Dr. Morton J. Canty Profile

Dr. Morton J. Canty

at Forschungszentrum Jülich GmbH

SPIE Involvement:

Author

Publications (8)

Proceedings Article | 23 October 2010 Paper

Linear and kernel methods for multi- and hypervariate change detection

Allan Nielsen, Morton Canty

Proceedings Volume 7830, 78300S (2010) https://doi.org/10.1117/12.870781

KEYWORDS: Remote sensing, Principal component analysis, Image analysis, Image processing, Internet, Image enhancement, Mining, Environmental sensing, RGB color model, MATLAB

Read Abstract +

The iteratively re-weighted multivariate alteration detection (IR-MAD) algorithm may be used both for unsuper- vised change detection in multi- and hyperspectral remote sensing imagery as well as for automatic radiometric normalization of multi- or hypervariate multitemporal image sequences. Principal component analysis (PCA) as well as maximum autocorrelation factor (MAF) and minimum noise fraction (MNF) analyses of IR-MAD images, both linear and kernel-based (which are nonlinear), may further enhance change signals relative to no-change background. The kernel versions are based on a dual formulation, also termed Q-mode analysis, in which the data enter into the analysis via inner products in the Gram matrix only. In the kernel version the inner products of the original data are replaced by inner products between nonlinear mappings into higher dimensional feature space. Via kernel substitution, also known as the kernel trick, these inner products between the mappings are in turn replaced by a kernel function and all quantities needed in the analysis are expressed in terms of the kernel function. This means that we need not know the nonlinear mappings explicitly. Kernel principal component analysis (PCA), kernel MAF and kernel MNF analyses handle nonlinearities by implicitly transforming data into high (even in¯nite) dimensional feature space via the kernel function and then performing a linear analysis in that space. In image analysis the Gram matrix is often prohibitively large (its size is the number of pixels in the image squared). In this case we may sub-sample the image and carry out the kernel eigenvalue analysis on a set of training data samples only. To obtain a transformed version of the entire image we then project all pixels, which we call the test data, mapped nonlinearly onto the primal eigenvectors. IDL (Interactive Data Language) implementations of IR-MAD, automatic radiometric normalization and kernel PCA/MAF/MNF transformations have been written which function as transparent and fully integrated extensions of the ENVI remote sensing image analysis environment. Also, Matlab code exists which allows for fast data exploration and experimentation with smaller datasets. Computationally demanding kernelization of test data with training data and kernel image projections have been programmed to run on massively parallel CUDA-enabled graphics processors, when available, giving a tenfold speed enhancement. The software will be available from the authors' websites in the near future. A data example shows the application to bi-temporal RapidEye data covering the Garzweiler open pit mine in the Ruhr area in Germany.

Proceedings Article | 28 September 2009 Paper

Kernel principal component and maximum autocorrelation factor analyses for change detection

Allan Nielsen, Morton Canty

Proceedings Volume 7477, 74770T (2009) https://doi.org/10.1117/12.829645

KEYWORDS: Principal component analysis, Factor analysis, Earth observing sensors, Signal to noise ratio, Interference (communication), Satellite imaging, Satellites, Cameras, Detection and tracking algorithms, Landsat

Read Abstract +

Proceedings Article | 10 October 2008 Paper

Kernel principal component analysis for change detection

Allan Nielsen, Morton Canty

Proceedings Volume 7109, 71090T (2008) https://doi.org/10.1117/12.800141

KEYWORDS: Principal component analysis, Data acquisition, Data modeling, Information science, Data centers, Aerospace engineering, Navigation systems, Sensors, Chemistry, Visualization

Read Abstract +

Proceedings Article | 29 October 2007 Paper

Investigation of alternative iteration schemes for the IR-MAD algorithm

Morton Canty, Allan Nielsen

Proceedings Volume 6748, 674808 (2007) https://doi.org/10.1117/12.736409

KEYWORDS: Copper, Image fusion, Landsat, Remote sensing, Sensors, RGB color model, Composites, Data centers, Multispectral imaging, Earth observing sensors

Read Abstract +

Proceedings Article | 11 October 2006 Paper

Targeted information collection for nuclear verification: a combination of object-based images analysis and pixel-based change detection with very high resolution satellite data exemplified for Iranian nuclear sites

Sven Nussbaum, Irmgard Niemeyer, Morton Canty

Proceedings Volume 6365, 63650J (2006) https://doi.org/10.1117/12.688258

KEYWORDS: Buildings, Satellites, Image analysis, Earth observing sensors, Satellite imaging, Image classification, Image resolution, Target detection, Uranium, Image segmentation

Read Abstract +

Proceedings Article | 21 October 2005 Paper

Feature recognition in the context of automated object-oriented analysis of remote sensing data monitoring the Iranian nuclear sites

S. Nussbaum, I. Niemeyer, M.J. Canty

Proceedings Volume 5988, 598805 (2005) https://doi.org/10.1117/12.629581

KEYWORDS: Image analysis, Shape analysis, Buildings, Statistical analysis, Satellite imaging, Satellites, Image segmentation, Feature extraction, Vegetation, Remote sensing

Read Abstract +

Proceedings Article | 10 November 2004 Paper

Unsupervised classification of changes in multispectral satellite imagery

Morton Canty, Allan Nielsen

Proceedings Volume 5573, (2004) https://doi.org/10.1117/12.565090

KEYWORDS: Signal to noise ratio, Multispectral imaging, Satellites, Fuzzy logic, Image classification, Satellite imaging, Earth observing sensors, Landsat, Expectation maximization algorithms, Statistical analysis

Read Abstract +

Proceedings Article | 23 January 2002 Paper

Object oriented post-classification of change images

Irmgard Niemeyer, Morton Canty

Proceedings Volume 4545, (2002) https://doi.org/10.1117/12.453661

KEYWORDS: Earth observing sensors, Satellites, Image segmentation, Spatial resolution, Image analysis, Satellite imaging, Image resolution, High resolution satellite images, Satellite communications, Landsat

Read Abstract +

Showing 5 of 8 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years