October 20, 2014 -
Neurotechnology announced it has released VeriLook Surveillance 3.0 software development kit, which provides real-time biometric face identification using live video streams from single or multiple high-resolution digital surveillance cameras.
The new version is highly intuitive, enabling users to not only identify faces in a crowd but also detect and distinguish people from objects while they are moving through the video frame.
Additionally, the software can detect if a person or object is entering or leaving a specific boundary area, which automatically alerts the system monitor.
Neurotechnology’s smart monitoring technology can be used for a range of applications, including retail and commercial areas, entrance monitoring and counting, automated time-attendance systems, transportation, law enforcement and security systems.
VeriLook Surveillance 3.0 includes a dynamic face model that can adapt to changes in visual appearance as subjects move across the frame.
The face model allows the system to accurately track faces in front of complex backgrounds and localize subjects in all video frames, even under complicated conditions.
Based on the latest biometric facial recognition engine from Neurotechnology’s MegaMatcher 5.0 line (VeriLook 5.5), VeriLook Surveillance 3.0 detects faces more rapidly with improved face feature determination and emotion detection, including detection of smiles, closed-eyes, open-mouths, clear glasses and dark glasses.
VeriLook Surveillance 3.0 matches face images against internal databases, such as authorized personnel or criminal watch lists.
A VeriLook Surveillance-based application can then lock or unlock a door, place a record into a time/attendance system or instantly trigger a report or alert for recognized or un-recognized faces.
When the video surveillance system is monitoring a large area or the cameras are positioned in a way that the captured faces are too small to be recognized or not entirely visible, VeriLook Surveillance’s moving object detection and classification capability enables users to distinguish people and objects in the scene.
If a moving person or object has crossed a defined border or entered/left a specific monitored area or region, VeriLook Surveillance will immediately send an alert notification and follow up with the appropriate action if a restricted or sensitive area has been compromised.
This moving object detection and classification capability allows VeriLook Surveillance to be used in various applications, such as event security or police applications, such as automatically detecting which vehicles are passing through red lights or stop signs.
“In this release of VeriLook Surveillance we have introduced new features, such as pedestrian detection, security zones and moving object tracking, all of which increase the flexibility of our product and allow our customers to apply it in many new and different ways,” said Dr. Raimond Laptik, surveillance research lead for Neurotechnology.
The software continues tracking subjects even when their faces momentarily disappear from the frame or when they are partially blocked by other objects or even other faces.
This capability can be attributed to the face recognition algorithm, which detects faces with up to 45 degrees out-of-plane rotation in yaw angle. It uses motion prediction models to re-localize faces that have temporarily gone out of view.