Real-Time Video Surveillance Search

Video surveillance depends on expensive, daunting and error-prone manual inspection. Automation is challenging because activities of interest are rare, scenes are over-crowded, computing demands are humongous, and offloading to commercial label and compute services is blocked by privacy laws. We propose a project that studies these research challenges by exploring computer vision by learning, using tactics less demanding in terms of labeled examples; together with new high-performance computing architectures that are scalable and secure in terms of their video processing capabilities. All research results will be integrated in a real-time video surveillance search engine for Amsterdam Schiphol Airport.

  • Projectnummer / Project number: 18038
  • Deelnemende kennisinstellingen / Participating institutes: Vrije Universiteit Amsterdam
  • Gebruikers / Users: 5 bedrijven en 3 instellingen / 5 companies and 3 institutions
  • Projectleider / Project leader: Prof. dr. C.G.M. Snoek, Universiteit van Amsterdam
  • Type project / Type project: Lopend
  • Startdatum / Start date: 1-1-2020
  • Einddatum / End date: 1-1-2024
  • Programma / Programme: Open Technologieprogramma
  • Vakgebied / Discipline: Informatica / Computer science


Contact

Drs. Paul Blank (Programmamedewerker) Drs. Paul Blank (Programmamedewerker) +31 (0)30 6001347 p.blank@nwo.nl