Nesrine Chehata

Bordeaux INP · ENSEGID

Multispectral and 3D LiDAR remote sensing data sources are valuable tools for characterizing the 3D vegetation structure and thus understanding the relationship between forest structure, biodiversity, and microclimate. This study focuses on mapping riparian forest species in the canopy strata using a fusion of Airborne LiDAR data and multispectral...

Multispectral and 3D LiDAR remote sensing data sources are valuable tools for characterizing the 3D vegetation structure and thus understanding the relationship between forest structure, biodiversity and microclimate. This study focuses on mapping riparian forest species in the canopy strata using a fusion of Airborne LiDAR data and multispectral m...

We propose a new deep learning-based method for estimating the occupancy of vegetation strata from airborne 3D LiDAR point clouds. Our model predicts rasterized occupancy maps for three vegetation strata corresponding to lower, medium, and higher cover. Our weakly-supervised training scheme allows our network to only be supervised with vegetation o...

In this paper, we present an approach to land cover mapping from Sentinel-2 (S-2) satellite image time series using deep learning methods in the context of few shots in agricultural areas which aims to learn a classifier to recognize unseen classes during training with limited labelled examples. In many countries, there is a lack of Land Parcel Inf...

Optical and radar satellite time series are synergetic: optical images contain rich spectral information, while C-band radar captures useful geometrical information and is immune to cloud cover. Motivated by the recent success of temporal attention-based methods across multiple crop mapping tasks, we propose to investigate how these models can be a...

The analysis of the multi-layer structure of wild forests is an important challenge of automated large-scale forestry. While modern aerial LiDARs offer geometric information across all vegetation layers, most datasets and methods focus only on the segmentation and reconstruction of the top of canopy. We release WildForest3D, which consists of 29 st...

We propose a new deep learning-based method for estimating the occupancy of vegetation strata from 3D point clouds captured from an aerial platform. Our model predicts rasterized occupancy maps for three vegetation strata: lower, medium, and higher strata. Our training scheme allows our network to only being supervized with values aggregated over c...

We propose a new deep learning-based method for estimating the occupancy of vegetation strata from 3D point clouds captured from an aerial platform. Our model predicts rasterized occupancy maps for three vegetation strata: lower, medium, and higher strata. Our training scheme allows our network to only being supervized with values aggregated over c...

Optical and radar satellite time series are synergetic: optical images contain rich spectral information, while C-band radar captures useful geometrical information and is immune to cloud cover. Motivated by the recent success of temporal attention-based methods across multiple crop mapping tasks, we propose to investigate how these models can be a...

In this article, margin theory is exploited to design better ensemble classifiers for remote sensing data. A semi-supervised version of the ensemble margin is at the core of this work. Some major challenges in ensemble learning are investigated using this paradigm in the difficult context of land cover classification: selecting the most informative...

Leveraging the recent availability of accurate, frequent, and multimodal (radar and optical) Sentinel-1 and -2 acquisitions, this paper investigates the automation of land parcel identi- fication system (LPIS ) crop type classification. Our approach allows for the automatic integration of temporal knowledge, i.e., crop rotations using existing parc...

Hyperspectral imagery consists of hundreds of contiguous spectral bands. However, most of them are redundant. Thus a subset of well-chosen bands is generally sufficient for a specific problem, enabling to design adapted superspectral sensors dedicated to specific land cover classification. Related both to feature selection and extraction, spectral...

Satellite image time series, bolstered by their growing availability, are at the forefront of an extensive effort towards automated Earth monitoring by international institutions. In particular, large-scale control of agricultural parcels is an issue of major political and economic importance. In this regard, hybrid convolutional-recurrent neural a...

In this article, we investigate several structured deep learning models for crop type classification on multi-spectral time series. In particular, our aim is to assess the respective importance of spatial and temporal structures in such data. With this objective, we consider several designs of convolutional, recurrent, and hybrid neural networks, a...

In this article, we investigate several structured deep learning models for crop type classification on multi-spectral time series. In particular, our aim is to assess the respective importance of spatial and temporal structures in such data. With this objective, we consider several designs of convolutional, recurrent, and hybrid neural networks, a...

