Local search for optimal global map generation using mid-decadal landsat images
By: L. Khatib, J. Gasch, Robert Morris, and S. Covington
Links
- The Publications Warehouse does not have links to digital versions of this publication at this time
- Download citation as: RIS | Dublin Core
Abstract
NASA and the US Geological Survey (USGS) are seeking to generate a map of the entire globe using Landsat 5 Thematic Mapper (TM) and Landsat 7 Enhanced Thematic Mapper Plus (ETM+) sensor data from the "mid-decadal" period of 2004 through 2006. The global map is comprised of thousands of scene locations and, for each location, tens of different images of varying quality to chose from. Furthermore, it is desirable for images of adjacent scenes be close together in time of acquisition, to avoid obvious discontinuities due to seasonal changes. These characteristics make it desirable to formulate an automated solution to the problem of generating the complete map. This paper formulates a Global Map Generator problem as a Constraint Optimization Problem (GMG-COP) and describes an approach to solving it using local search. Preliminary results of running the algorithm on image data sets are summarized. The results suggest a significant improvement in map quality using constraint-based solutions. Copyright ?? 2007, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
| Publication type | Conference Paper |
|---|---|
| Publication Subtype | Conference Paper |
| Title | Local search for optimal global map generation using mid-decadal landsat images |
| ISBN | 9781577353379 |
| Volume | WS-07-10 |
| Year Published | 2007 |
| Language | English |
| Larger Work Title | AAAI Workshop - Technical Report |
| First page | 66 |
| Last page | 70 |
| Conference Title | 2007 AAAI Workshop |
| Conference Location | Vancouver, BC |
| Conference Date | 22 July 2007 through 22 July 2007 |
| Google Analytic Metrics | Metrics page |