Name
Abstract | ||
|---|---|---|
Shoreline extraction algorithms from multispectral imagery depend on threshold selection over spectral values and segmentation in general. Although this gives high performance values for water delineation, error is accumulated on pixels near shoreline and makes detection of nearby ships, docks etc. very hard. Water-shadow spectral mixing is a well-studied problem as only four bands available. This mixing brings up untrustworthy shoreline results. Furthermore, problems due to segmentation of high-resolution remote sensing imagery tend to make shoreline detection results erroneous. In this study, a robust two-staged shoreline extraction algorithm is proposed. At first stage, segmentation over spectral values is applied, and then, some segments are combined according to edge information. As second part of the algorithm, pixel-based water information is integrated. This way, shoreline extraction technique is improved. Additionally, a sensitive and representative performance metric is introduced for shoreline extraction. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1109/SIU.2012.6204797 | Signal Processing and Communications Applications Conference |
Keywords | Field | DocType |
feature extraction,geophysical image processing,image resolution,image segmentation,remote sensing,spectral analysis,high-resolution remote sensing imagery segmentation,multispectral imagery,pixel-based water information,representative performance metric,satellite imagery,shoreline detection,shoreline extraction algorithm,shoreline extraction technique,threshold selection,water delineation,water-shadow spectral mixing | Computer vision,Histogram,Satellite imagery,Pattern recognition,Computer science,Segmentation,Multispectral image,Robustness (computer science),Feature extraction,Image segmentation,Pixel,Artificial intelligence | Conference |
ISBN | Citations | PageRank |
978-1-4673-0054-4 | 1 | 0.49 |
References | Authors | |
2 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Umit Rusen Aktas | 1 | 1 | 0.49 |
| Gulcan Can | 2 | 20 | 4.28 |
| Fatos T. Yarman-Vural | 3 | 15 | 3.51 |