429 publications from this institution
The accuracy of supervised classification is dependent to a large extent on the input training data. In general, the analyst aims to capture a large training set to fully describe the classes spectrally with the conventional statistical classifier in mind. However, it is not always necessary to provide a complete description of the classes if using a support vector machine (SVM) as the classifier. A key attraction of the SVM based approach to classification is that it seeks to fit an optimal hyperplane between the classes and since it uses only the training samples that lie at the edge of the class distributions in feature space (support vectors) it may require only a small training sample. The paper shows the potential of SVM of using only a fraction of the training data (support vectors) collected by the usual random scheme for a study carried in the south western part of Punjab state of India
List of Contributors. Foreword. Preface. Uncertainty in Remote Sensing and GIS: Fundamentals (P. M. Atkinson and G. M. Foody). Uncertainty in Remote Sensing (C. E. Woodcock). Toward a Comprehensive View of Uncertainty in Remote Sensing Analysis (J. L. Dungan). On the Ambiguity Induced by a Remote Sensor s PSF (J. F. Manslow and M. S. Nixon) . Pixel Unmixing at the Sub pixel Scale Based on Land Cover Class Probabilities: Application to Urban Areas (Q. Zhan, M. Molenaar and A. Lucieer). Super resolution Land Cover Mapping from Remotely Sensed Imagery using a Hopfield Neural Network (A. J. Tatem, H. G. Lewis, P. M. Atkinson and M. S. Nixon). Uncertainty in Land Cover Mapping from Remotely Sensed Data using Textural Algorithms and Artificial Neural Networks (A. M. Jakomulska and J. P. Radomski). Remote Monitoring of the Impact of ENSO related Drought on Sabah Rainforest using NOAA AVHRR Middle Infrared Reflectance: Exploring Emissivity Uncertainty (D. S. Boyd, P. C. Phipps, W. J. Duane and G. M. Foody). Land Cover Map 2000 and Meta data at the Land Parcel Level (G. M. Smith and R. M. F uller). Analysing Uncertainty Propagation in GIS: Why is it not that Simple? (G. B.M. Heuvelink). Managing uncertainty in a Geospatial Model of Biodiversity (A. J. Warren, M. J. Collins, E. A. Johnson and P. F. Ehlers). The Effects of Uncertainty in Deposition Data on Predicting Exceedances of Acidity Critical Loads for Sensitive UK Ecosystems (E. Heywood, J. R. Hall and R. A. Wadsworth). Vertical and Horizontal Spatial Variation of Geostatistical Prediction (A. Wameling). Geostatistical Prediction and Simulation of the Lateral and Vertical Extent of Soil Horizons (B. Warr, I. O. A. Odeh and M. A. Oliver). Increasing the Accuracy of Predictions of Monthly Precipitation in Great Britain using Kriging with an External Drift (C. D. Lloyd). Conditional Simulation Applied to Uncertainty Assessment in DTMs (J. Senegas, M. Schmitt and P. Nonin). Current Status of Uncertainty Issues in Remote Sensing and GIS (G. M. Foody and P. M. Atkinson). Index.
Training patterns vary in their importance in image classification. Consequently, the selection and refinement of training sets can have a major impact on classification accuracy. For classification by a neural network, training patterns that lie close to the location of decision boundaries in feature space may aid the derivation of an accurate classification. The role of such border training patterns and their identification is discussed in relation to a series of crop classifications from airborne Thematic Mapper data. It is shown that a neural network trained with a set of border patterns may have a lower accuracy of learning but a significantly higher accuracy of generalization than one trained with a set of patterns drawn from the cores of the classes. Unfortunately, conventional training pattern selection and refinement procedures tend to favour core training patterns. For classification by a neural network, procedures which encourage the inclusion of border training patterns should be adopted as this may facilitate the production of an accurate classification.
The ever-wet tropics are under threat from ENSO events and there is a need for a monitoring system to analyse and describe their responses to such events. This letter explores the relative value of using NOAA AVHRR middle infrared (MIR) reflectance data and NDVI data for the monitoring of ENSO-related drought stress of a tropical forest ecosystem in Sabah, Malaysia. Relationships between rainfall and MIR reflectance were examined. Correlation coefficients are generally large and significant (at 0.1 level) while those between rainfall and NDVI were small and insignificant. This letter concludes that there is potential in using MIR reflectance for monitoring the effects of ENSO-induced drought stress on these forests and this has a bearing on how NOAA AVHRR data may be used to further our knowledge on the impacts of ENSO events on tropical forest environments.
The main objective of this research is to assess the impact of intra-class spectral variation on the accuracy of soft classification and super-resolution mapping. The accuracy of both analyses was negatively related to the degree of intra-class spectral variation, but the effect could be reduced through the use of spectral sub-classes. The latter is illustrated in mapping the shoreline at a sub-pixel scale from Landsat ETM+ data. Reducing the degree of intra-class spectral variation increased the accuracy of soft classification, with the correlation between predicted and actual class coverage rising from 0.87 to 0.94, and super-resolution mapping, with the RMSE in shoreline location decreasing from 41.13 m to 35.22 m.
Information on tropical forest types and their biophysical properties is needed as they underpin our understanding and prediction of Earth system processes. This paper explores the potential use of reflected MIR, derived from channel 3 of the NOAA AVHRR sensor, for estimating the biomass of Cameroonian tropical forests. Results indicate significant inverse relationships between biomass and reflected MIR.
Neural networks are powerful general purpose computing tools. They have become popular in the analysis of remotely sensed data, particularly for classification and regression-type problems in which they have often been demonstrated to extract information more accurately than conventional methods. Although not free from problems, it seems likely that neural networks will be used increasingly in ecological research using remote sensing. Moreover, as some of the problems encountered in use of neural networks arise from a tendency to focus upon the MLP only it is likely that there will be a greater use of other network types. In addition, it is expected that the range of applications of neural networks in remote sensing will broaden. Applications in which neural networks have already been used and increased usage may be expected include: image preprocessing (e.g. geometric, atmospheric and radiometric correction), stereo-matching imagery, image compression, feature extraction, map generalisation, multi-source data analysis, data fusion and image sharpening (e.g. Day, 1997; Foody, 1999a). Thus while neural networks have rapidly become established in remote sensing it is likely that they will be used increasingly and in a broader range of activities that will help exploit more fully the potential of remote sensing as a useful tool in ecological research.
The signal-to-noise ratio (SNR) has been estimated for remotely sensed imagery using several image-based methods such as the homogeneous area (HA) and geostatistical (GS) methods. For certain procedures such as regression, an alternative SNR (SNRvar), the ratio of the variance in the signal to the variance in the noise, is potentially more informative and useful. In this paper, the GS method was modified to estimate the SNRvar, referred to as the SNRvar(GS). Specifically, the sill variance c of the fitted variogram model was used to estimate the variance of the signal component and the nugget variance c0 of the fitted model was used to estimate the variance of the noise. The assumptions required in this estimation are presented. The SNRvar(GS) was estimated using the modified GS method for six different land-covers and a range of wavelengths to explore its properties. The SNR*var(GS) was found to vary as a function of both wavelength and land-cover. The SNR*var(GS) represents a useful statistic that should be estimated and presented for different land-cover types and even per-pixel using a local moving window kernel.
Remotely sensed data are an attractive source of land cover information. In many applications the required information relates to the extent or coverage of
The mixed pixel problem may be reduced through the use of a soft image classification and super-resolution mapping analyses. Here, the positive attributes of two popular super-resolution mapping methods, based on contouring and the Hopfield neural network, are combined. For a binary classification scenario, the method is based on fitting a contour of equal class membership to a pre-final output of a standard Hopfield neural network. Analyses of simulated and real image data sets show that the proposed method is more accurate than the standard contouring and Hopfield neural network based methods, with error typically reduced by a factor of two or more. The sensitivity of the Hopfield neural network based approaches to the setting of a gain function is also explored.
Remote sensing has much to gain from citizen sensing. This is particularly evident in relation to the provision of ground reference data for use in the training and testing stages of supervised image classification analyses used to generate thematic maps from remotely sensed data. Citizens are able to provide data over large geographical areas inexpensively, addressing potential problems connected with ground data samples and authoritative good practices. The great potential of citizen sensing is, however, constrained by concerns, notably with the quality of the data generated. This paper provides an overview of some of the key issues in citizen sensing to support thematic mapping from remote sensing. It highlights especially some of the ways that citizen sensing can aid remote sensing studies as a source of ground reference data.
No abstract is provided for this article.
The effect of spatial, spectral and noise degradations on the accuracy of two highly contrasting thematic labelling scenarios was investigated. The study used hyperspectral imagery of a site near Falmouth, UK, to assess the effect of the data degradations on the accuracy of supervised classification when the H-resolution scene model was applicable and on labelling when an L-resolution scene model was applicable and no ground data were available. In both scenarios, the spatial, spectral and noise degradations affected the accuracy of labelling. However, over the range of degradations investigated, the noise content of the data was consistently noted to be a major variable affecting the accuracy of labelling.
