Automating the Hunt for Volcanoes on Venus
Abstract
Our long-term goal is to develop a trainable tool for locating patterns of interest in large image databases. Toward this goal we have developed a prototype system, based on classical filtering and statistical pattern recognition techniques, for automatically locating volcanoes in the Magellan SAR database of Venus. Training for the specific volcano-detection task is obtained by synthesizing feature templates (via normalization and principal components analysis) from a small number of examples provided by experts. Candidate regions identified by a focus of attention (FOA) algorithm are classified based on correlations with the feature templates. Preliminary tests show performance comparable to trained human observers.
Additional Information
© 1994 IEEE. Date of Current Version: 06 August 2002. The research described in this report has been carried out in part by the Jet Propulsion Laboratory, California Institute of Technology, under contract with the National Aeronautics and Space Administration. Support was provided primarily by NASA Office of Advanced Concepts and Technology (OACT - Code CD), a JPL DDF award, and NSF research initiation grant IRI 9211651. We would like to thank geologists Jayne Aubele and Larry Crumpler of Brown University for their assistance in labeling and analyzing the Magellan data. We would also like to thank John Loch, Jennifer Yu, and Joe Roden for help in developing the software and user-interfaces.Attached Files
Published - BURcvpr94.pdf
Files
| Name | Size | Download all |
|---|---|---|
|
md5:11bb2f94a4c1989d114a8d5f0df157a0
|
631.2 kB | Preview Download |
Additional details
- Eprint ID
- 29601
- Resolver ID
- CaltechAUTHORS:20120306-142457025
- NASA/JPL/Caltech
- NASA Office of Advanced Concepts and Technology
- JPL DDF Award
- IRI 9211651
- NSF Research Initiation grant
- Created
-
2012-03-13Created from EPrint's datestamp field
- Updated
-
2021-11-09Created from EPrint's last_modified field
- Other Numbering System Name
- INSPEC Accession Number
- Other Numbering System Identifier
- 4777946