pôle SIS / Image processing for Earth observation and cartography

Pôle SIS (Signal, Images et Systèmes)

Pôle SIS (Signal, Images et Systèmes)

Image processing for Earth observation and cartography
The Ariana project aims to provide image processing tools to aid in the solution of problems arising in a wide range of concrete applications in Earth observation and cartography, for example cartographic updating, land management, and agriculture, but also investigates other application domains as biological images or astrophysical images.

Menu SIS > Image processing for Earth
observation and cartography

Image processing for Earth observation and cartography - NEWS

From theoretical point of view, the project uses two broad classes of techniques to attack its problems, probabilistic models combined with stochastic algorithms, and variational models combined with deterministic algorithms. The project also concerns itself with a number of important, related problems, in particular the development of the parameter estimation procedures necessary to render the above methods automatic or semi-automatic, and the study of the optimization algorithms used to solve the problems.

This research area has been conducted in the Ariana project, a common team between INRIA and I3S.

Tree crown detection with Marked Point Processes. This work addresses the problem of tree crown extraction from Colour InfraRed (CIR) aerial images of forests. Our models are based on object processes, i.e. marked point processes [IC-269G. Perrin, X. Descombes, J. Zerubia, and J. Boureau. Forest resource assessment using stochastic geometry. In Proc. International Precision Forestry Symposium, 2006. 12 pages., IC-268G. Perrin, X. Descombes, and J. Zerubia. 2d and 3d vegetation resource parameters assessment using marked point processes. In Proc. International Conference on Pattern Recognition (ICPR), pages 1–4, Hong-Kong, 2006, Re-4G. Perrin, X. Descombes, and J. Zerubia. A non-bayesian model for tree crown extraction using marked point processes. Research Report 5846, INRIA, France, 2006. http://www. inria.fr/rrrt/rr-5846.html.]. These mathematical objects are random variables whose realizations are configurations of geometrical shapes. This approach yields an energy minimization problem, where the energy is composed of a regularization term (prior density), which introduces some constraints on the objects and their interactions, and a data term, which links the objects to the features to be extracted. Once the reference object has been chosen, we sample the process and extract the best configuration of objects with respect to the energy, using a Reversible Jump Markov Chain Monte Carlo (RJMCMC) algorithm embedded in a simulated annealing scheme.

New results have been obtained by proposing new models to deal with different densities of stand. In dense areas, we use an ellipse process, while in sparse vegetation an ellipsoid process is used. As a result, we obtain the number of stems, their position, the diameters of the crowns and the heights of the trees for sparse areas and coppice-with-standards structures. The resulting algorithms have been tested on high resolution CIR aerial images provided by the French National Forest Inventory (IFN) [NC-35]. This work has been supported by INRIA through the ARC (Action de Recherche Collaborative de l’INRIA) Mode de vie, in collaboration with the Digiplante project-team (INRIA Rocquencourt), the MAS laboratory, and LIAMA, Beijing, China (http://www-sop.inria.fr/ariana/Projets/ ModedeVie/MODEdeVIE.html). Software GRENAT [So-5] is deposited with the APP and has been transferred to the French National Forest Inventory (IFN), INRA (Avignon), Joint Research Center (JCR) from European Commission at Ispra, university of Cocody at Abidjan and university of Yaounde and ECP (Ecole Central Paris).

HOAC models for road network extraction in dense urban areas from VHR satellite images. The goal of this work was to develop robust approaches for the semi-automatic extraction of road networks in dense urban areas from very high resolution (VHR) optical satellite images. Starting from a previous higher-order active contour (HOAC) model developed for medium resolution images, we first concentrated on updating the road network using the image and out-of-date GIS data. We introduced a multi-resolution statistical data model and a prior energy linking the road network to the GIS data, with good results [IJ-93T. Peng, I. H. Jermyn, V. Prinet, and J. Zerubia. Incorporating generic and specific prior knowledge in a multi-scale phase field model for road extraction from VHR images.
IEEE Trans. Geoscience and Remote Sensing, 1(2):139–146, 2008.
http://dx.doi.org/10.1109/JSTARS.2008.922318.].

We then turned to the direct extraction of secondary roads. In the previous HOAC prior, the interaction between points on the same side of a road has the same range and magnitude as that between points on opposite sides of a road, a limitation that turned out to be serious for smaller roads. We developed two energies to overcome this limitation. The first [IC-264T. Peng, I. H. Jermyn, V. Prinet, and J. Zerubia. Extraction of main and secondary roads in VHR images using a higher-order phase field model. In Proc. XXI ISPRS Congress, Part A, pages 215–222,
Beijing, China, 2008.] is a nonlinear non-local HOAC term that increases the magnitude of interactions along the road. Although promising results were obtained at reduced resolutions, the computational cost of this term is high. The second [IC-263T. Peng, I. H. Jermyn, V. Prinet, and J. Zerubia. An extended phase field higher-order active contour model for networks and its application to road network extraction from VHR satellite images.
In Proc. European Conference on Computer Vision (ECCV), pages III: 509–520, Marseille, France, 2008.] is a new Euclidean invariant linear non-local HOAC term. This permits separate control of the interactions between points on the same side of a road and between points on opposite sides of a road. Via a stability analysis, we studied the behaviour of the energy as a function of its parameters, thereby establishing constraints on the parameters in terms of network width(s). The linear non-local term is also more efficient computationally than the nonlinear term, and can thus be applied to images at full resolution. This allows some narrower network branches to be extracted, and in general the extraction accuracy is improved at full resolution.

This work has been done during the PhD of Ting Peng (2005 - 2008). Ting Peng was awarded one of the five 2009 European Best IEEE Geoscience and Remote Sensing Society PhD prizes. This PhD was co-supervised by Baogang Hu and Véronique Prinet, both of LIAMA/CASIA, Chinese Academy of Sciences. The data (Quickbird images and GIS of Beijing urban areas) were respectively provided by DigitalGlobe and the Beijing Institute of Survey and Mapping. This work was partially supported by Thales Alenia Space, by the French Ministry of Foreign Affairs, and by CASIA.

Laboratoire d'Informatique, Signaux et Systèmes de Sophia-Antipolis
I3S - UMR7271 - UNS CNRS
2000, route des Lucioles - Les Algorithmes - bât. Euclide B - BP 121 - 06903 Sophia Antipolis Cedex - France
Tél. +33 4 92 94 27 01 - Fax : +33 4 92 94 28 98 - www.i3s.unice.fr