Automated Low-Level Analysis and Description of Diverse Intelligence Video (ALADDIN)

Massive numbers of video clips are generated daily on many types of consumer electronics and uploaded to the Internet. In contrast to videos that are produced for broadcast or from planned surveillance, the "unconstrained" video clips produced by anyone who has a digital camera present a significant challenge for manual as well as automated analysis. Such clips can include any possible scene and events, and generally have limited quality control.

Analysts who must work with such data are overwhelmed by its volume and lack of tools to probe it. Most current software tools that work with large collections of video clips focus on skimming to speed up the eyes-on-video/ears-on-audio process. Some advanced tools focus on automatic transcription and indexing of the speech from the audio signal. Other advanced tools apply computer vision techniques to extract features for unstructured "bag-of-words" search methods or to find clips that are "similar" to others. No technology currently exists to provide a user with the information necessary to fully understand the content or temporal processes within these data.

The Aladdin Video Program seeks to combine the state-of-the art in video extraction, audio extraction, knowledge representation, and search technologies in a revolutionary way to create fast, accurate, robust, and extensible technology that supports the multimedia analytic needs of the future.

 

For information contact:

dni-iarpa-info@iarpa.gov

 

Solicitation Status: Closed

IARPA-BAA-10-01
Proposers' Day Date: October 30, 2009
BAA Release Date: June 10, 2010
BAA Amendment 01 Release Date: June 28, 2010
BAA Question Period: June 10, 2010 - July 14, 2010
Proposal Due Date: July 28, 2010

Additional Information

Proposers' Day Briefings