Centre dedocumentation
scientifique

Mapping forest in the Swiss Alps treeline ecotone with explainable deep learning / Thiên-Anh Nguyen in Remote sensing of environment, vol 281 (November 2022)  

Public [article]  inRemote sensing of environment > vol 281 (November 2022) . - n° 113217 Titre : Mapping forest in the Swiss Alps treeline ecotone with explainable deep learning Type de document : Article/Communication Auteurs : Thiên-Anh Nguyen, Auteur ; Benjamin Kellenberger, Auteur ; Devis Tuia, Auteur Année de publication : 2022 Article en page(s) : n° 113217 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] Alpes [Termes IGN] apprentissage profond [Termes IGN] canopée [Termes IGN] carte forestière [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] écotone [Termes IGN] hauteur des arbres [Termes IGN] image à très haute résolution [Termes IGN] image aérienne [Termes IGN] image RVB [Termes IGN] inventaire forestier étranger (données) [Termes IGN] modèle numérique de surface de la canopée [Termes IGN] Suisse Résumé : (auteur) Forest maps are essential to understand forest dynamics. Due to the increasing availability of remote sensing data and machine learning models like convolutional neural networks, forest maps can these days be created on large scales with high accuracy. Common methods usually predict a map from remote sensing images without deliberately considering intermediate semantic concepts that are relevant to the final map. This makes the mapping process difficult to interpret, especially when using opaque deep learning models. Moreover, such procedure is entirely agnostic to the definitions of the mapping targets (e.g., forest types depending on variables such as tree height and tree density). Common models can at best learn these rules implicitly from data, which greatly hinders trust in the produced maps. In this work, we aim at building an explainable deep learning model for forest mapping that leverages prior knowledge about forest definitions to provide explanations to its decisions. We propose a model that explicitly quantifies intermediate variables like tree height and tree canopy density involved in the forest definitions, corresponding to those used to create the forest maps for training the model in the first place, and combines them accordingly. We apply our model to mapping forest types using very high resolution aerial imagery and lay particular focus on the treeline ecotone at high altitudes, where forest boundaries are complex and highly dependent on the chosen forest definition. Results show that our rule-informed model is able to quantify intermediate key variables and predict forest maps that reflect forest definitions. Through its interpretable design, it is further able to reveal implicit patterns in the manually-annotated forest labels, which facilitates the analysis of the produced maps and their comparison with other datasets. Numéro de notice : A2022-794 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.rse.2022.113217 Date de publication en ligne : 01/09/2022 En ligne : https://doi.org/10.1016/j.rse.2022.113217 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101928 [article]

Mapping individual abandoned houses across cities by integrating VHR remote sensing and street view imagery / Shengyuan Zou in International journal of applied Earth observation and geoinformation, vol 113 (September 2022)  

Public [article]  inInternational journal of applied Earth observation and geoinformation > vol 113 (September 2022) . - n° 103018 Titre : Mapping individual abandoned houses across cities by integrating VHR remote sensing and street view imagery Type de document : Article/Communication Auteurs : Shengyuan Zou, Auteur ; Le Wang, Auteur Année de publication : 2022 Article en page(s) : n° 103018 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] carte thématique [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] détection d'objet [Termes IGN] image à très haute résolution [Termes IGN] image Streetview [Termes IGN] logement [Termes IGN] New York (Etats-Unis ; état) [Termes IGN] théorie de Dempster-Shafer [Termes IGN] zone urbaine Résumé : (auteur) Abandoned houses (AH) present an utmost challenge confronting the urban environment in contemporary U.S. shrinking cities. Data accessibility is a major hurdle that prevents the acquisition of large-scale AH information at the individual property level. To this end, the latest revolution of open-access remote sensing platforms has witnessed a plethora of multi-source, multi-perspective fine-spatial-resolution data for urban environments, among which very-high-resolution (VHR) top-down view remote sensing images and horizontal-perspective Google Street View (GSV) images are prominent exemplifiers. In this study, we aim to map individual-level abandoned houses across cities by developing a method that can effectively leverage VHR remote sensing and GSV images. The proposed method is composed of four steps. First, we explored the feasibility of the three most relevant and complementary remote sensing data for individual-level AH detection, i.e., daytime VHR images, nighttime light VHR images, and GSV images. Second, we extracted discriminative features that are indicative of housing abandonment conditions from the three disparate data sources. Third, we applied decision-level fusion with Dempster-Shafer Theory (DST) to better leverage the prior knowledge about data effectiveness. In the last step, a geographical random forests (GRF) model was first implemented to improve the predictions of where houses were occluded on GSV images. We mapped individual AH in two typical U.S. shrinking cities, Buffalo, NY, and Cleveland, OH, which allowed us to further explore the individual-property-level spatial characteristics of AH. Results revealed that the proposed DST fusion and GRF prediction consistently achieved promising performance across the two cities. Given the merits of incorporating open-access and multi-perspective data, our proposed method has the potential to be generalized to understanding regional and national-scale urban environments tackling housing abandonment challenges. Numéro de notice : A2022-788 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.jag.2022.103018 Date de publication en ligne : 18/09/2022 En ligne : https://doi.org/10.1016/j.jag.2022.103018 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101894 [article]

