Dark Reading is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them.Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

Risk

DARPA Sharpens Focus On Video Analysis Technology

The VIRAT and PerSEAS programs aim to create better ways to detect dangerous behavior, such as burying improvised explosive devices, during combat.

>Slideshow: Next Generation Defense Technologies
Slideshow: Next Generation Defense Technologies
(click for larger image and for full slideshow)
The Department of Defense (DOD) is developing video-analysis technology for detecting activity from a variety of image-capturing sensors, a tool that would enable the military to better observe dangerous behavior during combat as it happens.

The Defense Advanced Research Project (DARPA) is working on ways to analyze large amounts of data from multiple video sensors specifically to make out people's movements. It's a problem that historically has been difficult to tackle merely with analysis by the human eye alone when it comes to large amounts of raw video footage, according to the agency.

The new technologies are meant to be used to help military analysts who are already tasked with analyzing video data to do their jobs better.

"The objectives of [the technologies] are not to replace human analysts, but to make them more effective and efficient by reducing their cognitive load and enabling them to search for activities and threats quickly and easily," said Mita Desai, DARPA program manager for VIRAT and PerSEAS, in a statement.

One of the technologies being developed--the Video and Image Retrieval and Analysis Tool (VIRAT)--is focused on identifying isolated actions in a small geographic area from full-motion video from military platforms such as Predator or Aerostats, according to DARPA.

Analysts using the tool can either monitor a live video feed for specific actions of interest or search archives of occurrences in the past for the same. To search through video, analysts use a video clips as the input query, according to DARPA.

While VIRAT has a narrow focus, the Persistent Stare Exploitation and Analysis System (PerSEAS) program analyzes video from a broader perspective over a longer period of time to help the military detect more complex threats, according to DARPA. The existing military sensors PerSEAS works with include Constant Hawk, Gorgon Stare, and ARGUS-IS.

While the two technologies are different and have different aims, PerSEAS leverages some algorithms from VIRAT, the agency said.

An initial prototype of VIRAT is available that works in two modes--forensic, which allows analysts to identify activities in thousands of hours of archived, untagged data, and streaming, which can highlight actions as a video download is being viewed. Development on PerSEAS is still under way, but the technology will be field tested soon, according to DARPA.

What industry can teach government about IT innovation and efficiency. Also in the new, all-digital issue of InformationWeek Government: Federal agencies have to shift from annual IT security assessments to continuous monitoring of their risks. Download it now. (Free registration required.)

Comment  | 
Print  | 
More Insights
Comments
Newest First  |  Oldest First  |  Threaded View
SOC 2s & Third-Party Assessments: How to Prevent Them from Being Used in a Data Breach Lawsuit
Beth Burgin Waller, Chair, Cybersecurity & Data Privacy Practice , Woods Rogers PLC,  12/5/2019
Navigating Security in the Cloud
Diya Jolly, Chief Product Officer, Okta,  12/4/2019
Register for Dark Reading Newsletters
White Papers
Video
Cartoon Contest
Write a Caption, Win a Starbucks Card! Click Here
Latest Comment: "This is the last time we hire Game of Thrones Security"
Current Issue
Navigating the Deluge of Security Data
In this Tech Digest, Dark Reading shares the experiences of some top security practitioners as they navigate volumes of security data. We examine some examples of how enterprises can cull this data to find the clues they need.
Flash Poll
Rethinking Enterprise Data Defense
Rethinking Enterprise Data Defense
Frustrated with recurring intrusions and breaches, cybersecurity professionals are questioning some of the industrys conventional wisdom. Heres a look at what theyre thinking about.
Twitter Feed
Dark Reading - Bug Report
Bug Report
Enterprise Vulnerabilities
From DHS/US-CERT's National Vulnerability Database
CVE-2014-0242
PUBLISHED: 2019-12-09
mod_wsgi module before 3.4 for Apache, when used in embedded mode, might allow remote attackers to obtain sensitive information via the Content-Type header which is generated from memory that may have been freed and then overwritten by a separate thread.
CVE-2015-3424
PUBLISHED: 2019-12-09
SQL injection vulnerability in Accentis Content Resource Management System before the October 2015 patch allows remote attackers to execute arbitrary SQL commands via the SIDX parameter.
CVE-2015-3425
PUBLISHED: 2019-12-09
Cross-site scripting (XSS) vulnerability in Accentis Content Resource Management System before October 2015 patch allows remote attackers to inject arbitrary web script or HTML via the ctl00$cph_content$_uig_formState parameter.
CVE-2015-7892
PUBLISHED: 2019-12-09
Stack-based buffer overflow in the m2m1shot_compat_ioctl32 function in the Samsung m2m1shot driver framework, as used in Samsung S6 Edge, allows local users to have unspecified impact via a large data.buf_out.num_planes value in an ioctl call.
CVE-2015-0841
PUBLISHED: 2019-12-09
Off-by-one error in the readBuf function in listener.cpp in libcapsinetwork and monopd before 0.9.8, allows remote attackers to cause a denial of service (crash) via a long line.