• La fusion d'images multispectrales à très haute résolution spatiale (THR) avec des séries temporelles d'images moins résolues spatialement mais comportant plus de bandes spectrales permet d'améliorer la classification de l'occupation du sol. Elle tire en effet le meilleur parti des points forts géométriques et sémantiques de ces deux sources. Ce...

Automatic analysis of Sentinel image time series is recommended for monitoring agricultural land use in Europe. To improve classification capacities, we propose a temporal structured classification combining Sentinel images and former vintages of the Land-Parcel Identification System. Inter-annual crop rotations are learned and combined with the sa...

Towns are characterized by a strong intern dynamic, a very high spatial heterogeneity of their elements, their 3D geometric shapes (horizontal and vertical) inducing shadows, and their large variety of materials. These characteristics make the collection of information of land surface properties and urban descriptors more delicate. Due to the enhan...

This study presents a first experience in Tunisia, on Tbeinya Forest Site in the West Northern of Tunisia. It has been made possible by the national research project (CPR) named INFOTEL3 carried out by the National Centre for Cartography and Remote Sensing. This work focuses on the contribution of a single data Sentinel2 multispectral image in clas...

Dans le cadre du projet de recherche Inventaire forestier par Télédétection et compte tenu des expériences acquises au cours des travaux précédents lors des inventaires de 1988 et de 2007 utilisant respectivement les images satellitales de moyennes résolution et les photos aériennes, il est proposé de développer une nouvelle méthodologie intégrant...

This paper focuses on agricultural land cover mapping at a high-resolution scale and over large areas from an operational point of view and from a high-resolution monodate image. In this context, training data are assumed to be collected by successive journeys of field surveys and, thus, are very limited. Supervised learning techniques are generall...

Very high spatial resolution multispectral images and lower spatial resolution hyperspectral images are complementary sources for urban object classification. The first enables a fine delineation of objects, while the second can better discriminate classes and consider richer land cover semantics. This paper presents a decision fusion scheme taking...

Cette habilitation présente mon parcours professionnel, une synthèse de mes travaux de recherche depuis une dizaine d’années et ouvre ensuite des perspectives sur les développements futurs envisagés. Ses travaux de recherche sont axés sur des développements méthodologiques guidés par des enjeux sociétaux et des problématiques appliquées en Environ...

In urban areas, material maps, i.e. knowledge concerning the roofing materials or the different kinds of ground areas, are necessary for several city modeling or monitoring applications. Airborne remote sensing techniques appear to be convenient for providing them at a large scale but require an enhanced imagery spectral resolution. A superspectral...

Cities today face a variety of issues: attractiveness and economic development, living conditions and urban redevelopment, the quality of life of citizens and the environmental conditions of the urban system as a whole.

This chapter introduces the main data analysis methods associated with topographic and bathymetric airborne LiDAR systems. Data delivered by these sensors can be of two types: the majority of commercial systems deliver three-dimensional (3D) point clouds (systems referred to as multiecho), whereas a limited number directly provides the whole laser...

In urban areas, information concerning very high resolution land cover and especially material maps are necessary for several city modelling or monitoring applications. That is to say, knowledge concerning the roofing materials or the different kinds of ground areas is required. Airborne remote sensing techniques appear to be convenient for providi...

In urban areas, information concerning very high resolution land cover and especially material maps are necessary for several city modelling or monitoring applications. That is to say, knowledge concerning the roofing materials or the different kinds of ground areas is required. Airborne remote sensing techniques appear to be convenient for providi...

In forested mountainous areas, the road location and characterization are invaluable inputs for various purposes such as forest management, wood harvesting industry, wildfire protection and fighting. Airborne topographic lidar has become an established technique to characterize the Earth surface. Lidar provides 3D point clouds allowing for fine rec...

In forested mountaneous areas, the road location and its geometric description are necessary information for many purposes linked to ecological issues. Topographic airborne laser scanning has become an established technique to characterize the Earth surface. Lidar provides 3D point clouds allowing for a fine reconstruction of the topography : very...

