Spectral resampling based on user-defined inter-band correlation filter: C3 and C4 grass species classification
作者： Clement Adjorlolo , Onisimo Mutanga , Moses A. Cho , Riyad Ismail
DOI: 10.1016/J.JAG.2012.07.011
关键词: Function (mathematics) 、 Multicollinearity 、 Geography 、 Resampling 、 Random forest 、 Correlation filter 、 Statistics 、 Correlation 、 Hyperspectral imaging 、 Weighting
摘要: 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 spectral dependence information between chosen band-centre its shorter longer wavelength neighbours. Weighting threshold (WTC, Pearson's r ) calculated, whereby = 1 at band-centre. Various WTC ( = 0.99, = 0.95 = 0.90) were assessed, bands with coefficients beyond assigned = 0. resultant random forest analysis classify situ C 3 4 grass canopy reflectance. respective datasets yielded improved accuracies (kappa = 0.82, 0.79 0.76) less correlated wavebands when compared resampled Hyperion (kappa = 0.76). Overall, results obtained from study suggested that should account for improve overall accuracy as well reducing multicollinearity.
harvard.edu
sci-hub.se 参考文章(56)
George Alan Blackburn, Quantifying Chlorophylls and Caroteniods at Leaf and Canopy Scales: An Evaluation of Some Hyperspectral Approaches Remote Sensing of Environment. ,vol. 66, pp. 273- 285 ,(1998) , 10.1016/S0034-4257(98)00059-5
Matthew Wiener, Andy Liaw, Classification and Regression by randomForest ,(2007)
Susan L. Ustin, John A. Gamon, Remote sensing of plant functional types New Phytologist. ,vol. 186, pp. 795- 816 ,(2010) , 10.1111/J.1469-8137.2010.03284.X
T.R. Hill, Description, classification and ordination of the dominant vegetation communities, Cathedral Peak, KwaZulu-Natal Drakensberg South African Journal of Botany. ,vol. 62, pp. 263- 269 ,(1996) , 10.1016/S0254-6299(15)30655-4
Achim Zeileis, Carolin Strobl, Danger: High Power! – Exploring the Statistical Properties of a Test for Random Forest Variable Importance ,(2008) , 10.5282/UBM/EPUB.2111
O Mutanga, A.K Skidmore, H.H.T Prins, Predicting in situ pasture quality in the Kruger National Park, South Africa, using continuum-removed absorption features Remote Sensing of Environment. ,vol. 89, pp. 393- 408 ,(2004) , 10.1016/J.RSE.2003.11.001
K.S. Schmidt, A.K. Skidmore, Spectral discrimination of vegetation types in a coastal wetland Remote Sensing of Environment. ,vol. 85, pp. 92- 108 ,(2003) , 10.1016/S0034-4257(02)00196-7
Stephen V. Stehman, Selecting and interpreting measures of thematic classification accuracy Remote Sensing of Environment. ,vol. 62, pp. 77- 89 ,(1997) , 10.1016/S0034-4257(97)00083-7
Michele Dalponte, Lorenzo Bruzzone, Loris Vescovo, Damiano Gianelle, The role of spectral resolution and classifier complexity in the analysis of hyperspectral images of forest areas. Remote Sensing of Environment. ,vol. 113, pp. 2345- 2355 ,(2007) , 10.1016/J.RSE.2009.06.013
D. N. H. HORLER, M. DOCKRAY, J. BARBER, The red edge of plant leaf reflectance International Journal of Remote Sensing. ,vol. 4, pp. 273- 288 ,(1983) , 10.1080/01431168308948546