Javier Rodriguez Saeta, CEO of Herta Security, shares how they’re using NVIDIA GPUs to train deep neural networks for pattern recognition to help with security at airports, stadiums and train stations.
Herta Security’s high performance video-surveillance solution for facial recognition is designed to identify people in crowded and changing environments in real-time. Their technology makes it possible to record subjects automatically through on-the-fly video capture, and works correctly even when the subject is wearing glasses, a hat, or their face is partially concealed. It even works with changes in facial expression, difficult lighting conditions and slight rotations of the face.
Share your GPU-accelerated science with us at http://nvda.ly/Vpjxr and with the world on #ShareYourScience.
Watch more scientists and researchers share how accelerated computing is benefiting their work at http://nvda.ly/X7WpH
Share Your Science: The Future of Facial Recognition for Video Surveillance
Apr 06, 2016
Discuss (0)
AI-Generated Summary
- Herta Security uses NVIDIA GPUs to train deep neural networks for pattern recognition in security applications.
- Their facial recognition system identifies people in crowded environments such as airports, stadiums and train stations in real time.
- The technology works correctly even when subjects wear glasses or hats, have partially concealed faces, show facial expression changes, face difficult lighting or have slight face rotations.
Next Steps
- Visit Herta Security to learn more about their GPU-accelerated video-surveillance solution.
- Watch more researchers share how accelerated computing benefits their work at Share Your Science.
Powered by NVIDIA Nemotron. AI-generated content may summarize information incompletely. Verify important information. Learn more
About the Authors
