Ortsaufgelöste spektrale Entmischung mit Hilfe von konvolutionalen neuronalen Netzen / Spatially resolved spectral unmixing using convolutional neural networks

Tm - Technisches Messen

Benzing

León

2020

Self Cite

ZusammenfassungIn diesem Beitrag wird eine Methode vorgestellt, mit der Daten zum Training von künstlichen neuronalen Netzen für die spektrale Entmischung erzeugt werden. Dies hat den Vorteil, dass nur Spektren der beteiligten Reinstoffe und, je nach verwendetem Modell, wenige Mischspektren zur Bestimmung der Parameter an realen Daten zur Verfügung stehen müssen. Daraus können mit Hilfe von Mischmodellen, die auch direkt zur Entmischung herangezogen werden können, große Mengen an Spektren zum Trainieren erzeugt werden. Im Gegensatz zum direkten Einsatz der Mischmodelle, wo von einem Spektrum pro Reinstoff ausgegangen wird, wird hier die Spektrenvariabilität berücksichtigt, indem unterschiedliche Spektren desselben Reinstoffs genutzt werden. Dabei wird die Eigenschaft künstlicher neuronaler Netze ausgenutzt, aussagekräftige Merkmale auf Basis großer Datenmengen lernen zu können.

Section: Künstliche Neuronale Netzeunclassified

Section: Verwendete Netzstrukturunclassified

Section: Vergleich Der Entmischungsverfahrenunclassified

unclassified

See 3 more Smart Citations

Erzeugung künstlicher Datensätze zum Training konvolutionaler neuronaler Netze für die spektrale Entmischung

Tm - Technisches Messen

Benzing

León

2020

Self Cite

CNN-based augmentation strategy for spectral unmixing datasets considering spectral variability

Image and Signal Processing for Remote Sensing XXVI

Heizmann

2020

Self Cite

Spectral unmixing is often relying on a mixing model that is only an approximation. Artificial neural networks have the advantage of not requiring model knowledge. Additional advantages in the domain of spectral unmixing are the easy handling of spectral variability and the possibility to force the sum-to-one and the non-negativity constraints. However, they need a lot of significant training data to achieve good results.To overcome this problem, mainly for classification problems, augmentation strategies are widely used to increase the size of training datasets synthetically. Spectral unmixing can be considered as a regression problem, where data augmentation is also feasible. One intuitive strategy is to generate spectra based on abundances that do not occur in the training dataset, while taking spectral variability into account.For the implementation of this approach, we use a convolutional neural network (CNN), where the input variables are extended by random values. This allows spectral variability to be taken into account. The random inputs are re-sampled for each data point in every epoch. During training the CNN learns the mixing model and the characteristic spectral variability of the training dataset. Additional spectra can be generated afterwards for any given abundances to extend the original training dataset.Because the generative CNN minimizes the error between generated spectra and the corresponding ground truth for the whole dataset during training, the variance of the spectra based on the same abundances is lower than in the training data. We have investigated two approaches for improvement. One is to increase the variance of the random input variables when generating new spectra. For the second, the estimated covariance matrices are considered by the objective function.The presented method is evaluated with real data, which were captured in our image processing laboratory. We found that the augmentation of the training dataset with the presented strategy leads to an improvement for spectral unmixing of the test dataset.

GAN-regularized augmentation strategy for spectral datasets

Tm - Technisches Messen

Heizmann

2022

Artificial neural networks are used in various fields including spectral unmixing, which is used to determine the proportions of substances involved in a mixture, and achieve promising results. This is especially true if there is a non-linear relationship between the spectra of mixtures and the spectra of the substances involved (pure spectra). To achieve sufficient results, neural networks need lots of representative training data. We present a method that extends existing training data for spectral unmixing consisting of spectra of mixtures by learning the mixing characteristic using an artificial neural network. Spectral variability is considered by random inputs. The network structure used is a generative adversarial net that takes the dependence on the abundances of pure substances into account by an additional term in its objective function, which is minimized during training. After training further data for abundance vectors for which there is no real measurement data in the original training dataset can be generated. A neural network trained with the augmented training dataset shows better performance in spectral unmixing compared to being trained with the original dataset. The presented network structure improves already existing results obtained with a generative convolutional neural network, which is superior to model-based approaches.