Monitoring the Recovery after 2016 Hurricane Matthew in Haiti via Markovian Multitemporal Region-Based Modeling

Abstract

The aim of this paper is to address the monitoring of the recovery phase in the aftermath of Hurricane Matthew (28 September–10 October 2016) in the town of Jérémie, southwestern Haiti. This is accomplished via a novel change detection method that has been formulated, in a data fusion perspective, in terms of multitemporal supervised classification. The availability of very high resolution images provided by last-generation satellite synthetic aperture radar (SAR) and optical sensors makes this analysis promising from an application perspective and simultaneously challenging from a processing viewpoint. Indeed, pursuing such a goal requires the development of novel methodologies able to exploit the large amount of detailed information provided by this type of data. To take advantage of the temporal and spatial information associated with such images, the proposed method integrates multisensor, multisource, and contextual information. Markov random field modeling is adopted here to integrate the spatial context and the temporal correlation associated with images acquired at different dates. Moreover, the adoption of a region-based approach allows for the characterization of the geometrical structures in the images through multiple segmentation maps at different scales and times. The performances of the proposed approach are evaluated on multisensor pairs of COSMO-SkyMed SAR and Pléiades optical images acquired over Jérémie, in the aftermath of and during the three years after Hurricane Matthew. The effectiveness of the change detection results is analyzed both quantitatively, through the computation of accuracy measures on a test set, and qualitatively, by visual inspection of the classification maps. The robustness of the proposed method with respect to different algorithmic choices is also assessed, and the detected changes are discussed in relation to the recovery endeavors in the area and ground-truth data collected in the field in April 2019.

Multimodal Fusion of Mobility Demand Data and Remote Sensing Imagery for Urban Land-Use and Land-Cover Mapping

“…Consistently with the previous works in [10,51], the random field model defined by the energy in (10) has been described as an MRF, rather than a conditional random field (CRF). This is due to the aforementioned interpretation of the segmentation labels s iq and the zone index ν i as additional features or observations.…”

“…This, in turn, can pave the way for the planning and design of interventions on the transport supply (in terms of both infrastructure and services) capable of meeting the needs arising from the changes in the urban areas. In this respect, since the OD matrix of a given city is normally updated on a regular basis, a possibly useful extension of the proposed region-based Markovian approach could be a multitemporal generalisation [51]. This extension would fuse such multitemporal OD data with a corresponding satellite image time series (SITS) to determine the temporal evolution of urban land use.…”

“…Overall, given the two aforementioned possible interpretations, the random field associated with the second proposed method can be correctly referred to as either an MRF or a CRF. In the following, we will continue referring to it as an MRF, for the sake of consistency with the previous papers in [10,51].…”

“…MRFs are a powerful family of stochastic models for image data in Bayesian image analysis [43,44]. They have been successfully applied for a long time in remote sensing for image classification and segmentation [24,[45][46][47][48][49][50], object-based and regionbased image analysis [10,51,52], cloud detection [53,54], and change detection [55][56][57]. They represent a multi-dimensional generalisation of Markov chains and, in the case of 2D images, are defined in terms of a Markovianity property on the two-dimensional pixel lattice with respect to a given neighbourhood system [11,43,44].…”

“…In the second developed technique, the algorithm in [62] is used to generate the Q segmentation maps (see Figure 6). It has been selected as a well-known approach for the segmentation of optical image data, which has proven successful in its combination with region-based MRF models in [10,51]. It is a graph-based region-merging algorithm and is parameterised by a parameter k that indirectly determines the scale of the extracted segments [62].…”