recognized among a configured group of persons enrolled in the Identities Database
o Person recognized, but not present in any of the configured group of identities
o Person unknown, not recognized as anyone among the ones enrolled in the Identities
Database
• Ability to create and manage a Transits Database, for the storage of the cropped image and the
relative biometric template of all the faces passed by the cameras processed in real time
• Ability to make forensic queries for:
o comparing a face image in input (a jpg image uploaded manually, or a picture enrolled in the
Identities Database, or a picture stored in the Transits Database) with all the identities
enrolled in the Identities Database, receiving as output a straight match or the first “n” most
likely matches
o comparing a face image in input (a manually uploaded jpg, a picture enrolled in the Identities
Database, a picture stored in the Transits Database) with all the ones stored in the Transits
Database, receiving as output all the images, relative camera and time stamps related to the
faces matching the comparison, according to a certain level of confidence configurable by
the user
• DwellTime function, for the storage of the time between the identification and match of a same
face along 2 correlated active areas
• Ability to provide, for each detected face, the estimation of the relative gender and age

Technical specifications

• Modular, scalable and hardware-independent software architecture, available for Windows o.s.
• Acquisition from:
o IP cameras (optical or thermal), through standard protocols RTSP with encoding formats
Mjpeg, mpeg2, mpeg4, h264, h265
o analogue cameras (optical or thermal), through video encoders or hybrid NVR/DVR
compatible with standard protocols RTSP with encoding formats Mjpeg, mpeg2, mpeg4,
h264, h265
o compatible VMS/DVR/NVR platforms
o video footages, exported in all standard formats (avi, mkv, asf, mpg, mov, …)
o single images, in jpeg format
o USB or integrated web cams
o thermographic sensors, through Genicam protocol
• Automatic and real time notifications through::
o TechnoAware-CentralManager client, local or remote
o compatible VMS/DVR/NVR platforms
o I/O contacts, through Modbus protocol
o http or TCP network sender, customizable
o e-mail, with in attachment the image related to the generated alarm
o FTP client, saving the video clip related to the generated alarm
o configured Telegram accounts
• Real time or off-line fruition of the processed faces identification data through:
o TechnoAware-CentralManager client, local or remote
o VTrack WebInterface
o API based on cgi call, for receiving automatically an xml file through http with the required
data
o compatible third-party platforms
o automatic periodical report in pdf format, customizable by project
• Enabling/disabling of configurations, functions and/or single rules by:
o an interrupt from an external input, through cgi call
o time scheduling, by timetabled configuration
o manual command, through VTrack-CentralManager client
o polling the status of an external I/O through network protocols, such as http, TCP, Modbus
• Built-in database for the storage of the processed events and data
• API for streaming out the real time processed video and/or metadata flow, for being acquired by
compatible third-party platforms
• Ability to manage redundant hardware architectures, by active FailOver function (both cases n:n
or n:1)
• Ability to work in virtualized environments

Configuration features

• Ability to configure unlimited independent active rules, by drawing in the image virtual polygonal
areas or lines of any shape and size
• Unlimited identities enrollable in the Identity Database
• For each enrolled identity, ability to add unlimited relative face templates
• Ability to detect and recognize multiple faces present in the provided images at the same time
• Identity data editing by:
o Manual entry
o Data import from external databases, by custom project
• Ability to filter the detection of target faces not complying a certain minimum quality
configurable by the user
• Ability to filter the detection of target faces not complying a minimum and/or a maximum size
configurable by the user
• Ability to configure a parameter of confidence time for confirming the detection and/or the
recognition of each target face
• Unlimited configurable no-processing areas, to inhibit not-of-interest areas in the image
• Ability to process the acquired video stream at a lower resolution and frame rate
• Ability to crop and process independently unlimited image portions of the acquired video flow
• Ability to set up and activate unlimited configurations of cameras and parameters, according to:
o planned timetable
o manual trigger
o time-based trigger
o time duration trigger
• Ability to import/export configurations previously set up
• Ability to manage different configurations for different configured presets of a PTZ camera
• Ability to process not-fixed cameras moving along a scenario
• Enabling/disabling of the modules by:
o an interrupt from an external input, through cgi call
o time scheduling, by timetabled configuration
o manual command, through VTrack-CentralManager client
o polling the status of an external I/O, through http or TCP call
• Ability to configure different user profiles, allowing to enable or to inhibit the access to the
configuration of the modules

Additional built-in diagnostic functions

• Tampering module, for configuring and triggering an alarm on detection of camera obscured,
dazzled or moved for longer than a configured time
• QualityCam module, for configuring and triggering an alarm on camera’s reduction of visibility
(i.e. because of dirt, or defocusing) and/or misalignment
• VideoLoss function, to trigger an alarm notification in case of a loss of communication with a
video source
• Watchdog function, for the automatic restart of the module in case of critical error or eventual
restart of the hardware unit
• HeartBeat function, for the periodical notification of the correct working of the module to an
external device
• CheckConfig function, for checking by a html/xml request the status of the active configuration
• Writing and storing of log files for each main process of the module
• Monitor Client, for configuring automatic notifications in case of misfunctioning events of the
connected VTrack modules

• Conditions of the target faces in the image for maximizing the detection and the identification
performances:
o clearly visible to the naked eye in the image, even in difficult environmental conditions
(night, heavy rain, snow, fog, sun glare, reflections, artificial lights, under/overexposed
camera, obstacles, …)
o with such a resolution in order to guarantee at least 80 pixels between the centers of the
eyes, at the point where the face is meant to be identified in the image
o with an angle of radial inclination in respect with the camera not larger than 20°-25°
o with an angle of tilt inclination in respect with the camera not larger than 20°-25°
o entirely visible in the image in the above indicated conditions for at least 10-15 continuous
frames
• Frame rate: such as to ensure good visibility of the target face for at least 10-15 continuous
frames
• Streaming compression rate: it should be as low as possible, or even zeroed off

Processing requirements

• Computational need (*):
o CPU: considering, as reference, a single core with 3.2GHz base speed,
– for video processing:
 up to 3 video streams in parallel processing video flows in VGA resolution (640×480)
at 8 frames per second
 up to 2 functions in parallel processing video flows in 4CIF resolution (704×576) at 8
frames per second
 up to 2 functions in parallel processing video flows in 800×600 resolution at 6 frames
per second
 up to 1 function processing video flows in HD (720p) resolution (1280×720) at 15
frames per second
 up to 1 function processing video flows in FullHD (1080p) resolution (1920×1080) at
8 frames per second
– for templates comparisons:
 about 200k comparisons/second, with a single core 3,2GHz
o GPU: NVIDIA CUDA compatible, according to the always up-to-date page
https://en.wikipedia.org/wiki/CUDA#GPUs_supported
o RAM: 12kB per enrolled template
• Supported OS: Windows, from 10 onwards
(*) These values should be considered as a purely indicative and generic reference and may vary according to the
complexity of the environment, the number and kind of targets, the specific function configured and the typology of
hardware used. TechnoAware strongly suggests to always contact anyway its technical support team for doublechecking and validating for free the hardware meant to be used, for each project, before purchasing it.