We propose a two-step algorithm for almost unsupervised detection of linear structures, in particular, main axes in road networks, as seen in synthetic aperture radar (SAR) images. The first step is local and is used to extract linear features from the speckle radar image, which are treated as roadsegment candidates. We present two local line detectors as well as a method for fusing information from these detectors. In the second global step, we identify the real roads among the segment candidates by defining a Markov random field (MRF) on a set of segments, which introduces contextual knowledge about the shape of road objects. The influence of the parameters on the road detection is studied and results are presented for various real radar images. Index Terms-Markov random fields (MRF's), road detection, SAR images, statistical properties. NOMENCLATURE Number of looks of the radar image. Amplitude of pixel. Number of pixels in region. Empirical mean of region. Empirical variation coefficient of region. Exact mean-reflected intensity of region. , Exact and empirical contrasts between regions and. Ratio edge detector response between regions and. Ratio line detector (D1) response. Cross-correlation edge detector response between regions and. Cross-correlation line detector (D2) response. Decision threshold for variable. Probability-density function (pdf) of a random variable for value and parameter values. Cumulative distribution function of a random variable for value and parameter values .
Abstract| Because of the importance of the security issues in the management of medical information, we suggest to use watermarking techniques to complete the existing measures for protecting medical images. We discuss the necessary requirements for such a system to be a c cepted b y m e dical sta and its complementary role with respect with existing security systems. We present di erent scenarios, one devoted to the authentication and tracing of the images, the second to the integrity control of the patient's record.
In multi-pass space-borne SAR interferometry, the two acquisitions often present low correlation levels and very noisy phase measurements which are incompatible with automatic phase unwrapping. Instead of dealing with many residues due to erroneous wrapped phase di erences, we propose to use the local frequency as measured by a spectral analysis algorithm presented in a previous paper 1]. For this purpose we present two conventional unwrapping algorithms, one local, the other global, that we revisit to bene t from the robust local frequency estimates. For a local approach based on path following techniques, we use the frequency estimates in a slope compensated lter which extend the complex averaging up to a su cient number of look to eliminate residues due to the noise. Then we connect residues due to non-interferometric features along mask components resulting from the detection of lay-overs and uncorrelated areas. For a global approach such as weighted least squares methods, we demonstrate that the use of noisy discrete phase gradient leads to a biased solution. To avoid this drawback, we propose to use the local frequency estimate and associated measure of con dence as phase gradient and weight. Results are presented on both topographic and di erential interferograms obtained from ERS-1 European radar satellite over various landscapes and over the displacement eld of the Landers 1992 earthquake.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.