Centre dedocumentation
scientifique

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]

Exploring the advantages of the maximum entropy model in calibrating cellular automata for urban growth simulation: a comparative study of four methods / Bin Zhang in GIScience and remote sensing, vol 59 n° 1 (2022)  

Public [article]  inGIScience and remote sensing > vol 59 n° 1 (2022) . - pp 71 - 95 Titre : Exploring the advantages of the maximum entropy model in calibrating cellular automata for urban growth simulation: a comparative study of four methods Type de document : Article/Communication Auteurs : Bin Zhang, Auteur ; Haijun Wang, Auteur Année de publication : 2022 Article en page(s) : pp 71 - 95 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] analyse comparative [Termes IGN] apprentissage automatique [Termes IGN] automate cellulaire [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] croissance urbaine [Termes IGN] entropie maximale [Termes IGN] modèle de simulation [Termes IGN] paysage urbain [Termes IGN] Pékin (Chine) [Termes IGN] régression logistique [Termes IGN] réseau neuronal artificiel [Termes IGN] urbanisation [Termes IGN] Wuhan (Chine) Résumé : (auteur) As a powerful predictive technique based on machine learning, the maximum entropy (MaxEnt) model has been widely used in geographic modeling. However, its performance in calibrating cellular automata (CA) for urban growth simulation has not been investigated. This study compares the MaxEnt model with logistic regression (LR), artificial neural network (ANN), and support vector machine (SVM) models to explore its advantages in simulating urban growth and interpreting driving mechanisms. With the land use data of 2000 and 2020 from GlobeLand30, the constructed LR-CA, ANN-CA, SVM-CA, and MaxEnt-CA models are applied to simulate the urban growth of Beijing, Tianjin, and Wuhan, respectively. Their performance has been evaluated from multiple aspects such as the accuracy of training, testing, and projecting, computational efficiency, simulation accuracy, and simulated urban landscape. The results indicate that the MaxEnt model is superior to the other models except for the computational efficiency, but the time required for the MaxEnt training and projecting is acceptable and far less than that of the SVM. Taking the LR-CA as the benchmark, the kappa coefficients (Kappa) of the MaxEnt-CA have been increased by 4.20%, 3.38%, and 5.87% in Beijing, Tianjin, and Wuhan, respectively; the increments of corresponding figure of merits (FoM) are 6.26%, 4.58%, and 8.49%. The driving mechanisms of urban growth such as the interactions, response curves, and importance of spatial variables, have also been revealed by the MaxEnt modeling. The driving mechanisms of urban growth in Tianjin are more complex than that in Beijing and Wuhan, because there are more variable interactions; the relationships between spatial factors and urban growth in the three study areas are all nonlinear; the topographic factors and city center of Beijing, the traffic factors and water bodies of Tianjin, and the traffic factors, city center and water bodies of Wuhan are significant factors affecting their urban growth. Numéro de notice : A2022-130 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/URBANISME Nature : Article DOI : 10.1080/15481603.2021.2016240 Date de publication en ligne : 30/12/2021 En ligne : https://doi.org/10.1080/15481603.2021.2016240 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99715 [article]

Endmember bundle extraction based on multiobjective optimization / Rong Liu in IEEE Transactions on geoscience and remote sensing, vol 59 n° 10 (October 2021)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 59 n° 10 (October 2021) . - pp 8630 - 8645 Titre : Endmember bundle extraction based on multiobjective optimization Type de document : Article/Communication Auteurs : Rong Liu, Auteur ; Xiao Xiang Zhu, Auteur Année de publication : 2021 Article en page(s) : pp 8630 - 8645 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse spectrale [Termes IGN] compensation par faisceaux [Termes IGN] distribution de Pareto [Termes IGN] image hyperspectrale [Termes IGN] modèle linéaire [Termes IGN] optimisation par essaim de particules Résumé : (auteur) A number of endmember extraction methods have been developed to identify pure pixels in hyperspectral images (HSIs). The majority of them use only one spectrum to represent one kind of material, which ignores the spectral variability problem that particularly characterizes a HSI with high spatial resolution. Only a few algorithms have been developed to identify multiple endmembers representing the spectral variability within each class, called endmember bundle extraction (EBE). This article introduces multiobjective particle swarm optimization for the identification of multiple endmember spectra with variability. Unlike existing convex geometry-based EBE methods, which operate on a single geometry of the dataspace, the proposed method divides the observed data into subsets along the spectral dimension and simultaneously operates on multiple dataspaces to obtain candidate endmembers based on multiobjective particle swarm optimization. The candidate endmembers are then refined by spatial post-processing and sequential forward floating selection to produce the final result. Experiments are conducted on both synthetic and real hyperspectral data to demonstrate the effectiveness of the proposed method in comparison with several state-of-the-art methods. Numéro de notice : A2021-714 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.3037249 En ligne : https://doi.org/10.1109/TGRS.2020.3037249 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98621 [article]

Modeling in forestry using mixture models fitted to grouped and ungrouped data / Eric K. Zenner in Forests, vol 12 n° 9 (September 2021)  