Feature-selection high-resolution network with hypersphere embedding for semantic segmentation of VHR remote sensing images / Hanwen Xu in IEEE Transactions on geoscience and remote sensing, vol 60 n° 6 (June 2022)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 60 n° 6 (June 2022) . - n° 4411915 Titre : Feature-selection high-resolution network with hypersphere embedding for semantic segmentation of VHR remote sensing images Type de document : Article/Communication Auteurs : Hanwen Xu, Auteur ; Xinming Tang, Auteur ; Bo Ai, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 4411915 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] architecture de réseau [Termes IGN] attention (apprentissage automatique) [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] entropie [Termes IGN] extraction de traits caractéristiques [Termes IGN] image à très haute résolution [Termes IGN] segmentation multi-échelle [Termes IGN] segmentation sémantique Résumé : (auteur) Very-high-resolution (VHR) remote sensing images contain various multiscale objects, such as large-scale buildings and small-scale cars. However, these multiscale objects cannot be considered simultaneously in the widely used backbones with a large downsampling factor (e.g., VGG-like and ResNet-like), resulting in the appearance of various context aggregation approaches, such as fusing low-level features and attention-based modules. To alleviate this problem caused by backbones with a large downsampling factor, we propose a feature-selection high-resolution network (FSHRNet) based on an observation: if the features maintain high resolution throughout the network, a high precision segmentation result can be obtained by only using a 1× 1 convolution layer with no need for complex context aggregation modules. Specifically, the backbone of FSHRNet is a multibranch structure similar to HRNet where the high-resolution branch is the principal line. Then, a lightweight dynamic weight module, named the feature-selection convolution (FSConv) layer, is presented to fuse multiresolution features, allowing adaptively feature selection based on the characteristic of objects. Finally, a specially designed 1× 1 convolution layer derived from hypersphere embedding is used to produce the segmentation result. Experiments with other widely used methods show that the proposed FSHRNet obtains competitive performance on the ISPRS Vaihingen dataset, the ISPRS Potsdam dataset, and the iSAID dataset. Numéro de notice : A2022-559 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2022.3183144 En ligne : https://doi.org/10.1109/TGRS.2022.3183144 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101184 [article]

Effect of label noise in semantic segmentation of high resolution aerial images and height data / Arabinda Maiti in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol V-2-2022 (2022 edition)  

Public [article]  inISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences > vol V-2-2022 (2022 edition) . - pp 275 - 282 Titre : Effect of label noise in semantic segmentation of high resolution aerial images and height data Type de document : Article/Communication Auteurs : Arabinda Maiti, Auteur ; Sander J. Oude Elberink, Auteur ; M. George Vosselman, Auteur Année de publication : 2022 Article en page(s) : pp 275 - 282 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] bruit (théorie du signal) [Termes IGN] données altimétriques [Termes IGN] données d'entrainement (apprentissage automatique) [Termes IGN] image à très haute résolution [Termes IGN] image aérienne [Termes IGN] orthoimage [Termes IGN] segmentation sémantique Résumé : (auteur) The performance of deep learning models in semantic segmentation is dependent on the availability of a large amount of labeled data. However, the influence of label noise, in the form of incorrect annotations, on the performance is significant and mostly ignored. This is a big concern in remote sensing applications, wherein acquired datasets are spatially limited, labeling is done by domain experts with possible sources of high inter-and intra-observer variability leading to erroneous predictions. In this paper, we first simulate the label noise while conducting experiments on two different datasets with very high-resolution aerial images, height data, and inaccurate labels, responsible for the training of deep learning models. We then focus on the effect of these noises on the model performance. Different classes respond differently to the label noise. The typical size of an object belonging to a class is a crucial factor regarding the class-specific performance of the model trained with erroneous labels. Errors caused by relative shifts of labels are the most influential label errors. The model is generally more tolerant of the random label noise than other label errors. It has been observed that the accuracy gets reduced by at least 3% while 5% of label pixels are erroneous. In this regard, our study provides a new perspective of evaluating and quantifying the propagation of label noise in the model performance that is indeed important for adopting reliable semantic segmentation practices. Numéro de notice : A2022-434 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.5194/isprs-annals-V-2-2022-275-2022 Date de publication en ligne : 17/05/2022 En ligne : https://doi.org/10.5194/isprs-annals-V-2-2022-275-2022 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100741 [article]

