Object-oriented classification of Landsat ETM+ satellite image

This paper presents results of object-oriented classification of Landsat ETM+ satellite image conducted using eCognition software. The classified image was acquired on 7 May 2000. In this particular study, an area of 423 km2 within the borders of Legionowo Community near Warsaw is considered. Prior to classification, segmentation of the Landsat ETM+ image is performed using panchromatic channel, fused multispectral and panchromatic data. The applied methods of classification enabled the identification of 18 land cover and land use classes. After the classification, generalization and raster to vector conversion, verification and accuracy assessment are performed by means of visual interpretation. Overall accuracy of the classification reached 94.6%. The verification and classification results are combined to form the final database. This is followed by comparing the object-oriented with traditional pixel-based classification. The latter is performed using the so-called hybrid classification based on both supervised and unsupervised classification approaches. The traditional pixel-based approach identified only 8 classes. Comparison of the pixel-based classification with the database obtained using the object-oriented approach revealed that the former reached 72% and 61% accuracy, according to the applied method.