Herta BioSurveillance

Herta BioSurveillance

Face recognition is one of the least invasive biometrics, since data is captured effortlessly and generally involves no user interaction. Herta’s video surveillance solution, BioSurveillance, detects multiple faces in real-time, incorporates on-the-fly video enrollment, identifies previously trained individuals, and facilitates run-time management of alarms and individuals. Our technology makes it possible to record subjects automatically through (on-the-fly) video capture, and works correctly even with partial facial concealment, wearing of glasses, handkerchiefs or caps, changes in facial expression, difficult lighting conditions and slight rotations of the face. Intel is committed to respecting human rights and avoiding complicity in human rights abuses. See Intel's Global Human Rights Principles. Intel's products and software are intended only to be used in applications that do not cause or contribute to a violation of an internationally recognized human right.

*Please note that member solutions are often customizable to meet the needs of individual enterprise end users.



  • Blacklisted People
    BioSurveillance uses video surveillance cameras to recognize the faces of blacklisted people.
  • Occluded Faces
    BioSurveillance yields excellent performance with partial occlusions of the face, glasses, scarfs, caps, changes of facial expression, shadows, high contrasts and extreme or poor lighting conditions, and on moderate rotations of the face.
  • Independent
    BioSurveillance works on the move and at a distance, and does not require end-user collaboration.
  • Flexible
    Individuals can be enrolled in the system through a photograph as well as using real time or recorded video.


WorldwideAI Software/SaaSCross-IndustryDefense and SpaceGovernmentFacial Detection/Recognition/ClassificationVideo Surveillance and AnalyticsHybrid CloudOn-premise (Private Cloud, Other)Intel® Core™ ProcessorIntel® Distribution of OpenVINO™ Toolkit powered by oneAPIIntel® Optimization for PyTorch*Models cant be re-trained - Inference onlyWindowsLinux ProprietaryDeep Learning