How Artificial Intelligence Is Transforming Video Surveillance

by Avigilon
Sep 5, 2018

Share

Searching through large volumes of recorded video is a challenging yet crucial task for security operators. We have reached a critical point where the limitations of the human attention span make it difficult for security operators to search through the volumes of surveillance data effectively.

To answer this challenge, Avigilon is developing technologies and products that harness the power of AI to dramatically increase the effectiveness of security systems by focusing human attention on what matters most. By delivering true video content search, real-time alerts and automation, Avigilon provides effective security solutions that are helping to solve real-world challenges.

Transforming Surveillance

In the past, video surveillance searches were conducted per camera, based on time, motion and activity. However, a person or object of interest may not be specific to a single camera, and their clothing or appearance may change over time, making it necessary for security operators to quickly and accurately search all cameras across a site to locate what they are looking for.

Through the power of AI, this is now possible. Advanced AI technology, like Avigilon Appearance Search™ technology, provides security operators with the ability to quickly locate a specific person or vehicle of interest across an entire site. This enhanced search capability is designed to help improve response times by answering the critical who, what, where and when of an investigation with decisive action.

How AI and Appearance Search Are Being Applied

This technology is being deployed across a range of verticals to address some of the industry’s biggest security challenges. For instance, Fulton County School System in Metro Atlanta, Georgia has installed a complete Avigilon surveillance solution to help enhance safety at more than 100 of its schools. Advanced AI technology, combined with the advanced search capabilities of Avigilon Control Center (ACC) software, has provided their operators with powerful insights that enable proactive event response and can help save time and effort during critical investigations.

Charlotte Hungerford Hospital (CHH) in Torrington, Connecticut has also deployed an AI-based Avigilon solution to improve security across its multiple locations. Avigilon Appearance Search helps CHH when they need to quickly locate a specific person or vehicle of interest across all cameras both inside the hospital and care centers as well as outside parking lots. This technology provides CHH’s operators with enhanced situational awareness, enabling proactive event response.

A New Level of Automation

Avigilon Unusual Motion Detection (UMD) technology uses AI in video search to bring a new level of automation to surveillance, helping to reduce hours of work reviewing recorded video to minutes. Without any pre-defined rules or setup, UMD technology is able to continuously learn what typical activity in the scene looks like, and then detect and flag unusual motion. This allows operators to search through large amounts of video faster, as UMD focuses their attention on the atypical events that may need further investigation.

 

© 2018, Avigilon Corporation. All rights reserved. AVIGILON, the AVIGILON logo, AVIGILON APPEARANCE SEARCH, AVIGILON CONTROL CENTER, and ACC are trademarks of Avigilon Corporation. Other names or logos mentioned herein may be the trademarks of their respective owners.

Keep current on Avigilon

Sign up to receive our blogs.

Follow us on Twitter, Facebook, LinkedIn, and view Avigilon videos on YouTube.

Category: Security

Tags:


For Media Relations

Please email media@avigilon.com or call 604-629-5182


Glossar

ACC-Version Aktuelle ACC-Version mit Kamera getestet. Falls nicht anders angegeben, werden auch höhere Versionen von ACC unterstützt.
Audio-Eingang Audiofeed von Kamera empfangen
Audioausgabe Audio an mit der Kamera verbundene Lautsprecher senden
Automatische Erkennung Automatische Erkennung von Kamera-IP-Adressen bei Verbindung in einer LAN-Umgebung
Komprimierungskategorie Beschreibt die für die Kamera unterstützten Codierungstypen
Anschlussart Beschreibt den Typ des verwendeten Gerätetreibers. „Nativ“ bezieht sich auf den spezifischen Gerätetreiber des Herstellers.
Entzerrung Entzerrung von Fischaugen- oder Panoramakameras im Client
Digitaler Input Empfang von digitalen oder Relaiseingaben von der Kamera
Digitaler Output Auslösung von digitalen oder Relaisausgaben, die physisch mit einer Kamera verbunden sind
Bewegung Schnelle Anzeige, ob Bewegungsaufzeichnung für die Kamera verfügbar ist
Bewegungskonfiguration Konfiguration der Bewegungserkennung im ACC-Client
Bewegungsaufzeichnung Unterstützung von bewegungsbasierter Aufzeichnung
PTZ Schnelle Anzeige, ob PTZ-Funktionen für die Kamera verfügbar sind
PTZ-Steuerung Grundlegende PTZ-Bewegung
PTZ-Muster/-Touren Möglichkeit zum Erstellen und Auslösen von PTZ-Mustern oder PTZ-Touren je nach Kameraunterstützung
PTZ-Voreinstellungen Erstellen und Auslösen von voreingestellten PTZ-Positionen
Einheitentyp Kameratyp
Verifiziert von Organisation, die eine Kamera und die angegebenen Funktionen getestet hat
Verifizierte Firmware Specific firmware version tested.
Hersteller Blah
Modell DS-2DE2103
Anschlussart ONVIF
Einheitentyp IP-PTZ-Kamera
Compression Types H.264

  • ACC-Version
  • Modell DS-2DE2103
  • Anschlussart ONVIF
  • Hersteller Blah
  • Hersteller Blah
  • Hersteller Blah
  • Hersteller Blah
  • Hersteller Blah
  • Hersteller Blah
  • Hersteller Blah
  • Hersteller Blah
  • Hersteller Blah

Verifiziert von:

Vendor
Testbericht herunterladen