Site Search:
Print This Page
Home
Opportunities
Browse FedBiz Opps
Browse SBIR Opps
Browse FedGrants
Browse Tech Needs
Search FedBiz Opps
Search FedGrants
Search SBIR Opps
Search Tech Needs
Licensable Patents
Labs
Calendar
Success Stories
Hot Technologies
Related Links
Resources
Contact Us
DoD TTIPT
Login
(Register Here)
STTR Opportunity View
Back to Listing
ST081-009
Go To DOD SBIR Site
Basic Information:
Title:
Building Labels for Urban Environments (BLUE)
Program:
STTR
Technology Area:
Information Systems, Sensors
Open Date:
2/19/2008
Close Date:
3/19/2008
Description:
Urban areas include many buildings of various types: hotels, stores, offices, apartments, fire stations, hospitals, restaurants, places of worship, etc. In most cases, the proper classification of a building as an instance of one (or more) of a type is a matter of function more than form. The difference between an apartment building and an office building, for example, may not be obvious from its visual features alone. This poses a significant technical challenge for automated object recognition systems, which exploit patterns of visual features in still images. DARPA seeks innovative approaches that exploits surveillance video data to classify buildings automatically. In addition to visual feature data such as color and line orientation, video captures data concerning motion over time. The latter affords the opportunity for automated recognition of patterns in moving objects in the vicinity of buildings. These motion patterns may be reliable indicators of a buildings function. BLUE technology should be able to learn patterns that distinguish building types and to process video from surveillance video data, such as that collected from high-endurance military UAV platforms, to label buildings correctly. Proposed research in the initial phase of this effort should focus on demonstrating, in a rigorously empirical and quantitative fashion, the capability of the offerors technical approach. Offerors must clearly indicate the data sources they propose to use for development and testing, the building classes on which will they will concentrate, and metrics they will use to measure accuracy. Offerors are encouraged to follow emerging standards in geospatial representation, such as the CityGML building classification taxonomy and GML/KML for overlay of building labels on geospatial images.
Objective:
Research and develop technologies enabling automated labeling of urban buildings by function type from surveillance video data.
Phase I:
Feasibility study to investigate viability and design approaches for BLUE technology. Validate through experimentation. Evaluate potential benefit to military operations and commercial applications.
Phase II:
Apply Phase I results, data, and analysis to develop a prototype that demonstrates the efficacy of BLUE technology. Evaluate the performance of prototype through experimentation on operationally realistic data. Successful technical approaches may transition to the system developed on the DARPA Urban Reasoning and Geospatial Exploitation (URGENT) program.
Phase III:
BLUE technology will provide enhanced mapping capabilities for both military and commercial cartographic organizations.
References:
1. CityGML, http://www.citygml.org/
STTR Keywords
Cartography, object recognition, video exploitation
TechMatch Keyword(s):
Computer Software
Applications
Data Visualization and Graphics
Image Processing and Pattern Recognition
Knowledge Management
Geographic Information Systems (GIS)
Decision Support
Databases
Sensors
Surveillance
Net-Centric Warfare (NCW)
Urban Operations
DISCLAIMER:
The Solicitations listed on this site are copies from the various SBIR agency solicitations and are not necessarily the latest and most up-to-date. For this reason, you should use the agency link listed below which will take you directly to the appropriate agency server where you can read the official version of this solicitation and download the appropriate forms and rules.
The Official Website can be found at:
http://www.acq.osd.mil/sadbu/sbir/solicitations/index.htm
© 2002, 2010 by
West Virginia High Technology Consortium Foundation
.
All rights reserved.
Disclaimer.