dc.contributor.author |
Adjorlolo, C
|
|
dc.contributor.author |
Mutanga, O
|
|
dc.contributor.author |
Cho, Moses A
|
|
dc.contributor.author |
Ismail, R
|
|
dc.date.accessioned |
2013-01-28T08:04:10Z |
|
dc.date.available |
2013-01-28T08:04:10Z |
|
dc.date.issued |
2013-04 |
|
dc.identifier.citation |
Adjorlolo, C., Mutanga, O., Cho, M.A. and Ismail, R. 2013. Spectral resampling based on user-defined interband correlation filter: C3 and C4 grass species classification. International Journal of Applied Earth Observation and Geoinformation Science, vol. 21, pp. 535-544 |
en_US |
dc.identifier.issn |
0303-2434 |
|
dc.identifier.uri |
http://www.sciencedirect.com/science/article/pii/S0303243412001493
|
|
dc.identifier.uri |
http://hdl.handle.net/10204/6447
|
|
dc.description |
Copyright: 2012 Elsevier. This is the preprint version of the work. The definitive version is published in International Journal of Applied Earth Observation and Geoinformation Science, vol. 21, pp. 535-544 |
en_US |
dc.description.abstract |
In this paper, a user-defined inter-band correlation filter function was used to resample hyperspectral data and thereby mitigate the problem of multicollinearity in classification analysis. The proposed resampling technique convolves the spectral dependence information between a chosen band-centre and its shorter and longer wavelength neighbours. Weighting threshold of inter-band correlation (WTC, Pearson’s r) was calculated, whereby r = 1 at the band-centre. Various WTC (r = 0.99, r = 0.95 and r = 0.90) were assessed, and bands with 0 coefficients beyond a chosen threshold were assigned r = 0. The resultant data were used in the random forest analysis to classify C3 and C4 grass species. The respective WTC datasets yielded improved classification accuracies (kappa = 0.82, 0.79 and 0.76) with less correlated wavebands when compared to resampled Hyperion bands (kappa = 0.76). Overall, the results obtained from this study suggested that resampling of hyperspectral data should account for the spectral dependence information to improve overall classification accuracy as well as reducing the problem of multicollinearity. |
en_US |
dc.language.iso |
en |
en_US |
dc.publisher |
Elsevier |
en_US |
dc.relation.ispartofseries |
Workflow;9533 |
|
dc.subject |
Earth observation |
en_US |
dc.subject |
Hyperspectral data |
en_US |
dc.subject |
Spectral resampling |
en_US |
dc.subject |
Inter-band correlation |
en_US |
dc.subject |
Grass species classification |
en_US |
dc.subject |
Random forests |
en_US |
dc.title |
Spectral resampling based on user-defined interband correlation filter: C3 and C4 grass species classification |
en_US |
dc.type |
Article |
en_US |
dc.identifier.apacitation |
Adjorlolo, C., Mutanga, O., Cho, M. A., & Ismail, R. (2013). Spectral resampling based on user-defined interband correlation filter: C3 and C4 grass species classification. http://hdl.handle.net/10204/6447 |
en_ZA |
dc.identifier.chicagocitation |
Adjorlolo, C, O Mutanga, Moses A Cho, and R Ismail "Spectral resampling based on user-defined interband correlation filter: C3 and C4 grass species classification." (2013) http://hdl.handle.net/10204/6447 |
en_ZA |
dc.identifier.vancouvercitation |
Adjorlolo C, Mutanga O, Cho MA, Ismail R. Spectral resampling based on user-defined interband correlation filter: C3 and C4 grass species classification. 2013; http://hdl.handle.net/10204/6447. |
en_ZA |
dc.identifier.ris |
TY - Article
AU - Adjorlolo, C
AU - Mutanga, O
AU - Cho, Moses A
AU - Ismail, R
AB - In this paper, a user-defined inter-band correlation filter function was used to resample hyperspectral data and thereby mitigate the problem of multicollinearity in classification analysis. The proposed resampling technique convolves the spectral dependence information between a chosen band-centre and its shorter and longer wavelength neighbours. Weighting threshold of inter-band correlation (WTC, Pearson’s r) was calculated, whereby r = 1 at the band-centre. Various WTC (r = 0.99, r = 0.95 and r = 0.90) were assessed, and bands with 0 coefficients beyond a chosen threshold were assigned r = 0. The resultant data were used in the random forest analysis to classify C3 and C4 grass species. The respective WTC datasets yielded improved classification accuracies (kappa = 0.82, 0.79 and 0.76) with less correlated wavebands when compared to resampled Hyperion bands (kappa = 0.76). Overall, the results obtained from this study suggested that resampling of hyperspectral data should account for the spectral dependence information to improve overall classification accuracy as well as reducing the problem of multicollinearity.
DA - 2013-04
DB - ResearchSpace
DP - CSIR
KW - Earth observation
KW - Hyperspectral data
KW - Spectral resampling
KW - Inter-band correlation
KW - Grass species classification
KW - Random forests
LK - https://researchspace.csir.co.za
PY - 2013
SM - 0303-2434
T1 - Spectral resampling based on user-defined interband correlation filter: C3 and C4 grass species classification
TI - Spectral resampling based on user-defined interband correlation filter: C3 and C4 grass species classification
UR - http://hdl.handle.net/10204/6447
ER -
|
en_ZA |