Within Mediterranean rural areas, soil and water resources are facing increasing pressures in relation to changes in anthropogenic and climate forcing. Current strategies for resource management have to be redesigned in order to mitigate existing competitions and to propose adaptation solutions. New strategies to be explored include the combination...

Spectral optimization consists in identifying the most relevant band subset for a specific application. It is a way to reduce hyperspectral data huge dimensionality and can be applied to design specific superspectral sensors dedicated to specific land cover applications. Spectral optimization includes both band selection and band extraction. On the...

Hyperspectral imagery generates huge data volumes, consisting of hundreds of contiguous and often highly redundant spectral bands. Difficulties are caused by this high dimensionality. Feature selection (FS) is a possible strategy to reduce the number of bands, consisting in selecting the most relevant bands for a classification problem. It is adapt...

Active learning (AL) has shown a great potential in the field of remote sensing to improve the efficiency of the classification process while keeping a limited training dataset. Active learning uses heuristics to select the most informative pixels in each iteration. In literature, there are several metrics and selection criteria. In this paper, we...

Active learning (AL) has shown a great potential in the field of remote sensing to improve the efficiency of the classification process while keeping a limited training dataset. Active learning uses heuristics to select the most informative pixels in each iteration. In literature, there are several metrics and selection criteria. In this paper, we...

Hyperspectral imagery generates huge data volumes, consisting of hundreds of contiguous and often highly redundant spectral bands. Difficulties are caused by this high dimen-sionality. Feature selection (FS) is a possible strategy to reduce the number of bands, consisting in selecting the most relevant bands for a classification problem. It is adap...

This study evaluates the potential of High Resolution Spotlight TerraSAR-X image for forest type discrimination. Emphasis is put on textural analysis accessible with high resolution radar data. Textural attributes are extracted from GLCM matrices, wavelet, and Fourier Transform (i.e. FOTO method). Their contribution for classification is assessed b...

The automatic mapping of terrace slopes in terraced landscape from remote sensing is still an open question. Among remote sensing data, high resolution digital elevation models appear obviously as the required data to perform such automatic mapping. Pleiades satellite constellation, with its agility, provide new highly resoluted digital elevation m...

The difficulties of having expertise in expert systems, the increasing of the data volume, self adaptation and prediction, all those problems are solved in the presence of learning. The classical definition of learning in cognitive science is the ability to improve the performance as the exercise of an activity. With learning, knowledge is automati...

Les pratiques et les arrangements spatiaux des parcelles agricoles ont un fort impact sur les flux d'eau dans les paysages cultivés . Afin de surveiller les paysages à grande échelle, il ya un fort besoin de délimitation automatique ou semi-automatique des parcelles agricoles. Cet article montre la contribution des images satellitaires à très haute...

Intermediate results of two state-of-the-art wrapper feature selection approaches (GA and SFFS) applied to hyperspectral data sets were used to derive information about band importance for specific land cover classification problems. Several feature selection performance scores (classification accuracies, Bhattacharyya separability) were tested. Th...

Les pratiques et les arrangements spatiaux des parcelles agricoles ont un fort impact sur les flux d'eau dans les pay-sages cultivés. Afin de surveiller les paysages à grande échelle, il y a un fort besoin de délimitation automatique ou semi-automatique des parcelles agricoles. Cet article montre la contribution des images satellitaires à très haut...

Agricultural practices and spatial arrangements of fields have a strong impact on water flows in cultivated landscapes. In order to monitor landscapes at a large scale, there is a strong need for automatic or semi-automatic field delineation. This paper shows the contribution of very high resolution satellite imagery, such as Pléiades imagery, for...

The difficulties of having expertise in expert systems, the increasing of the data volume, self adaptation and prediction, all those problems are solved in the presence of learning. The classical definition of learning in cognitive science is the ability to improve the performance as the exercise of an activity. With learning, knowledge is automati...

The main goal of this study is to design a method to describe the structure of forest stands from Very High Resolution satellite imagery, relying on some typical variables such as crown diameter, tree height, trunk diameter, tree density and tree spacing. The emphasis is placed on the automatization of the process of identification of the most rele...

