Adaptive Satellite Images Segmentation by Level Set Multiregion Competition
نویسندگان
چکیده
In this paper, we present an adaptive variational segmentation algorithm of spectral-texture regions in satellite images using level set. Satellite images contain both textured and non-textured regions, so for each region cues of spectral and texture are integrated according to their discrimination power. Motivated by Fisher-Rao’s linear discriminant analysis, two region’s weights are defined to code respectively the relevance of spectral and texture cues. Therefore, regions with or without texture are processed in the same framework. The obtained segmentation criterion is minimized via curves evolution within an explicit correspondence between the interiors of evolving curves and regions in segmentation. Thus, an unambiguous segmentation to a given arbitrary number of regions is obtained by the multiregion competition algorithm. Experimental results on both natural and satellite images are shown. Key-words: Level set theory, adaptive multispectral image segmentation, textured / non-textured regions, discrimination power, multiregion competition. ∗ This work is partially supported by QuerySat project and INRIA STIC project. † Projet IMEDIA, bat. 11, INRIA Rocquencourt, Domaine de Voluceau, B.P. 105, 78153 Le Chesnay Cedex France, {Olfa.Besbes, Nozha.Boujemaa}@inria.fr ‡ Unité URISA, École Supérieure des Communications de Tunis (SUP’COM), Cité Technologique des Communications de Tunis, 2088 Tunisie, [email protected] in ria -0 00 70 17 1, v er si on 1 19 M ay 2 00 6 Segmentation adaptative d’images satellitaires par courbes de niveaux et compétition multirégion Résumé : Dans ce rapport, nous proposons un algorithme de segmentation adaptative d’images satellitaires en utilisant une approche variationnelle par courbes de niveaux. Les images satellitaires contiennent des régions texturées et d’autres non texturées. De ce fait, les caractéristiques spectrale et texturale associées à chaque région sont intégrées selon leurs pouvoirs de discrimination. En se basant sur l’analyse de discrimination linéaire de FisherRao, nous définissons pour chaque région deux poids qui codent respectivement la pertience des caractéristiques spectrale et texturale. Ainsi, les régions avec ou sans texture sont analysées dans un même formalisme. Le critère de segmentation obtenu est minimisé par évolution des courbes avec une correspondance explicite entre les régions de la partition et les régions définies par les courbes actives. Une partition du domaine de l’image en un nombre donné quelconque de régions est alors obtenue par l’algorithme de compétition multirégion. Des résultats expérimentaux obtenus sur des images naturelles et satellitaires sont montrés. Mots-clés : Théorie des courbes de niveaux, segmentation adaptative d’images multispectrales, régions texturées / non-texturées, pouvoir de discrimination, compétition multirégion. in ria -0 00 70 17 1, v er si on 1 19 M ay 2 00 6 Adaptive Satellite Images Segmentation by Level Set Multiregion Competition 3
منابع مشابه
Multiregion competition: A level set extension of region competition to multiple region image partitioning
The purpose of this study is to investigate a new representation of a partition of an image domain into a fixed but arbitrary number of regions by explicit correspondence between the regions of segmentation and the regions defined by simple closed planar curves and their intersections, and the use of this representation in the context of region competition to provide a level set multiregion com...
متن کاملObject-Oriented Method for Automatic Extraction of Road from High Resolution Satellite Images
As the information carried in a high spatial resolution image is not represented by single pixels but by meaningful image objects, which include the association of multiple pixels and their mutual relations, the object based method has become one of the most commonly used strategies for the processing of high resolution imagery. This processing comprises two fundamental and critical steps towar...
متن کاملA multi-scale convolutional neural network for automatic cloud and cloud shadow detection from Gaofen-1 images
The reconstruction of the information contaminated by cloud and cloud shadow is an important step in pre-processing of high-resolution satellite images. The cloud and cloud shadow automatic segmentation could be the first step in the process of reconstructing the information contaminated by cloud and cloud shadow. This stage is a remarkable challenge due to the relatively inefficient performanc...
متن کاملRobust Potato Color Image Segmentation using Adaptive Fuzzy Inference System
Potato image segmentation is an important part of image-based potato defect detection. This paper presents a robust potato color image segmentation through a combination of a fuzzy rule based system, an image thresholding based on Genetic Algorithm (GA) optimization and morphological operators. The proposed potato color image segmentation is robust against variation of background, distance and ...
متن کاملA Method for Body Fat Composition Analysis in Abdominal Magnetic Resonance Images Via Self-Organizing Map Neural Network
Introduction: The present study aimed to suggest an unsupervised method for the segmentation of visceral adipose tissue (VAT) and subcutaneous adipose tissue (SAT) in axial magnetic resonance (MR) images of the abdomen. Materials and Methods: A self-organizing map (SOM) neural network was designed to segment the adipose tissue from other tissues in the MR images. The segmentation of SAT and VA...
متن کامل