Unsupervised and hierarchical cluster analysis and classification of SAR images
| Autor: | Edward C. Poser, Yiu‐fai Wong, Kenneth J. Peters |
|---|---|
| Rok vydání: | 1993 |
| Předmět: |
business.industry
Feature vector Single-linkage clustering k-means clustering Pattern recognition computer.software_genre Hierarchical clustering ComputingMethodologies_PATTERNRECOGNITION Geography Cluster (physics) Canopy clustering algorithm Artificial intelligence Data mining business Cluster analysis computer k-medians clustering |
| Zdroj: | AIP Conference Proceedings. |
| ISSN: | 0094-243X |
| DOI: | 10.1063/1.44394 |
| Popis: | We describe an application of a new clustering algorithm [1] to the cluster analysis and classification of a SAR image of an agricultural site. The clustering algorithm is unsupervised and hierarchical. It can cluster data in any multidimensional space and is insensitive to variability in cluster densities, cluster sizes, and ellipsoidal shapes. There is a natural way to determine the optimal number clusters. Using techniques described in [2–4], we extracted a 12‐dimensional feature vector for each pixel in the image. The clustering algorithm was able to partition a set of unlableed feature vectors from 13 selected sites into 13 clusters without any supervision. The cluster parameters were then used to classify the whole image. The classification map is much less noisy and more accurate than those obtained by hierarchical rules. This algorithm, more powerful than existing ones, may be useful for remote sensing for land use. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|