Exploitable results Verification data Summary: Verification data for remotely sensed information enable the user to establish the veracity and accuracy of their classification. This data is especially tuned for sub-pixel phenomena, and is a unique dataset in the context of the verification of information derived from satellite remote sensing. It provides detailed by-pixel information for considerable areas of large and small field agriculture, semi-natural and suburban landscapes. The original data is included either as point-based field survey data, or as exhaustive detailed interpretation of aerial photography. The methods for deriving sub-pixel proportions from these original data are documented. Visualization package VTBeans The VTBeans software package has been developed as part of the FLIERS project and used extensively by researchers at Leicester (and now by researchers around the world through the Web download). The package provides a palette of visualization tools, which can be dynamically linked to enable complex, multi-dimensional patterns to be viewed and explored simultaneously in a number of simpler co-ordinate spaces. The visualization tools includes some totally novel methods (e.g. random and serial animation), and some adaptations of familiar visual metaphors (e.g. fuzzy spectral signatures and interactive scatterplots). This allows the easy exploration of unfamiliar phenomena such as entropy and fuzzy membership, and gives the user great flexibility in selecting and linking co-ordinate spaces for visualization. The toolkit has been demonstrated at various conferences in Europe, Canada and Hong Kong, and has also been used to illustrate teaching of multivariate methods. Framework toolkit software package SFT Ver 2.0 Summary: The FLIERS software framework and toolkit (FLIERS SFT) software package has been developed as a key part of the work package, and tested extensively by researchers at Southampton and by external users. The FLIERS SFT package incorporates all of the new mapping strategies and algorithms, maintains GIS links via a portable binary image format and via the ability to read ERDAS Imagine files, and provides a complete set of data manipulation tools. The software has been used to investigate mapping strategies and to assess their performance as part of the Southampton work package in FLIERS. The new mapping strategies include a kernel-based area estimator, use of uncertainty from data to result together with texture for remotely sensed image analysis. In addition the software is already used in several external research projects, including ongoing projects at the University of Southampton investigating improving spatial resolution and predicting chlorophyll a from hyperspectral imagery. Textural signature, Bayesian estimation of the Markov random field parameters The work on the Bayesian estimation of Markov fields in the FLIERS project has been a step towards the full exploitation of the Markov field as a model of texture. Since aerial and satellite images may contain clearly visible textural segments and also smoothly changing textures, and in general, no a priori information the tessellation of an image is available, simultaneously unsupervised estimation of both the textural homogeneity and the parameters was necessary. Markov field parameters were recognized as a potential set of textural signature, but their estimation was a problem. A separation of the problems of segmentation and parameterization was not wanted. By posing the problem as a Bayesian estimation problem, i.e. by writing the joint posterior probability density of a tessellation and parameters on condition of the data and then estimating the posterior mean of the field parameters, both problems were solved simultaneously. The advantage of the Bayesian formulation lies in the posterior density: it gives the complete statistical description of the result and can be used to derive metrics on uncertainties like sample size effects and noise. The parameters can be used, for example, for a hierarchical model or as in our as an input to a classifier. The parameterization is under certain general conditions consistent from one image to another. This provides the opportunity to screen textural changes in a series of images taken from one target - landscape, cell cultivation, ice. The task was completed by writing a software program which estimates the Markov parameters using the Markov Chain Monte Carlo algorithm. The parameter values with their uncertainty estimates are then computable as an input to a classifier. Virtual reality system Summary: The virtual reality (VR) system that has been developed during the FLIERS project can be used to visualize multi-dimensional earth observation data in an effective way. It can be used to explore results of techniques used to extract quantitative sub-pixel information, such as fuzzy membership and spectral unmixing. The VR system allows for the display, in an immersive graphical environment, of several different three-dimensional representations of the same data. This approach helps understand the structure of information in different feature sub-spaces, which can aid modeling and product extraction. The exploratory tool developed during this project extends this functionality by combining the methods normally present in desktop applications, with the enhanced abilities (both quantitative and qualitative) of an immersive system. Searching for OpenAIRE data... There was an error trying to search data from OpenAIRE No results available
