Neurotechnology updates SentiVeillance SDK with biometrics for masked faces, new tracking features

A new version of the SentiVeillance computer vision software with face biometrics has been released by Neurotechnology to add face detection and biometrics for people wearing masks and new algorithms for faster and more accurate license plate recognition.

SentiVeillance SDK 8.0 also features new capabilities for vehicle and human (VH) mode, including analysis of the make and model of automobiles and gender estimation for pedestrians. A new working mode combination also enables facial recognition to be used with VH mode for fast and accurate identification, according to the announcement. The combination mode also allows subjects to be tracked even when the face is too occluded for biometrics.

The software provides computer vision-based identification and analytics for live video surveillance feeds or stored video.

Neurotechnology says the high reliability offered by the face biometric algorithm within SentiVeillance makes it suitable for use with high image-volume watchlists and databases, both to identify subjects and enroll new ones. Subjects passing behind objects can also be tracked with biometrics as they reappear.

“I am very grateful for all the hard work our team put into this latest release that enhances speed and accuracy and provides compelling new ways to use our software,” says Vytautas Pranckenas, SentiVeillance product lead for Neurotechnology. “There has never been a more important time for reliable recognition solutions that can adapt to new conditions, such as people wearing masks.”

The automated license plate recognition (ALPR) capability of SentiVeillance is up to twice as fast running on a CPU and up to five times as fast when a GPU is used, the company says.

The new SDK also includes a precompiled sample with source codes and integration to the Mobotix m16 camera with thermal sensing, which adds temperature readings and mask estimation and allows temperature thresholds or deviation from an average to be set for specific actions, and is designed to assist with physical access control.

Neurotechnology upgraded the speed and efficiency of its MegaMatcher SDKs and solutions last September.

Article Topics

biometric identification  |  biometrics  |  face detection  |  facial recognition  |  licence plate readers  |  mask detection  |  Neurotechnology  |  SDK  |  video surveillance