Home > Research > Publications & Outputs > Spatially weighted supervised classification fo...


Text available via DOI:

View graph of relations

Spatially weighted supervised classification for remote sensing

Research output: Contribution to journalJournal articlepeer-review

<mark>Journal publication date</mark>2004
<mark>Journal</mark>International Journal of Applied Earth Observation and Geoinformation
Issue number4
Number of pages15
Pages (from-to)277-291
Publication StatusPublished
<mark>Original language</mark>English


A simple approach for incorporating a spatial weighting into a supervised classifier for remote sensing applications is presented. The classifier modifies the feature-space distance-based metric with a spatial weighting. This is facilitated by the use of a non-parametric (k-nearest neighbour, k-NN) classifier in which the spatial location of each pixel in the training data set is known and available for analysis. A remotely sensed image was simulated using a combined Boolean and geostatistical unconditional simulation approach. This simulated image comprised four wavebands and represented three classes: Managed Grassland, Woodland and Rough Grassland. This image was then used to evaluate the spatially weighted classifier. The latter resulted in modest increase in the accuracy of classification over the original k-NN approach. Two spatial distance metrics were evaluated: the non-centred covariance and a simple inverse distance weighting. The inverse distance weighting resulted in the greatest increase in accuracy in this case.

Bibliographic note

M1 - 4