The potential of very high spatial resolution Pléiades image texture for forest structure quantification and mapping was assessed on maritime pine stands in south-western France. A preliminary step showed that multi-linear regressions allowed a reliable prediction of forest variables (such as crown diameter or tree height) from a set of features au...

Cette étude montre le potentiel de l'information texturale des images à très haute résolution spatiale Pléiades pour la quantification et la cartographie de la structure forestière des peuplements de pin maritime du sud-ouest de la France (massif forestier landais). Une première étape montre qu'il est possible d'estimer, par régressions linéaires m...

In this paper, we present an approach that is able to deal with large-scale road network extraction in montaneous forested areas. While former methods focus on delineating patches of roads without computing a coherent road network, we formu-late a very large number of road hypothesis that are pruned using a graph reasoning and weak a priori knowled...

The potential of very high resolution Pléiades image texture for forest structure mapping was assessed on maritime pine stands in south-western France. A preliminary step showed that multi-linear regressions allow a reliable prediction of forest variables (such as crown diameter or tree height) from a set of features automatically selected among a...

Building detection from geospatial optical images has been a popular topic of research for the last twenty years and in particular with the emergence of very high resolution satel-lites. Existing methods exhibit various flaws and prevent them from being efficient at large scales of space and time: they are context-dependent, require a tedious param...

Agricultural practices and spatial arrangements of fields have a strong impact on water flows in cultivated landscapes. In order to monitor landscapes at a large scale, there is a strong need for automatic or semi-automatic field delineation. Field measurements for delineating parcel network are not efficient, thus very high resolution satellite im...

The potential of very high resolution Pléiades image texture for forest structure mapping was assessed on maritime pine stands in south-western France. A preliminary step showed that multi-linear regressions allow a reliable prediction of forest variables (such as crown diameter or tree height) from a set of features automatically selected among a...

Natural disasters are generally brutal and may affect large areas, which then need to be rapidly mapped to assess the impacts of such events on ecosystems and to prevent related risks. Ground investigations may be complex, whereas remote-sensing techniques enable a fast regional-scale assessment of damage and offer a cost-effective option for large...

Natural disasters are generally brutal and may affect large areas, which then need to be rapidly mapped to assess the impacts of such events on ecosystems and to prevent related risks. Ground investigations may be complex, whereas remote-sensing techniques enable a fast regional-scale assessment of damage and offer a cost-effective option for large...

Accurate Digital Terrain Models (DTMs) are inevitable inputs for mapping and analyzing areas subject to natural hazards. Topographic airborne laser scanning has become an established technique to characterize the Earth's surface: lidar provides 3D point clouds allowing for a fine reconstruction of the topography while preserving high frequencies of...

This paper presents a new feature selection method which aims to effectively and efficiently map remote sensing data. An automated texture-based modelling procedure of forest structure variables is at the core of our approach. We show that texture features that are highly correlated to genuine physical parameters of forest structure have potential...

This work exploits the margin theory to design better ensemble classifiers for remote sensing data. The margin paradigm is at the core of a new bagging algorithm. This method increases the classification accuracy, particularly in case of difficult classes, and significantly reduces the training set size. The same margin framework is used to derive...

Agricultural practices are major drivers of water flows in cultivated landscapes. Especially, the spatial arrangements and connectivities of tilled/untilled fields have a strong impact onto run off and soil erosion at the landscape and watershed scales. Very high spatial resolution satellite images offer the possibility to classify tilled vs. until...

High resolution GIS data describing forests is an important knowledge, both for mapping and for environmental monitoring purposes. The extraction of such information out of imagery consists in a detection of woody areas followed by a thematic enrichment in forested areas, including a discrimination between evergreen, deciduous and mixt plantings. T...

Agricultural practices are major drivers of water flows in cultivated landscapes. Especially, the spatial arrangements and connectivities of tilled/untilled fields have a strong impact onto run off and soil erosion at the landscape and watershed scales. Very high spatial resolution satellite images offer the possibility to classify tilled vs. until...