Automated Scene Understanding

Award Information
Agency:
Department of Defense
Branch
Navy
Amount:
$732,445.00
Award Year:
2011
Program:
SBIR
Phase:
Phase II
Contract:
N0001411-C-0308
Agency Tracking Number:
O2-1301
Solicitation Year:
2009
Solicitation Topic Code:
OSD09-SP3
Solicitation Number:
2009.2
Small Business Information
ObjectVideo
11600 Sunrise Valley Drive, Suite # 290, Reston, VA, -
Hubzone Owned:
N
Socially and Economically Disadvantaged:
N
Woman Owned:
N
Duns:
038732173
Principal Investigator:
Tae Choe
Principal Investigator
(703) 654-9300
tchoe@objectvideo.com
Business Contact:
Paul Brewer
VP, New Technology
(703) 725-3084
pbrewer@objectvideo.com
Research Institution:
Stub




Abstract
ObjectVideo, Inc. proposes to develop video inference algorithms and a modular architecture for scene understanding based on the computational framework of Spatio-temporal And-Or Graph (ST-AoG). Various image inference modules can be integrated to the framework through an API for scene understanding. The system can be easily upgradeable as new image processing modules are developed. The architecture also supports the input of user-provided context to improve inference. Leveraging earlier work on semantic annotation, we will develop algorithms to infer complex relationships between scene entities. Plain text reports of the scene are automatically generated to describe these relationships, contextual information, and events of interest. To achieve a high compression rate for bandwidth-limited applications, the text description can be used to synthesize image and video to provide a representative rendering of the scene and events. In addition, we propose a method for indexing hierarchical data as well as a scalable framework for searching a large imagery dataset.

* information listed above is at the time of submission.

Agency Micro-sites

US Flag An Official Website of the United States Government