Centre de documentation
scientifique

A geometry-aware attention network for semantic segmentation of MLS point clouds / Jie Wan in International journal of geographical information science IJGIS, vol 37 n° 1 (January 2023)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 37 n° 1 (January 2023) . - pp 138 - 161 Titre : A geometry-aware attention network for semantic segmentation of MLS point clouds Type de document : Article/Communication Auteurs : Jie Wan, Auteur ; Yongyang Xu, Auteur ; Qinjun Qiu, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : pp 138 - 161 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] attention (apprentissage automatique) [Termes IGN] corrélation [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] figure géométrique [Termes IGN] fonction de perte [Termes IGN] graphe [Termes IGN] Perceptron multicouche [Termes IGN] scène urbaine [Termes IGN] segmentation sémantique [Termes IGN] semis de points Résumé : (auteur) Semantic segmentation of mobile laser scanning (MLS) point clouds can provide meaningful 3 D semantic information of urban facilities for various applications. However, it still remains a challenge to extract accurate 3 D semantic information from MLS point cloud data due to its irregular 3 D geometric structure in a large-scale outdoor scene. To this end, this study develops a geometry-aware attention point network (GAANet) with geometric properties of the point cloud as a reference. Specifically, the proposed method first builds a graph-like region for each input point to establish the geometric correlation toward its neighbors for robustly descripting local geometry-aware features. Thereafter, the method introduces a novel multi-head attention mechanism to efficiently learn local discriminative features on the constructed graphs and a feature combination operation to capture both local and global geometric dependencies inside fused point features for significantly facilitating the segmentation of small or incomplete 3 D objects at point-level. Finally, an adaptive loss function is appended to handle class imbalance for the overall performance improvement. The validation experiments on two challenging benchmarks demonstrate the effectiveness and powerful generation ability of the proposed method, which achieves state-of-the-art performance with mean IoU of 65.09% and 95.20% in the Toronto-3D and Oakland 3-D MLS dataset, respectively. Numéro de notice : A2023-038 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1080/13658816.2022.2111572 Date de publication en ligne : 24/08/2022 En ligne : https://doi.org/10.1080/13658816.2022.2111572 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102309 [article]

Deep learning for the detection of early signs for forest damage based on satellite imagery / Dennis Wittich 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 307 - 315 Titre : Deep learning for the detection of early signs for forest damage based on satellite imagery Type de document : Article/Communication Auteurs : Dennis Wittich, Auteur ; Franz Rottensteiner, Auteur ; Mirjana Voelsen, Auteur ; Christian Heipke, Auteur ; Sönke Müller, Auteur Année de publication : 2022 Article en page(s) : pp 307 - 315 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] apprentissage profond [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] dégradation de la flore [Termes IGN] dommage forestier causé par facteurs naturels [Termes IGN] fonction de perte [Termes IGN] image Sentinel-MSI [Termes IGN] régression [Termes IGN] série temporelle [Termes IGN] surveillance forestière Résumé : (auteur) We present an approach for detecting early signs for upcoming forest damages by training a Convolutional Neural Network (CNN) for the pixel-wise prediction of the remaining life-time (RLT) of trees in forests based on Sentinel-2 imagery. We focus on a scenario in which reference data are only available for a related task, namely for a bi-temporal pixel-wise classification of forest degradation. This reference is used to train a CNN for the pixel-wise prediction of forest degradation. In this context, we propose a new sub-sampling-based approach for compensating the effects of a heavy class imbalance in the training data. Using the resulting classification model, we predict semi-labels for images of a Sentinel-2 time series, from which training data for a CNN designed to regress the RLT can be derived after some label cleansing. However, due to data gaps in the time series, e.g. caused by clouds, only intervals can be derived for the target variable to be regressed, and for some training pixels one of the interval limits may even be unknown. Consequently, we propose a new loss function for training a CNN for regressing the RLT that only requires the known interval limits. The method is evaluated on a data set in Germany, covering a time-span of 5 years. We show that the proposed sub-sampling strategy for dealing with strong label imbalance when training the classifier significantly reduces the training time compared to other approaches. We further show that our model predicts the RLT with a maximum error of two months for 80% of the forest pixels that die within one year from the acquisition date of the Sentinel-2 image. Numéro de notice : A2022-432 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.5194/isprs-annals-V-2-2022-307-2022 Date de publication en ligne : 17/05/2022 En ligne : https://doi.org/10.5194/isprs-annals-V-2-2022-307-2022 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100738 [article]

