Land cover mapping using combined Landsat TM imagery and textural features from ERS-1 synthetic aperture radar imagery
Texture features computed from unfiltered ERS-1 SAR imagery have been used as additional features alongside Landsat-TM radiances to map Mediterranean land cover. The texture features were normalised to reduce the impact of speckle noise. The classification procedure was carried out with a multilayer perceptron neural network. The results show that the addition of contrast, angular second moment, entropy, and inverse difference moment features from SAR to the TM channels can give overall accuracy improvement in land cover classification of 2-3 %. Whilst overall this is not very significant, for particular classes the use of texture leads to great improvements in accuracy which could be useful in mapping applications. The results of the use of the SAR texture measures are compared using a number of different accuracy measures derived from individual confusion matrices.
Bibliographic Reference: Paper presented: The European Symposium on Satellite Remote Sensing, Roma (IT), September 26-30, 1994
Availability: Available from (1) as Paper EN 38602 ORA
Record Number: 199411301 / Last updated on: 1994-12-06
Original language: en
Available languages: en