NSF Award Abstract - #9983430| NSF Award Abstract - #9983430 |
AWSFL008-DS3 |
| NSF Org | IIS |
| Latest Amendment Date | July 22, 2002 |
| Award Number | 9983430 |
| Award Instrument | Continuing grant |
| Program Manager |
Lawrence Brandt IIS DIV OF INFORMATION & INTELLIGENT SYSTEMS CSE DIRECT FOR COMPUTER & INFO SCIE & ENGINR |
| Start Date | August 1, 2000 |
| Expires | July 31, 2004 (Estimated) |
| Expected Total Amount | $500000 (Estimated) |
| Investigator |
Aidong Zhang azhang@cse.buffalo.edu (Principal Investigator current) David M. Mark (Co-Principal Investigator current) |
| Sponsor |
SUNY Buffalo 501 Capen Hall Buffalo, NY 14260 716/645-2977 |
| NSF Program | 1706 DIGITAL GOVERNMENT |
| Field Application | 0000099 Other Applications NEC |
| Program Reference Code | 1387,9218,HPCC, |
EIA-9983430 Zhang, Aidong SUNY BuffaloDigital Government: Very Large Scale Multidimensional Data Management and Retrieval for USGS and NIMA Imagery
This project will conduct research on managing and retrieving multidimensional data held by partner government agencies (the United States Geological Survey (USGS) and the National Imaging and Mapping Agency (NIMA)). In such applications, geographic image databases distributed at remote locations must be made available at other locations for purpose of data retrieval. With the advent of content-based retrieval of image data, traditional methods for database design and query search will not be suitable in developing distributed image retrieval systems.
The objective of the proposed research is to investigate novel approaches to supporting effective and efficient access to the integrated geographic image databases over the Internet. These approaches will establish a foundation for the design of distributed geographic image retrieval systems. The technical challenge relating to the design of such integration is the creation of meta-level system on top of the image databases. The specific research goals are : (1) identify multi-scale representation (multidimensional) methods for geographic images, (2) investigate novel clustering approaches that can detect clusters of arbitrary shape of multidimensional image data, (3) construct a metadata model that formulates the metadata that are needed for the integrated system to direct a visual query to relevant databases, (4) develop the theoretical foundation of database selection approaches based on the metadata, and (5) design novel visual query processing approaches that integrate heterogeneous features extracted from the content of visual data.
During the project period, USGS and NIMA will provide all necessary imagery data sets and their categories. A system will be disseminated at both USGS and NIMA sites at the end of the project period. Through the above research activities, the fundamental understanding and novel techniques will be provided to support the design of distributed volume of multidimensional data distributed over the Internet and will find broad applications as a template for the development of distributed image database system in other government agencies, such as NASA. The experimental results to be generated can be used to establish effective benchmarks for assessing the performance of distributed image data retrieval systems.
