Using colour, texture, and hierarchial segmentation for high-resolution remote sensing
| Autor: | Roger Trias-Sanz, Georges Stamon, Jean Louchet |
|---|---|
| Rok vydání: | 2008 |
| Předmět: |
Computer science
Segmentation-based object categorization Multispectral image ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Scale-space segmentation Image segmentation Texture (geology) Atomic and Molecular Physics and Optics Computer Science Applications Transformation (function) Market segmentation Segmentation Computers in Earth Sciences Engineering (miscellaneous) Remote sensing |
| Zdroj: | ISPRS Journal of Photogrammetry and Remote Sensing. 63:156-168 |
| ISSN: | 0924-2716 |
| DOI: | 10.1016/j.isprsjprs.2007.08.005 |
| Popis: | Image segmentation can be performed on raw radiometric data, but also on transformed colour spaces, or, for high-resolution images, on textural features. We review several existing colour space transformations and textural features, and investigate which combination of inputs gives best results for the task of segmenting high-resolution multispectral aerial images of rural areas into its constituent cartographic objects such as fields, orchards, forests, or lakes, with a hierarchical segmentation algorithm. A method to quantitatively evaluate the quality of a hierarchical image segmentation is presented, and the behaviour of the segmentation algorithm for various parameter sets is also explored. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect