P
Philippe Marthon
Researcher at ENSEEIHT
Publications - 43
Citations - 641
Philippe Marthon is an academic researcher from ENSEEIHT. The author has contributed to research in topics: Synthetic aperture radar & Edge detection. The author has an hindex of 10, co-authored 42 publications receiving 587 citations. Previous affiliations of Philippe Marthon include University of Toulouse.
Papers
More filters
Journal ArticleDOI
An optimal multiedge detector for SAR image segmentation
TL;DR: A new step-edge detector for SAR images is proposed, which is optimal in the minimum mean square error (MSSE) sense under a stochastic multiedge model and thresholding of the edge strength map by a modified version of the watershed algorithm and region merging to eliminate false edges complete an efficient segmentation scheme.
Proceedings ArticleDOI
Comparison of wavelet-based and statistical speckle filters
TL;DR: It is shown that spatially adaptive statistical filters yield better noise reduction and preservation of structures than wavelet- based methods, but that the latter have certain advantages compared to statistical filters which are not spatially adapted.
Proceedings ArticleDOI
SAR image segmentation by morphological methods
TL;DR: Two different approaches -- watershed thresholding and basin dynamics -- are compared and a new algorithm for the computation of edge dynamics is proposed that brings improvement on ERS-1 images of an agricultural zone.
Proceedings ArticleDOI
Fusion of high resolution optical and SAR images with vector data bases for change detection
TL;DR: A processing chain to update building databases using high resolution SAR and optical images and based on a score obtained by the fusion of features in the framework of Dempster Shafer evidence theory.
Journal ArticleDOI
Optimal edge detection and edge localization in complex SAR images with correlated speckle
TL;DR: The authors develop optimal criteria for detection and localization of step edges in single look complex (SLC) synthetic aperture radar (SAR) images that can easily take the speckle autocorrelation into account, and achieve better edge detection and edge localization than with operators known from the literature.