CaltechAUTHORS
  A Caltech Library Service

Automated analysis of radar imagery of Venus: handling lack of ground truth

Burl, M. C. and Fayyad, Usama M. and Perona, Pietro and Smyth, Padhraic (1994) Automated analysis of radar imagery of Venus: handling lack of ground truth. In: 1994 IEEE International Conference on Image Processing, Proceedings (ICIP-94). IEEE Computer Society Press , Los Alamitos, CA, pp. 236-240. ISBN 0-8186-6952-7 http://resolver.caltech.edu/CaltechAUTHORS:20120306-150027112

[img]
Preview
PDF - Published Version
See Usage Policy.

484Kb

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20120306-150027112

Abstract

Lack of verifiable ground truth is a common problem in remote sensing image analysis. For example, consider the synthetic aperture radar (SAR) image data of Venus obtained by the Magellan spacecraft. Planetary scientists are interested in automatically cataloging the locations of all the small volcanoes in this data set; however, the problem is very difficult and cannot be performed with perfect reliability even by human experts. Thus, training and evaluating the performance of an automatic algorithm on this data set must be handled carefully. We discuss the use of weighted free-response receiver-operating characteristics (wFROCs) for evaluating detection performance when the “ground truth” is subjective. In particular, we evaluate the relative detection performance of humans and automatic algorithms. Our experimental results indicate that proper assessment of the uncertainty in “ground truth” is essential in applications of this nature.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
http://dx.doi.org/10.1109/ICIP.1994.413852DOIUNSPECIFIED
http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=413852&tag=1PublisherUNSPECIFIED
Additional Information:© 1994. Date of Current Version: 06 August 2002. The authors would like to thank Jayne Aubele and Larry Crumpler of the Department of Geological Sciences, Brown University, for their assistance in labelling images, and Maureen Burl (JPL) for assistance with the experiments. The research described in this paper was carried out by the Jet Propulsion Laboratory, California Institute of Technology, under a contract with the National Aeronautics and Space Administration.
Funders:
Funding AgencyGrant Number
NASA/JPL/CaltechUNSPECIFIED
Other Numbering System:
Other Numbering System NameOther Numbering System ID
INSPEC Accession Number5021857
Record Number:CaltechAUTHORS:20120306-150027112
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20120306-150027112
Official Citation:Burl, M.C.; Fayyad, U.M.; Perona, P.; Smyth, P.; , "Automated analysis of radar imagery of Venus: handling lack of ground truth," Image Processing, 1994. Proceedings. ICIP-94., IEEE International Conference , vol.3, no., pp.236-240 vol.3, 13-16 Nov 1994 doi: 10.1109/ICIP.1994.413852 URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=413852&isnumber=9214
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:29602
Collection:CaltechAUTHORS
Deposited By: Ruth Sustaita
Deposited On:12 Mar 2012 22:13
Last Modified:26 Dec 2012 14:55

Repository Staff Only: item control page