# American Institute of Mathematical Sciences

• Previous Article
Semi-automatic segmentation of NATURA 2000 habitats in Sentinel-2 satellite images by evolving open curves
• DCDS-S Home
• This Issue
• Next Article
Sharp consistency estimates for a pressure-Poisson problem with Stokes boundary value problems
March  2021, 14(3): 1017-1032. doi: 10.3934/dcdss.2020348

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

 1 Department of Mathematics, Slovak University of Technology, Radlinského 11,810 05 Bratislava, Slovakia, Algoritmy:SK, s.r.o., Šulekova 6,811 06 Bratislava, Slovakia 2 Institute of Botany, Slovak Academy of Sciences, Dúbravská cesta 9,845 23 Bratislava, Slovakia

* Corresponding author

Received  December 2018 Revised  November 2019 Published  May 2020

Fund Project: This work was supported by projects APVV-16-0431, APVV-15-0522, VEGA 1/0608/15 and ESA Contract No. 4000122575/17/NL/SC

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.

Citation: Karol Mikula, Jozef Urbán, Michal Kollár, Martin Ambroz, Ivan Jarolímek, Jozef Šibík, Mária Šibíková. An automated segmentation of NATURA 2000 habitats from Sentinel-2 optical data. Discrete & Continuous Dynamical Systems - S, 2021, 14 (3) : 1017-1032. doi: 10.3934/dcdss.2020348
##### References:

