A training algorithm for optimal margin classifiers
COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
The nature of statistical learning theory
The nature of statistical learning theory
Classification of high resolution satellite images using texture from the panchromatic band
ISVC'07 Proceedings of the 3rd international conference on Advances in visual computing - Volume Part II
Identifying orthoimages in Web Map Services
Computers & Geosciences
| Hi-index | 0.01 |
This paper studies the influence of airborne LIDAR elevation data on the classification of multispectral SPOT5 imagery over a semi-urban area; to do this, multispectral and LIDAR elevation data are integrated in a single imagery file composed of independent multiple bands. The Support Vector Machine is used to classify the imagery. A scheme of five classes was chosen; ground truth samples were then collected in two sets, one for training the classifier and the other for checking its quality after classification. The results show that the integration of LIDAR elevation data improves the classification of multispectral bands; the assessment and comparison of the classification results have been carried out using complete confusion matrices. Improvements are evident in classes with similar spectral characteristics but for which altitude is a relevant discrimination factor. An overall improvement of 28.3% was obtained, when LIDAR was included.