Unveiling the complex canopy spatial structure of a Mediterranean old-growth beech (Fagus sylvatica L.) forest from UAV observations / Francesco Solano in Ecological indicators, vol 138 (May 2022)  

Public [article]  inEcological indicators > vol 138 (May 2022) . - n° 108807 Titre : Unveiling the complex canopy spatial structure of a Mediterranean old-growth beech (Fagus sylvatica L.) forest from UAV observations Type de document : Article/Communication Auteurs : Francesco Solano, Auteur ; Giuseppe Modica, Auteur ; Salvatore Praticò, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 108807 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques [Termes IGN] Calabre [Termes IGN] écosystème forestier [Termes IGN] Fagus sylvatica [Termes IGN] forêt ancienne [Termes IGN] forêt méditerranéenne [Termes IGN] forêt primaire [Termes IGN] image à très haute résolution [Termes IGN] image captée par drone [Termes IGN] modèle numérique de surface de la canopée [Termes IGN] orthophotoplan numérique [Termes IGN] photogrammétrie aérienne [Termes IGN] structure spatiale [Termes IGN] structure-from-motion [Termes IGN] surveillance forestière Résumé : (auteur) In front of climate change scenarios and global loss of biodiversity, it is essential to monitor the structure of old-growth forests to study ecosystem status and dynamics to inform future conservation and restoration programmes. We propose an Unmanned Aerial Vehicle (UAV)-based framework to monitor fine-grained forest top canopy structure in a primary old-growth beech (Fagus sylvatica L.) forest in Pollino National Park, Italy, which belongs to the UNESCO World Heritage (UNESCO WH) serial site “Ancient and Primeval beech forests of the Carpathians and other regions of Europe”. Canopy profile, gap properties and their spatial distribution patterns were analysed using the canopy height model (CHM) derived from UAV surveys. Very high-resolution orthomosaic images coupled with direct field measurement data were used to assess gap detection accuracy and CHM validation. Forest canopy properties along with the vertical layering of the canopy were further explored using second-order statistics. The reconstructed canopy profile revealed a bimodal top height frequency distribution. The upper canopy layer (h > 14 m) was the most represented canopy height, with the remaining 50% split between the medium and lowest layer; 551 gaps were identified within 11.5 ha. Gap size varied between 2 m2 and 353 m2, and 19 m2was the mean gap size; the gap size-frequency relationship reflected a power-law probability distribution. About 97 % of the gaps were Numéro de notice : A2022-369 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.1016/j.ecolind.2022.108807 Date de publication en ligne : 01/04/2022 En ligne : https://doi.org/10.1016/j.ecolind.2022.108807 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100598 [article]

Synergistic use of particle swarm optimization, artificial neural network, and extreme gradient boosting algorithms for urban LULC mapping from WorldView-3 images / Alireza Hamedianfar in Geocarto international, vol 37 n° 3 ([01/02/2022])  

Permalink

DiResNet: Direction-aware residual network for road extraction in VHR remote sensing images / Lei Ding in IEEE Transactions on geoscience and remote sensing, vol 59 n° 12 (December 2021)  

Permalink

Automatic tuning of segmentation parameters for tree crown delineation with VHR imagery / Camile Sothe in Geocarto international, vol 36 n° 19 ([01/11/2021])  

Permalink

A repeatable change detection approach to map extreme storm-related damages caused by intense surface runoff based on optical and SAR remote sensing: Evidence from three case studies in the South of France / Arnaud Cerbelaud in ISPRS Journal of photogrammetry and remote sensing, Vol 182 (December 2021)  

Permalink

A novel method based on deep learning, GIS and geomatics software for building a 3D city model from VHR satellite stereo imagery / Massimiliano Pepe in ISPRS International journal of geo-information, vol 10 n° 10 (October 2021)  

Permalink

Classification of tree species in a heterogeneous urban environment using object-based ensemble analysis and World View-2 satellite imagery / Simbarashe Jombo in Applied geomatics, vol 13 n° 3 (September 2021)  

Permalink

A deep translation (GAN) based change detection network for optical and SAR remote sensing images / Xinghua Li in ISPRS Journal of photogrammetry and remote sensing, vol 179 (September 2021)  

Permalink

Vehicle detection in very-high-resolution remote sensing images based on an anchor-free detection model with a more precise foveal area / Xungen Li in ISPRS International journal of geo-information, vol 10 n° 8 (August 2021)  

Permalink

Comparison of classification methods for urban green space extraction using very high resolution worldview-3 imagery / S. Vigneshwaran in Geocarto international, vol 36 n° 13 ([15/07/2021])  

Permalink

Mask R-CNN-based building extraction from VHR satellite data in operational humanitarian action: An example related to Covid-19 response in Khartoum, Sudan / Dirk Tiede in Transactions in GIS, Vol 25 n° 3 (June 2021)  

Permalink