Spatially weighted supervised classification for remote sensing
Spatially weighted supervised classification for remote sensing
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.
k-NN approach, remote sensing, spatially weighted
277-291
Atkinson, P.M.
aaaa51e4-a713-424f-92b0-0568b198f425
2004
Atkinson, P.M.
aaaa51e4-a713-424f-92b0-0568b198f425
Atkinson, P.M.
(2004)
Spatially weighted supervised classification for remote sensing.
International Journal of Applied Earth Observation and Geoinformation, 5 (4), .
(doi:10.1016/j.jag.2004.07.006).
Abstract
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.
Text
Atkinson_JAG_2004.pdf
- Other
Restricted to Registered users only
More information
Published date: 2004
Keywords:
k-NN approach, remote sensing, spatially weighted
Identifiers
Local EPrints ID: 15770
URI: http://eprints.soton.ac.uk/id/eprint/15770
ISSN: 0303-2434
PURE UUID: 255f0f6e-d20a-479e-863e-00de5baf7716
Catalogue record
Date deposited: 01 Jun 2005
Last modified: 15 Mar 2024 05:43
Export record
Altmetrics
Contributors
Author:
P.M. Atkinson
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics