An automated segmentation of NATURA 2000 habitats from Sentinel-2 optical data

Abstract

In this paper, we present a mathematical model and numerical method designed for the segmentation of satellite images, namely to obtain in an automated way borders of Natura 2000 habitats from Sentinel-2 optical data. The segmentation model is based on the evolving closed plane curve approach in the Lagrangian formulation including the efficient treatment of topological changes. The model contains the term expanding the curve in its outer normal direction up to the region of habitat boundary edges, the term attracting the curve accurately to the edges and the smoothing term given by the influence of local curvature. For the numerical solution, we use the flowing finite volume method discretizing the arising advection-diffusion intrinsic partial differential equation including the asymptotically uniform tangential redistribution of curve grid points. We present segmentation results for satellite data from a selected area of Western Slovakia (Záhorie) where the so-called riparian forests represent the important European Natura 2000 habitat. The automatic segmentation results are compared with the semi-automatic segmentation performed by the botany expert and with the GPS tracks obtained in the field. The comparisons show the ability of our numerical model to segment the habitat areas with the accuracy comparable to the pixel resolution of the Sentinel-2 optical data.

Exploring Natura 2000 Habitats by Satellite Image Segmentation: a case study from the Čierny Balog area (Central Slovakia)

“…NaturaSat software integrates various image-processing techniques together with vegetation data management (Mikula et al 2021a). The software allows a user to focus the Sentinel-2 image to the selected habitat occurrence indicating point and then allows a user to perform either semiautomatic (Mikula et al 2021b) or automatic (Mikula et al 2021c) segmentation by evolving the initial curve, either in the form of a straight line or automatically chosen image isoline (semiautomatic segmentation) or in the form of a small circle (or circles) or a small square (automatic segmentation). The segmentation curve is evolved by a general mathematical model including homogeneity and edge detector driving forces and curvature in uence (Ambroz et al 2020, Mikula et al 2021b.…”

Wall Structure Geometry Verification Using TLS Data and BIM Model

“…The mathematical model is a modification and extension of the model described in more detail in [39]. The segmentation curve is an evolving closed planar curve with a position vector of its points denoted by x = (x 1 ,x 2 ).…”

Natural Numerical Networks for Natura 2000 habitats classification by satellite images

“…First, we see the correspondence of these points and bright colors in the relevancy map of the 91F0 habitat, which indicates the correct classification of the pixels along the Latorica River. Furthermore, we automatically segmented the habitat area [30] starting the segmentation from 11 habitat marking points. The evolution of the segmentation curves undergoing topological changes is presented in Fig.…”

“…During the exploration of the relevancy maps created for the southern area of the Central We segmented the area by applying the automatic segmentation method [30], as shown at the bottom right in Fig. 15, to obtain the final segmentation result.…”