Adam Bannister

Editor, IFSEC Global

Author Bio ▼

Adam Bannister is editor of IFSEC Global. A former managing editor at Dynamis Online Media Group, he has been at the helm of the UK's leading fire and security publication since 2014.
January 21, 2019

Sign up to free email newsletters

Download

Mobile access series #1: What you need to know

counter-terror tech

AI video analytics from BriefCam triumphs in terror-attack simulation

Video analytics developer BriefCam has won a competition assessing the response of AI-powered software during a terror-attack simulation.

The Massachusetts-based company won the Defence and Security Accelerator (DASA) Hackathon, which was sponsored by the UK government, by identifying a terrorist in less than two hours.

Given only limited details about the culprit – comparable to the level of detail investigators typically work with in real-world situations – participants trawled hundreds of hours of low resolution, low frame-rate video from dozens of cameras and files. The video was accompanied by simulated, high resolution, live streams.

Judges assessed how effectively, and quickly, participants picked out subjects of interest – such as people, places and events – established relationships between them, and charted an event timeline and narrative, as well as their near-term predictions. The application of artificial intelligence (AI) techniques, including machine vision, was also considered.

“We are honoured to have won this hackathon and demonstrate how we help accelerate the time-to-target for investigations.” Trevor Matz, CEO, BriefCam

BriefCam’s video content analytics platform makes video surveillance data “searchable, quantifiable and actionable.”

Using the company’s patented Video Synopsis platform customers can review hours of video in minutes – sometimes seconds – and quantitatively analyse video to generate insights that can drive operational decisions. Balancing sensitivity, accuracy and efficiency these capabilities are designed to yield quick, usable results in fast-moving emergency situations like terror attacks.

Deep neural networks, which are trained in diverse data sets, enhance the accuracy of face matching and object classification. Face recognition is integrated with granular object classification, multi-camera search, quantitative analytics and real-time alerting capabilities.

“Our mission is to help law enforcement agencies solve crimes faster and support municipalities in creating safer cities, so we are honoured to have won this hackathon, and demonstrate how we help accelerate the time-to-target for investigations,” said Trevor Matz, CEO of BriefCam. “By leveraging the advanced deep learning and artificial intelligence capabilities of our comprehensive video analytics platform, law enforcement agencies globally are protecting what matters most.”

BriefCam customer include law enforcement, transportation authorities, major enterprises, and healthcare and educational institutions.

Free Download: Connected security for smart infrastructure

With the rise of the Internet of Things, people, homes and businesses are more connected than ever. Explore what this means for smart buildings, cities and infrastructure in this free eBook from Abloy UK.

Related Topics

Leave a Reply

avatar
  Subscribe  
Notify of

Sign up to free email newsletters