Pretražite po imenu i prezimenu autora, mentora, urednika, prevoditelja

Napredna pretraga

Pregled bibliografske jedinice broj: 108844

Fast LCNN ica for Unsupervised Hyperspectral Image Classifier


Kopriva, Ivica; Szu, Harold;
Fast LCNN ica for Unsupervised Hyperspectral Image Classifier // Wavelets and Independent Component Analysis IX / Szu, Harold ; Buss, James ; Bell, Anthony ; (ur.).
Bellingham, USA: SPIE, 2002. str. 169-183 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)


CROSBI ID: 108844 Za ispravke kontaktirajte CROSBI podršku putem web obrasca

Naslov
Fast LCNN ica for Unsupervised Hyperspectral Image Classifier

Autori
Kopriva, Ivica ; Szu, Harold ;

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Wavelets and Independent Component Analysis IX / Szu, Harold ; Buss, James ; Bell, Anthony ; - Bellingham, USA : SPIE, 2002, 169-183

Skup
SPIE AeroSense Symposium - Wavelets and Independent Component Analysis IX

Mjesto i datum
Orlando, Florida, 1-5.4.2002

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Hyper-spectral imaging; sub-pixel resolution; constrained maximum entropy; fast Lagrangian method; unsupervised neural networks; independent component analysis; independent class analysis.

Sažetak
Since in remote sensing each pixel could have its own unique radiation source including man-made objects associated with different spectral reflectance matrix A, we could not average over neighborhood pixels. Instead, we solve pixel-by-pixel independent classes analysis (ica) without pixel average by Lagrange Constraint of the data measurement model and Gibbs&#8217 ; equal a priori probability assumption based on Shannon&#8217 ; s Entropy with probability normalization condition for an arbitrary number of M classes that is bounded by the spectral data components N. We formulate the Fast Lagrangian method to maximize the Shannon entropy with the equality constraints in order to achieve O(N) numerical complexity contrary to the O(N2) numerical complexity associated with the solution of the inverse problem required in the classical Lagrangian formulation. Trivial equal probability solution with uniformly distributed class vector is avoided by introducing additional set of the inequality constraints. The unknown spectral reflectance matrix A is estimated blindly in non-parameterized form minimizing an LMS energy function . We apply the Riemannian metric to the gradient learning for reproducing the biological Hebbian rule in terms of a full rank vector outer product formula and demonstrate faster convergence than standard Euclidean gradient. Since the proposed Fast Lagrangian method has O(N) numerical complexity we have achieved a real time hyperspectral remote sensing capability as platform moves, samples and processes. A FPGA firmware implementation for massive pixel parallel algorithm has been fired for patent.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika



POVEZANOST RADA


Projekti:
036024

Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb

Profili:

Avatar Url Ivica Kopriva (autor)


Citiraj ovu publikaciju:

Kopriva, Ivica; Szu, Harold;
Fast LCNN ica for Unsupervised Hyperspectral Image Classifier // Wavelets and Independent Component Analysis IX / Szu, Harold ; Buss, James ; Bell, Anthony ; (ur.).
Bellingham, USA: SPIE, 2002. str. 169-183 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
Kopriva, I., Szu, H. & (2002) Fast LCNN ica for Unsupervised Hyperspectral Image Classifier. U: Szu, H., Buss, J., Bell, A. & (ur.)Wavelets and Independent Component Analysis IX.
@article{article, year = {2002}, pages = {169-183}, keywords = {Hyper-spectral imaging, sub-pixel resolution, constrained maximum entropy, fast Lagrangian method, unsupervised neural networks, independent component analysis, independent class analysis.}, title = {Fast LCNN ica for Unsupervised Hyperspectral Image Classifier}, keyword = {Hyper-spectral imaging, sub-pixel resolution, constrained maximum entropy, fast Lagrangian method, unsupervised neural networks, independent component analysis, independent class analysis.}, publisher = {SPIE}, publisherplace = {Orlando, Florida} }
@article{article, year = {2002}, pages = {169-183}, keywords = {Hyper-spectral imaging, sub-pixel resolution, constrained maximum entropy, fast Lagrangian method, unsupervised neural networks, independent component analysis, independent class analysis.}, title = {Fast LCNN ica for Unsupervised Hyperspectral Image Classifier}, keyword = {Hyper-spectral imaging, sub-pixel resolution, constrained maximum entropy, fast Lagrangian method, unsupervised neural networks, independent component analysis, independent class analysis.}, publisher = {SPIE}, publisherplace = {Orlando, Florida} }




Contrast
Increase Font
Decrease Font
Dyslexic Font