Journal ArticleDOI
Estimation of ground cover composition per pixel after matching image and ground data with subpixel accuracy
TLDR
In this article, a new method is presented to estimate the abundance of different cover types within individual pixels, and several linear and non-linear multivariate calibration techniques are compared with respect to their ability to establish a relation between pixel values and fractions of ground cover.Abstract:
This paper is concerned with subpixel modelling of land cover estimation. A new method is presented to estimate the abundance of different cover types within individual pixels. Several linear and non-linear multivariate calibration techniques are compared with respect to their ability to establish a relation between pixel values and fractions of ground cover. The method is demonstrated using Landsat-TM imagery and data from Dutch heathlands. By using an optimization procedure for matching field data to image data, a solution was found for the problem of positioning errors in the training set formation.read more
Citations
More filters
Journal ArticleDOI
Linear spectral mixture models and support vector machines for remote sensing
TL;DR: It is shown that the constrained least squares LSMM is equivalent to the linear SVM, which relies on proving that the LSMM algorithm possesses the "maximum margin" property, which provides important insights about the role of the bias term and rank deficiency in the pure pixel matrix within the LS MM algorithm.
Journal ArticleDOI
A review of mixture modeling techniques for sub‐pixel land cover estimation
Charles Ichoku,Arnon Karnieli +1 more
TL;DR: In this article, five different types of mixture models are reviewed: linear, probabilistic, geometric-optical, stochastic geometric, and fuzzy models, and a summary of the conception and formulation of each of these types of models is presented.
Journal ArticleDOI
Using lidar and effective LAI data to evaluate IKONOS and Landsat 7 ETM+ vegetation cover estimates in a ponderosa pine forest
TL;DR: In this paper, spectral mixture analyses of IKONOS and ETM+ data were used to isolate spectral endmembers (bare soil, understory grass, and tree/shade) and calculate their subpixel fractional coverages.
Journal ArticleDOI
Spectral mixture analyses of hyperspectral data acquired using a tethered balloon
Xuexia Chen,Lee A. Vierling +1 more
TL;DR: In this paper, the Short Wave Aerostat-Mounted Imager (SWAMI) tethered balloon-mounted platform was utilized to evaluate linear and nonlinear spectral mixture analysis (SMA) for a grassland-conifer forest ecotone during the summer of 2003.
Journal ArticleDOI
Visualizing uncertainty in multi-spectral remotely sensed imagery
Lucy Bastin,Peter Fisher,Jo Wood +2 more
TL;DR: A Java-based toolkit, which uses interactive and linked views to enable visualization of data uncertainty by a variety of means, which allows users to consider error and uncertainty as integral elements of image data, to be viewed and explored, rather than as labels or indices attached to the data.
References
More filters
Book
Generalized Linear Models
Peter McCullagh,John A. Nelder +1 more
TL;DR: In this paper, a generalization of the analysis of variance is given for these models using log- likelihoods, illustrated by examples relating to four distributions; the Normal, Binomial (probit analysis, etc.), Poisson (contingency tables), and gamma (variance components).
Journal ArticleDOI
Generalized Linear Models
TL;DR: In this paper, the authors used iterative weighted linear regression to obtain maximum likelihood estimates of the parameters with observations distributed according to some exponential family and systematic effects that can be made linear by a suitable transformation.
Journal ArticleDOI
Review Article Digital change detection techniques using remotely-sensed data
TL;DR: An evaluation of results indicates that various procedures of change detection produce different maps of change even in the same environment.
Journal Article
Derivation and applications of probabilistic measures of class membership from the maximum-likelihood classification
TL;DR: The maximum likelihood classification of remotely sensed data involves considerable computational effort, in the process calculating a large amount of information on the class membership characteristics for each case (e.g., pixel) as mentioned in this paper.
Related Papers (5)
Spectral mixture modeling: A new analysis of rock and soil types at the Viking Lander 1 Site
Sub-pixel land cover composition estimation using a linear mixture model and fuzzy membership functions
Giles M. Foody,D. P. Cox +1 more