Please use this identifier to cite or link to this item:
Author(s): A. Jalobeanu
C. Gama
J.A. Gonçalves
Title: Probabilistic surface change detection and measurement from digital aerial stereo images
Issue Date: 2010
Abstract: We propose a new method to measure changes in terrain topography from two optical stereo image pairs acquired at differentdates. The main novelty is in the ability of computing the spatial distribution of uncertainty, thanks to stochastic modeling andprobabilistic inference. Thus, scientists will have access to quantitative error estimates of local surface variation, so they cancheck the statistical significance of elevation changes, and make, where changes have occurred, consistent measurements ofvolume or shape evolution. The main application area is geomorphology, as the method can help study phenomena such ascoastal cliff erosion, sand dune displacement and various transport mechanisms through the computation of volume changes. Itcan also help measure vegetation growth, and virtually any kind of evolution of the surface.We first start by inferring a dense disparity map from two images, assuming a known viewing geometry. The imagesare accurately rectified in order to constrain the deformation on one of the axes, so we only have to infer a one-dimensionalparameter field. The probabilistic approach provides a rigorous framework for parameter estimation and error computation, soall the disparities are described as random variables. We define a generative model for both images given all model variables.It mainly consists of warping the scene using B-Splines, and defining a spatially adaptive stochastic model of the radiometricdifferences between the two views. The inversion, which is an ill-posed inverse problem, requires regularization, achievedthrough a smoothness prior model. Bayesian inference allows us to recover disparities as probability distributions. This is doneon each stereo pair, then disparity maps are transformed into surface models in a common ground frame in order to perform thecomparison. We apply this technique to high resolution digital aerial images of the Portuguese coast to detect cliff erosion andquantify the effects of weathering
Subject: Ciências da terra e ciências do ambiente
Earth and related Environmental sciences
Scientific areas: Ciências exactas e naturais::Ciências da terra e ciências do ambiente
Natural sciences::Earth and related Environmental sciences
Source: IGARSS 2010: Remote Sensing: Global Vision for Local Action
Document Type: Artigo em Livro de Atas de Conferência Internacional
Rights: openAccess
Appears in Collections:FCUP - Artigo em Livro de Atas de Conferência Internacional

Files in This Item:
File Description SizeFormat 
48280.pdf137.09 kBAdobe PDFThumbnail

This item is licensed under a Creative Commons License Creative Commons