TY  - CONF
AU  - Lange, Julius
AU  - Cavallaro, Gabriele
AU  - Götz, Markus
AU  - Ernir, Erlingsson
AU  - Riedel, Morris
TI  - The Influence of Sampling Methods on Pixel-Wise Hyperspectral Image Classification with 3D Convolutional Neural Networks
M1  - FZJ-2018-04967
SP  - 2087 - 2090
PY  - 2018
AB  - Supervised image classification is one of the essential techniques for generating semantic maps from remotely sensed images.The lack of labeled ground truth datasets, due to the inherent time effort and cost involved in collecting training samples, has led to the practice of training and validating new classifiers within a single image. In line with that, the dominant approach for the division of the available ground truth into disjoint training and test sets is random sampling. This paper discusses the problems that arise when this strategy is adopted in conjunction with spectral-spatial and pixel-wise classifiers such as 3D Convolutional Neural Networks (3D CNN). It is shown that a random sampling scheme leads to a violation of the independence assumption and to the illusion that global knowledge is extracted from the training set.To tackle this issue, two improved sampling strategies based on the Density-Based Clustering Algorithm (DBSCAN) are proposed. They minimize the violation of the train and test samples independence assumption and thus ensure an honest estimation of the generalization capabilities of the classifier.
T2  - IEEE International Geoscience and Remote Sensing Symposium (IGARSS)
CY  - 22 Jul 2018 - 27 Jul 2018, Valencia (Spain)
Y2  - 22 Jul 2018 - 27 Jul 2018
M2  - Valencia, Spain
LB  - PUB:(DE-HGF)8 ; PUB:(DE-HGF)7
DO  - DOI:10.1109/IGARSS.2018.8518671
UR  - https://juser.fz-juelich.de/record/851272
ER  -