that land and preserve the productive capacity of that land for
future generations (Figure 7).
(See http://www.derm.qld.gov.au/land/planning/strategic-
cropping/index.html ).
s E =
P d & i Queenstand|
wil Ë *%
S Loves
oY 1500's
pereat
Strategic Cropping Land Area: Summer 2011 e iometers
Sc0'E 150°00*E 155-D0"E
Figure 7. Cropping areas detected by this study within the
Strategic Cropping Land trigger map during summer
2011, as indicated by green patches in the map.
Overlaid is the footprints of 35 Landsat scenes that
cover the study area.
The legislation aims to restrict developmental activities on
cropping areas, which have been cultivated at least three times
between 1 January 1999 to 31 December 2010 and that meet
on-ground assessment against the site level SCL criteria. This
has generated a demand for automated large area crop
classification.
The trigger map indicates the location of potential SCL in
Queensland and is based on soil, land and climate information.
The SCL area extends to 42-million ha, which is almost one-
quarter of Queensland and requires 35 Landsat scenes to cover
the entire area. SVM models were applied on these 35 sets of
multi-temporal Landsat data to demarcate areas cropped during
summer 2010 (Figure 7) and winter 2011 (Figure 8)
Strategic Cropping Land Area: Winter 2011
Figure 8. Cropping areas detected by this study within the
Strategic Cropping Land trigger map during winter
2011, as indicated by green patches in the map.
International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XXXIX-B7, 2012
XXII ISPRS Congress, 25 August — 01 September 2012, Melbourne, Australia
4. CONCLUSIONS
Results of this study demonstrated the distinctive advantage of
object-based methods over pixel-based methods, considering
the complexities of within-field spectral heterogeneity and
spectral mixing. This is well supported by several other studies
(Castillejo-González et al., 2009; Pefía-Barragán et al., 2011).
This investigation further combined the superiority of object-
based data with a powerful non-parametric SVM classifier
(Boser et al., 1992; Dixon and Candade, 2007; Huang et al.,
2002) to perform automated large-area broadacre crop mapping.
Comparative analysis clearly revealed that substantially higher
overall classification accuracy (9596) was observed with the
object-based SVM, compared with that of traditional pixel-
based classification (8996). Object-based classification also
resulted in neater and speckle-free images. Further, object-
based SVM models were used to classify different broadacre
crop types for summer and winter seasons. Influence of
different shape, textural and spectral variables and their weights
on crop-mapping accuracy was also examined. Temporal
change in the spectral characteristics, specifically through
vegetation indices derived from multi-temporal Landsat data,
was found to be the most critical information that aftected the
accuracy of classification using SVM models. However, use of
these variables was constrained by the multi-temporal data
availability and cloud cover.
ACKNOWLEDGMENTS
Authors wish to thank United States Geologic Survey (USGS)
for providing Landsat images used for this study.
REFERENCES
Baatz, M., Schápe, A., 2000. Multi-resolution segmentation-
Anoptimization approach for high quality multi-scale
segmentation, in: Strbl, J. (Ed.), Angewandte Geographische
Informationsverarbeitung XII. Beiträge zum AGIT-Symposium
2000. Karlsruhe, Herbert Wichmann Verlag, Salzburg, p.
12—23.
Barbosa, P.M., Casterad, M.A., Herrero, J., 1996. Performance
of several Landsat 5 Thematic Mapper (TM) image
classification methods for crop extent estimates in an irrigation
district. International Journal of Remote Sensing, 17, pp. 3665-
3674.
Blaschke, T., 2010. Object based image analysis for remote
sensing. ISPRS Journal of Photogrammetry and Remote
Sensing, 65, pp. 2-16.
Boser, B.E., Guyon, L, V, V., 1992. A training algorithm for
optimal margin classiers, Fifth Annual Workshop on
Computational Learning Theory. ACM Press, p. 144.
Breiman, L., 2001. Random Forests. Machine Learning, 45, pp.
5-32.
Castillejo-González, I.L., Lépez-Granados, F., García-Ferrer,
A., Pefia-Barragán, J.M., Jurado-Expósito, M., de la Orden,
M.S., González-Audicana, M., 2009. Object- and pixel-based
analysis for mapping crops and their agro-environmental
associated measures using QuickBird imagery. Computers and
Electronics in Agriculture, 68, pp. 207-215.
