Multichannel InSAR Building Edge Detection

Abstract

In this paper, the problem of building edge detection in synthetic aperture radar images is addressed. A new stochastic approach based on local Gaussian Markov random field (LGMRF) is proposed. The algorithm finds the edges of buildings starting from the estimation of the hyperparameters of the LGMRF model. The hyperparameters are seen as an indicator of the spatial correlation between adjacent pixels. The procedure is applied on interferometric data, using singlechannel and multichannel configurations. The algorithm has been tested on simulated and real data, providing good results in both case

Integration and Delivery of Interferometric Synthetic Aperture Radar [InSAR] Data Into Stormwater Planning Within Karst Terranes

“…The authors implemented this approach on a and showed rapid temporal decorrelation; however, such areas tend to have limited human population and infrastructure, and are therefore of lesser value in terms of surface analysis. Buffering on roads within GIS can eliminate apparent scatterers falling outside of areas of concern, and automated edge detection methods can remove scatterers coinciding with buildings from the dataset (Ferraioli, 2010). be optimized for soil type, topography, the consideration of local landowners, and, in karst terranes, the need to avoid groundwater contamination and active karst features.…”

Building detection in SAR imagery

“…Other techniques [2], [3], [6] did not utilize bright lines and shadows, but instead used Markov random fields (MRF) to generate labels which model the a priori information of the scene. The labels represent the actual values of the data being utilized and can be generated for multiple types of data: the amplitude and InSAR phase [3], the real and imaginary parts of multiple co-registered SAR images [2], and the height, calculated from the InSAR phase [6].…”

“…The labels represent the actual values of the data being utilized and can be generated for multiple types of data: the amplitude and InSAR phase [3], the real and imaginary parts of multiple co-registered SAR images [2], and the height, calculated from the InSAR phase [6]. This technique generates a parameter for the MRF distribution which describes the label and depends only on the surrounding values.…”

BUILDING ROOF BOUNDARY EXTRACTION FROM LiDAR AND IMAGE DATA BASED ON MARKOV RANDOM FIELD

“…A theory that has been gaining ground in feature extraction, such as in the extraction of buildings, is the probabilistic theory of Markov Random Field (MRF) (Krishnamachari and Chellappa, 1996;Katartzis and Sahli, 2008;Ferraioli, 2010;Galvanin and Dal Poz, 2012;Fernandes and Dal Poz, 2016). The great advantage of using the MRF model is that this formalism easily allows the characterization of contextual information.…”