Uncertainty estimation for stereo matching based on evidential deep learning / Chen Wang in Pattern recognition, vol 124 (April 2022)  

Public [article]  inPattern recognition > vol 124 (April 2022) . - n° 108498 Titre : Uncertainty estimation for stereo matching based on evidential deep learning Type de document : Article/Communication Auteurs : Chen Wang, Auteur ; Xiang Wang, Auteur ; Jiawei Zhang, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 108498 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] appariement d'images [Termes IGN] apprentissage profond [Termes IGN] distribution de Gauss [Termes IGN] fonction de perte [Termes IGN] lissage de données [Termes IGN] modèle d'incertitude [Termes IGN] reconstruction d'image Résumé : (auteur) Although deep learning-based stereo matching approaches have achieved excellent performance in recent years, it is still a non-trivial task to estimate the uncertainty of the produced disparity map. In this paper, we propose a novel approach to estimate both aleatoric and epistemic uncertainties for stereo matching in an end-to-end way. We introduce an evidential distribution, named Normal Inverse-Gamma (NIG) distribution, whose parameters can be used to calculate the uncertainty. Instead of directly regressed from aggregated features, the uncertainty parameters are predicted for each potential disparity and then averaged via the guidance of matching probability distribution. Furthermore, considering the sparsity of ground truth in real scene datasets, we design two additional losses. The first one tries to enlarge uncertainty on incorrect predictions, so uncertainty becomes more sensitive to erroneous regions. The second one enforces the smoothness of the uncertainty in the regions with smooth disparity. Most stereo matching models, such as PSM-Net, GA-Net, and AA-Net, can be easily integrated with our approach. Experiments on multiple benchmark datasets show that our method improves stereo matching results. We prove that both aleatoric and epistemic uncertainties are well-calibrated with incorrect predictions. Particularly, our method can capture increased epistemic uncertainty on out-of-distribution data, making it effective to prevent a system from potential fatal consequences. Code is available at https://github.com/Dawnstar8411/StereoMatching-Uncertainty. Numéro de notice : A2022-198 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.1016/j.patcog.2021.108498 Date de publication en ligne : 23/12/2021 En ligne : https://doi.org/10.1016/j.patcog.2021.108498 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99992 [article]

BuyTheDips : PathLoss for improved topology-preserving deep learning-based image segmentation / Minh On Vu Ngoc (2022)  

Public Titre : BuyTheDips : PathLoss for improved topology-preserving deep learning-based image segmentation Type de document : Article/Communication Auteurs : Minh On Vu Ngoc, Auteur ; Yizi Chen , Auteur ; Nicolas Boutry, Auteur ; Jonathan Fabrizio, Auteur ; Clément Mallet , Auteur Editeur : Ithaca [New York - Etats-Unis] : ArXiv - Université Cornell Année de publication : 2022 Projets : SODUCO / Perret, Julien Importance : 13 p. Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] chemin le plus court, algorithme du [Termes IGN] fonction de perte [Termes IGN] image numérique [Termes IGN] proximité sémantique [Termes IGN] segmentation d'image Résumé : (auteur) Capturing the global topology of an image is essential for proposing an accurate segmentation of its domain. However, most of existing segmentation methods do not preserve the initial topology of the given input, which is detrimental for numerous downstream object-based tasks. This is all the more true for deep learning models which most work at local scales. In this paper, we propose a new topology-preserving deep image segmentation method which relies on a new leakage loss: the Pathloss. Our method is an extension of the BALoss [1], in which we want to improve the leakage detection for better recovering the closeness property of the image segmentation. This loss allows us to correctly localize and fix the critical points (a leakage in the boundaries) that could occur in the predictions, and is based on a shortest-path search algorithm. This way, loss minimization enforces connectivity only where it is necessary and finally provides a good localization of the boundaries of the objects in the image. Moreover, according to our research, our Pathloss learns to preserve stronger elongated structure compared to methods without using topology-preserving loss. Training with our topological loss function, our method outperforms state-of-the-art topology-aware methods on two representative datasets of different natures: Electron Microscopy and Historical Map. Numéro de notice : P2022-005 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Thématique : IMAGERIE/INFORMATIQUE Nature : Preprint nature-HAL : Préprint DOI : 10.48550/arXiv.2207.11446 En ligne : https://doi.org/10.48550/arXiv.2207.11446 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101338