Feasibility of using template-based and object-based automated detection methods for quantifying black and hybrid imported fire ant (Solenopsis invicta and S. invicta × richteri) mounds in aerial digital imagery
James T. Vogt A D and Bradley Wallet B CA USDA, ARS Biological Control of Pests Research Unit, PO Box 67, Stoneville, Mississippi 38776, USA.
B Automated Decisions, LLC, 821 W. Lindsey St., Norman, Oklahoma 73069, USA.
C ConocoPhillips School of Geology and Geophysics, College of Earth and Energy, The University of Oklahoma, 100 E. Boyd St., Norman, Oklahoma 73109, USA.
D Corresponding author. Email: jt.vogt@ars.usda.gov
The Rangeland Journal 30(3) 291-295 https://doi.org/10.1071/RJ08007
Submitted: 25 January 2008 Accepted: 19 March 2008 Published: 21 August 2008
Abstract
Imported fire ants construct earthen nests (mounds) that exhibit many characteristics which make them potentially good targets for remote sensing programs, including geographical orientation, topography, and bare soil surrounded by actively growing vegetation. Template-based features and object-based features extracted from aerial multispectral imagery of fire ant infested pastures were used to construct classifiers for automated fire ant mound detection. A classifier constructed using template-based features alone yielded a 79% probability of detection with a corresponding false positive rate of 9%. Addition of object-based features (compactness and symmetry) to the classifier yielded a 79% probability of detection with a corresponding false positive rate of 4%. Maintaining a 79% detection rate when applying the classifier to a second, unique pasture dataset with different seasonal and other environmental factors resulted in a false positive rate of 17.5%. Data demonstrate that automated detection of mounds with classifiers incorporating template- and object-based features is feasible, but it may be necessary to construct unique classifiers on a site-specific basis.
Additional keyword: classification.
Acknowledgements
This work was supported by a Phase I Small Business Innovation Research Grant, United States Department of Agriculture, Cooperative State Research, Education, and Extension Service. We thank Mr Steven Coy for expert assistance in the field. Allan Showler and E. Raymond Hunt, Jr. provided many helpful comments on an earlier version of the manuscript.
Fillman D. A., Sterling W. L.
(1985) Inaction levels for the red IFA, Solenopsis invicta (Hym.: Formicidae): a predator of the boll weevil, Anthonomus grandis (Col.: Curculionidae). Agriculture, Ecosystems & Environment 13, 93–102.
| Crossref | GoogleScholarGoogle Scholar |
(accessed 7 April 2008).
Green L. R.,
Olson W. G.,
Hart J. K., Davis M. R.
(1977) Aerial photographic detection of IFA mounds. Photogrammetric Engineering and Remote Sensing 43, 1051–1057.
(accessed 11 February 2008).
Showler A. T., Reagan T. E.
(1991) Effects of sugarcane borer, weed, and nematode control strategies in Louisiana sugarcane. Environmental Entomology 20, 358–370.
(accessed 4 December 2007).
Vogt J. T.
(2004a) Quantifying IFA (Hymenoptera: Formicidae) mounds with airborne digital imagery. Environmental Entomology 33, 1045–1051.
Vogt J. T.
(2004b) Detection of IFA (Hymenoptera: Formicidae) mounds with satellite imagery. Environmental Entomology 33, 1718–1721.
Vogt J. T.
(2007) Three-dimensional method for characterizing ant mounds. Florida Entomologist 90, 533–558.
| Crossref |
Vogt J. T.,
Streett D. A., Boykin D.
(2004) Seasonal characteristics of black IFA (Hymenoptera: Formicidae) mounds in northern Mississippi pastures. Sociobiology 43, 513–522.
Wallet B. W.,
Solka J. L., Priebe C. E.
(1997) A method for detecting microcalcifications in digital mammograms. Journal of Digital Imaging 10, 136–139.
|
CAS |
PubMed |