Public [article]  inForests > vol 12 n° 9 (September 2021) . - n° 1196 Titre : Modeling in forestry using mixture models fitted to grouped and ungrouped data Type de document : Article/Communication Auteurs : Eric K. Zenner, Auteur ; Mahdi Teimouri, Auteur Année de publication : 2021 Article en page(s) : n° 1196 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Statistiques [Termes IGN] algorithme espérance-maximisation [Termes IGN] complexité [Termes IGN] diamètre à hauteur de poitrine [Termes IGN] distribution de Weibull [Termes IGN] distribution, loi de [Termes IGN] dynamique de la végétation [Termes IGN] estimation par noyau [Termes IGN] méthode du maximum de vraisemblance (estimation) [Termes IGN] modélisation de la forêt [Termes IGN] structure d'un peuplement forestier Résumé : (auteur) The creation and maintenance of complex forest structures has become an important forestry objective. Complex forest structures, often expressed in multimodal shapes of tree size/diameter (DBH) distributions, are challenging to model. Mixture probability density functions of two- or three-component gamma, log-normal, and Weibull mixture models offer a solution and can additionally provide insights into forest dynamics. Model parameters can be efficiently estimated with the maximum likelihood (ML) approach using iterative methods such as the Newton-Raphson (NR) algorithm. However, the NR algorithm is sensitive to the choice of initial values and does not always converge. As an alternative, we explored the use of the iterative expectation-maximization (EM) algorithm for estimating parameters of the aforementioned mixture models because it always converges to ML estimators. Since forestry data frequently occur both in grouped (classified) and ungrouped (raw) forms, the EM algorithm was applied to explore the goodness-of-fit of the gamma, log-normal, and Weibull mixture distributions in three sample plots that exhibited irregular, multimodal, highly skewed, and heavy-tailed DBH distributions where some size classes were empty. The EM-based goodness-of-fit was further compared against a nonparametric kernel-based density estimation (NK) model and the recently popularized gamma-shaped mixture (GSM) models using the ungrouped data. In this example application, the EM algorithm provided well-fitting two- or three-component mixture models for all three model families. The number of components of the best-fitting models differed among the three sample plots (but not among model families) and the mixture models of the log-normal and gamma families provided a better fit than the Weibull distribution for grouped and ungrouped data. For ungrouped data, both log-normal and gamma mixture distributions outperformed the GSM model and, with the exception of the multimodal diameter distribution, also the NK model. The EM algorithm appears to be a promising tool for modeling complex forest structures. Numéro de notice : A2021-721 Affiliation des auteurs : non IGN Thématique : FORET Nature : Article DOI : 10.3390/f12091196 En ligne : https://doi.org/10.3390/f12091196 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98639 [article]

Benford’s law and geographical information – the example of OpenStreetMap / Franz-Benjamin Mocnik in International journal of geographical information science IJGIS, vol 35 n° 9 (September 2021)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 35 n° 9 (September 2021) . - pp 1746 - 1772 Titre : Benford’s law and geographical information – the example of OpenStreetMap Type de document : Article/Communication Auteurs : Franz-Benjamin Mocnik, Auteur Année de publication : 2021 Article en page(s) : pp 1746 - 1772 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique [Termes IGN] distribution de Benford [Termes IGN] données localisées [Termes IGN] données localisées des bénévoles [Termes IGN] données statistiques [Termes IGN] hétérogénéité spatiale [Termes IGN] OpenStreetMap [Termes IGN] qualité des données Résumé : (auteur) Few laws about geographical information are known, partly because geographical information is inherently complex. Tobler’s first law of Geography and, to a lesser degree, also his second law are among the rare exceptions. In this article, we explore the validity of Benford’s law in the context of the example of OpenStreetMap. More specifically, we compare the distribution of several numerical features of geographical entities to the Benford distribution. It is demonstrated that the numerical features examined are in accordance with Benford’s law to a varying degree with little variation between the types of geographical entities. Spatial patterns in the deviation from Benford’s law are shown to be similar for some aspects but to strongly differ for other ones. We show that many aspects of the data tend to deviate more than average from the Benford distribution in Africa, Greenland, smaller island countries, and, to a lesser degree, in South America. Also, the scale-dependency of Benford’s law is explored. Motivated by the use of Benford’s law to detect indications for fraud in economic and other datasets, future prospects and limitations to systematically develop intrinsic data quality measures are discussed. Numéro de notice : A2021-594 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/MATHEMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2020.1829627 Date de publication en ligne : 07/04/2021 En ligne : https://doi.org/10.1080/13658816.2020.1829627 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98215 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
079-2021091	SL	Revue	Centre de documentation	Revues en salle	Disponible

Role of maximum entropy and citizen science to study habitat suitability of jacobin cuckoo in different climate change scenarios / Priyinka Singh in ISPRS International journal of geo-information, vol 10 n° 7 (July 2021)  

Permalink

Hyperspectral image denoising via clustering-based latent variable in variational Bayesian framework / Peyman Azimpour in IEEE Transactions on geoscience and remote sensing, vol 59 n° 4 (April 2021)  

Permalink

Space-time disease mapping by combining Bayesian maximum entropy and Kalman filter: the BME-Kalman approach / Bisong Hu in International journal of geographical information science IJGIS, vol 35 n° 3 (March 2021)  

Permalink

Urban flood hazard mapping using machine learning models: GARP, RF, MaxEnt and NB / Mahya Norallahi in Natural Hazards, vol 106 n° 1 (March 2021)  

Permalink

Using automated vegetation cover estimation from close-range photogrammetric point clouds to compare vegetation location properties in mountain terrain / R. Niederheiser in GIScience and remote sensing, vol 58 n° 1 (February 2021)  

Permalink

Adaptive filtering / Wenping Cao (2021)  

Permalink

Data science: Measuring uncertainties / Carlos Alberto De Bragança Pereira (2021)  

Permalink

Mathematics and digital signal processing / Pavel Lyakhov (2021)  

Permalink

Polynomials: special polynomials and number-theoretical applications / Ákos Pintér (2021)  

Permalink

Spatial characterization and distribution modelling of Ensete ventricosum (wild and cultivated) in Ethiopia / Meron Awoke Eshetae in Geocarto international, vol 36 n° 1 ([01/01/2021])  

Permalink