论文信息 - Automatic change detection in RapidEye data using the combined MAD and kernel MAF methods

Automatic change detection in RapidEye data using the combined MAD and kernel MAF methods

The IR-MAD components show changes for a large part of the entire subset. Especially phenological changes in the agricultural fields surrounding the open pit are predominant. As opposed to this, kMAF components focus more on changes in the open-cast mine (and changes due to the two clouds and their shadows, not visible in the zoom). Ground data were available from bucket-wheel excavators on the extraction side (to the northwest in the open pit) in terms of elevation data for both dates. No ground data were available for changes due to backfill (southeastern part of the open pit) or changes due to mining machines other than the bucket-wheels.

Allan Aasbjerg Nielsen | Frank Thonfeld | Morton J. Canty | Antje Hecheltjen

[1] H. Hotelling. Analysis of a complex of statistical variables into principal components. , 1933 .

[2] Allan Aasbjerg Nielsen. Kernel parameter dependence in spatial factor analysis , 2010, 2010 IEEE International Geoscience and Remote Sensing Symposium.

[3] Bernhard Schölkopf,et al. Nonlinear Component Analysis as a Kernel Eigenvalue Problem , 1998, Neural Computation.

[4] J. Grodecki,et al. Block Adjustment of High-Resolution Satellite Images Described by Rational Polynomials , 2003 .

[5] Allan Aasbjerg Nielsen,et al. Kernel Maximum Autocorrelation Factor and Minimum Noise Fraction Transformations , 2011, IEEE Transactions on Image Processing.

[6] Paul Switzer,et al. Ordering of time-difference data from multispectral imagery , 1986 .

[7] H. Hotelling. Relations Between Two Sets of Variates , 1936 .

[8] Allan Aasbjerg Nielsen,et al. The Regularized Iteratively Reweighted MAD Method for Change Detection in Multi- and Hyperspectral Data , 2007, IEEE Transactions on Image Processing.