show all references

##### References:
First row: the original image $I^0$ and smoothed image $I^{\sigma_0}$. Second row: the visualization of $g(\mathbf{x})$, smoothed edge detector $g_1(\mathbf{x})$ and a zoom of the vector field $-\nabla g_1(\mathbf{x})$ where we see arrows pointing towards the edges in $I^0$. Third row: the functions $H(\mathbf{x})$ using (5) and $g_2(\mathbf{x} )$ evaluated by using the initial circle plotted in the Fourth row, left. Fourth row: the initial segmentation curve placed in $I^0$ and its time evolution until the final segmentation state (bottom right). In the middle image we see that the evolving curve undergoes topological changes which are resolved efficiently
Closed planar curve discretization (left) corresponding to the uniform discretization of the unit circle (right)
Visualization of the curve discretization: curve grid points (red) and their midpoints. Finite volumes $\mathbf{p}_{i-1}, \mathbf{p}_i,$ and $\mathbf{p}_{i+1}$ are highlighted by green, brown and yellow color. Note that $\mathbf{p}_i$ is not a straight line given by $\mathbf{x}_{i-\frac{1}2}$ and $\mathbf{x}_{i+\frac{1}2}$, but a broken line given by $\mathbf{x}_{i-\frac{1}2}$, $\mathbf{x}_{i}$ and $\mathbf{x}_{i+\frac{1}2}$, see also [1]
First row: the original image $I^0$ and smoothed image $I^{\sigma_0}$. Second row: the visualization of the function $g(\mathbf{x})$ and smoothed edge detector $g_1(\mathbf{x})$. Third row: the function $H(\mathbf{x})$ and $g_2(\mathbf{x})$ evaluated by using the initial circle plotted in the Fourth row, left. Fourth row: the initial segmentation curve placed in $I^0$ (bottom left) and its time evolution (bottom middle) until the final segmentation state (bottom right) is reached
First row: the original image $I^0$ and smoothed image $I^{\sigma_0}$. Second row: the visualization of the function $g(\mathbf{x})$ and smoothed edge detector $g_1(\mathbf{x})$. Third row: the function $H(\mathbf{x})$ and $g_2(\mathbf{x})$ evaluated by using the initial circle plotted in the Fourth row, left. Fourth row: the initial segmentation curve placed in $I^0$ (bottom left) and its time evolution (bottom middle) until the final segmentation state (bottom right) is reached
Left: the evolution of the segmentation curve from the initial circle to the final state. Right: the final automatic segmentation (red) together with the result of the semi-automatic segmentation (yellow) and the GPS track (light-blue)
Left: the evolution of the segmentation curve from the initial circle to the final state. Right: the final automatic segmentation (red) together with the result of the semi-automatic segmentation (yellow) and the GPS track (light-blue)
Left: the evolution of the segmentation curve from the initial circle to the final state. Right: the final automatic segmentation (red) together with the result of the semi-automatic segmentation (yellow) and the GPS track (light-blue)
 [1] Marion Darbas, Jérémy Heleine, Stephanie Lohrengel. Numerical resolution by the quasi-reversibility method of a data completion problem for Maxwell's equations. Inverse Problems & Imaging, 2020, 14 (6) : 1107-1133. doi: 10.3934/ipi.2020056 [2] Lekbir Afraites, Abdelghafour Atlas, Fahd Karami, Driss Meskine. Some class of parabolic systems applied to image processing. Discrete & Continuous Dynamical Systems - B, 2016, 21 (6) : 1671-1687. doi: 10.3934/dcdsb.2016017 [3] Zhihua Zhang, Naoki Saito. PHLST with adaptive tiling and its application to antarctic remote sensing image approximation. Inverse Problems & Imaging, 2014, 8 (1) : 321-337. doi: 10.3934/ipi.2014.8.321 [4] Yila Bai, Haiqing Zhao, Xu Zhang, Enmin Feng, Zhijun Li. The model of heat transfer of the arctic snow-ice layer in summer and numerical simulation. Journal of Industrial & Management Optimization, 2005, 1 (3) : 405-414. doi: 10.3934/jimo.2005.1.405 [5] Armin Lechleiter, Tobias Rienmüller. Factorization method for the inverse Stokes problem. Inverse Problems & Imaging, 2013, 7 (4) : 1271-1293. doi: 10.3934/ipi.2013.7.1271 [6] Jia Cai, Guanglong Xu, Zhensheng Hu. Sketch-based image retrieval via CAT loss with elastic net regularization. Mathematical Foundations of Computing, 2020, 3 (4) : 219-227. doi: 10.3934/mfc.2020013 [7] Carlos Gutierrez, Nguyen Van Chau. A remark on an eigenvalue condition for the global injectivity of differentiable maps of $R^2$. Discrete & Continuous Dynamical Systems - A, 2007, 17 (2) : 397-402. doi: 10.3934/dcds.2007.17.397 [8] Qiang Guo, Dong Liang. An adaptive wavelet method and its analysis for parabolic equations. Numerical Algebra, Control & Optimization, 2013, 3 (2) : 327-345. doi: 10.3934/naco.2013.3.327 [9] Ka Luen Cheung, Man Chun Leung. Asymptotic behavior of positive solutions of the equation $\Delta u + K u^{\frac{n+2}{n-2}} = 0$ in $IR^n$ and positive scalar curvature. Conference Publications, 2001, 2001 (Special) : 109-120. doi: 10.3934/proc.2001.2001.109 [10] Tao Wu, Yu Lei, Jiao Shi, Maoguo Gong. An evolutionary multiobjective method for low-rank and sparse matrix decomposition. Big Data & Information Analytics, 2017, 2 (1) : 23-37. doi: 10.3934/bdia.2017006 [11] Deren Han, Zehui Jia, Yongzhong Song, David Z. W. Wang. An efficient projection method for nonlinear inverse problems with sparsity constraints. Inverse Problems & Imaging, 2016, 10 (3) : 689-709. doi: 10.3934/ipi.2016017 [12] Boris Kramer, John R. Singler. A POD projection method for large-scale algebraic Riccati equations. Numerical Algebra, Control & Optimization, 2016, 6 (4) : 413-435. doi: 10.3934/naco.2016018 [13] Petra Csomós, Hermann Mena. Fourier-splitting method for solving hyperbolic LQR problems. Numerical Algebra, Control & Optimization, 2018, 8 (1) : 17-46. doi: 10.3934/naco.2018002 [14] Christina Surulescu, Nicolae Surulescu. Modeling and simulation of some cell dispersion problems by a nonparametric method. Mathematical Biosciences & Engineering, 2011, 8 (2) : 263-277. doi: 10.3934/mbe.2011.8.263 [15] Min Li. A three term Polak-Ribière-Polyak conjugate gradient method close to the memoryless BFGS quasi-Newton method. Journal of Industrial & Management Optimization, 2020, 16 (1) : 245-260. doi: 10.3934/jimo.2018149 [16] Misha Bialy, Andrey E. Mironov. Rich quasi-linear system for integrable geodesic flows on 2-torus. Discrete & Continuous Dynamical Systems - A, 2011, 29 (1) : 81-90. doi: 10.3934/dcds.2011.29.81 [17] José Raúl Quintero, Juan Carlos Muñoz Grajales. On the existence and computation of periodic travelling waves for a 2D water wave model. Communications on Pure & Applied Analysis, 2018, 17 (2) : 557-578. doi: 10.3934/cpaa.2018030 [18] A. Kochergin. Well-approximable angles and mixing for flows on T^2 with nonsingular fixed points. Electronic Research Announcements, 2004, 10: 113-121. [19] Peter Benner, Jens Saak, M. Monir Uddin. Balancing based model reduction for structured index-2 unstable descriptor systems with application to flow control. Numerical Algebra, Control & Optimization, 2016, 6 (1) : 1-20. doi: 10.3934/naco.2016.6.1 [20] Manfred Einsiedler, Elon Lindenstrauss. On measures invariant under diagonalizable actions: the Rank-One case and the general Low-Entropy method. Journal of Modern Dynamics, 2008, 2 (1) : 83-128. doi: 10.3934/jmd.2008.2.83

2019 Impact Factor: 1.233