Estimating per-pixel thematic uncertainty in remote sensing classifications

Authors:
K. M. Brown;G. M. Foody;P. M. Atkinson
Affiliations:
Environment Agency Geomatics, Bath, BA2 9ES, UK;School of Geography, University of Nottingham, Nottingham, NG7 2RD, UK;School of Geography, University of Southampton, Southampton, SO17 1BJ, UK
Venue:
International Journal of Remote Sensing
Year:
2009

Citing 7
Cited 1

Probabilistic neural networks

Neural Networks
Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition
Mapping Land Cover from Remotely Sensed Data with a Softened Feedforward Neural Network Classification

Journal of Intelligent and Robotic Systems
Neural network uncertainty assessment using Bayesian statistics: a remote sensing application

Neural Computation
Supervised texture classification using a probabilistic neural network and constraint satisfaction model

IEEE Transactions on Neural Networks
Comparison of two different PNN training approaches for satellite cloud data classification

IEEE Transactions on Neural Networks
A temporally adaptive classifier for multispectral imagery

IEEE Transactions on Neural Networks

Using uncertainty information to combine soft classifications

IPMU'10 Proceedings of the Computational intelligence for knowledge-based systems design, and 13th international conference on Information processing and management of uncertainty

Quantified Score

Hi-index	0.00

Visualization

Abstract

Standard methodologies for estimating the thematic accuracy of hard classifications, such as those using the confusion matrix, do not provide indications of where thematic errors occur. However, spatial variation in thematic error can be a key variable affecting output errors when operations such as change detection are applied. One method of assessing thematic error on a per-pixel basis is to use the outputs of a classifier to estimate thematic uncertainty. Previous studies that have used this approach have generally used a single classifier and so comparisons of the relative accuracy of classifiers for predicting per-pixel thematic uncertainty have not been made. This paper compared three classification methods for predicting thematic uncertainty: the maximum likelihood, the multi-layer perceptron and the probabilistic neural network. The results of the study are discussed in terms of selecting the most suitable classifier for mapping land cover or predicting thematic uncertainty.