Characterization of Signals from Multiscale Edges
IEEE Transactions on Pattern Analysis and Machine Intelligence
Unsupervised texture segmentation using Gabor filters
Pattern Recognition
Nonlinear image labeling for multivalued segmentation
IEEE Transactions on Image Processing
Coastline Detection from SAR Images by Level Set Model
ICIAP '09 Proceedings of the 15th International Conference on Image Analysis and Processing
Calculation and analysis of typical coastal low-tide marks based on Lidar data
WiCOM'09 Proceedings of the 5th International Conference on Wireless communications, networking and mobile computing
Regions segmentation from SAR images
ICIAP'11 Proceedings of the 16th international conference on Image analysis and processing: Part I
Hi-index | 0.00 |
The coast area is a vital and highly dynamic environment whose multiple geophysical parameters are worth monitoring. At present the current coastline extraction operations made through high-resolution aerial images consist of the visual photo-interpretation. This performance, which mainly finds cartographic applications, is rather slow in comparison to the possibilities of remote sensing and image processing techniques. The aim of this paper is to describe the development and testing of an innovative algorithm able to extract semiautomatically the coastline by means of remote sensed images. The approach proposed is based on fuzzy connectivity concepts and takes into account the coherence measure extracted from an InSAR (Interferometric Synthetic Aperture Radar) couple. The method combines uniformity features and the averaged image that represents a simple way of facing textural characteristics. The results are then quantitatively evaluated through the comparison with optical aerial images. An automatic procedure is proposed for the evaluation of results, which makes use of distance measurements between the satellite and the aerial result, even though there is a considerable difference in space resolution.