Centre de documentation
scientifique

Siamese KPConv: 3D multiple change detection from raw point clouds using deep learning / Iris de Gelis in ISPRS Journal of photogrammetry and remote sensing, vol 197 (March 2023)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 197 (March 2023) . - pp 274 - 291 Titre : Siamese KPConv: 3D multiple change detection from raw point clouds using deep learning Type de document : Article/Communication Auteurs : Iris de Gelis, Auteur ; Sébastien Lefèvre, Auteur ; Thomas Corpetti, Auteur Année de publication : 2023 Article en page(s) : pp 274 - 291 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques [Termes IGN] apprentissage profond [Termes IGN] bâtiment [Termes IGN] détection de changement [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] modèle numérique de surface [Termes IGN] réseau neuronal siamois [Termes IGN] semis de points [Termes IGN] végétation [Termes IGN] zone urbaine Résumé : (auteur) This study is concerned with urban change detection and categorization in point clouds. In such situations, objects are mainly characterized by their vertical axis, and the use of native 3D data such as 3D Point Clouds (PCs) is, in general, preferred to rasterized versions because of significant loss of information implied by any rasterization process. Yet, for obvious practical reasons, most existing studies only focus on 2D images for change detection purpose. In this paper, we propose a method capable of performing change detection directly within 3D data. Despite recent deep learning developments in remote sensing, to the best of our knowledge there is no such method to tackle multi-class change segmentation that directly processes raw 3D PCs. Thereby, based on advances in deep learning for change detection in 2D images and for analysis of 3D point clouds, we propose a deep Siamese KPConv network that deals with raw 3D PCs to perform change detection and categorization in a single step. Experimental results are conducted on synthetic and real data of various kinds (LiDAR, multi-sensors). Tests performed on simulated low density LiDAR and multi-sensor datasets show that our proposed method can obtain up to 80% of mean of IoU over classes of changes, leading to an improvement ranging from 10% to 30% over the state-of-the-art. A similar range of improvements is attainable on real data. Then, we show that pre-training Siamese KPConv on simulated PCs allows us to greatly reduce (more than 3,000 ) the annotations required on real data. This is a highly significant result to deal with practical scenarios. Finally, an adaptation of Siamese KPConv is realized to deal with change classification at PC scale. Our network overtakes the current state-of-the-art deep learning method by 23% and 15% of mean of IoU when assessed on synthetic and public Change3D datasets, respectively. The code is available at the following link: https://github.com/IdeGelis/torch-points3d-SiameseKPConv. Numéro de notice : A2023-147 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2023.02.001 Date de publication en ligne : 17/02/2023 En ligne : https://doi.org/10.1016/j.isprsjprs.2023.02.001 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102805 [article]

Multi-objective optimization of urban environmental system design using machine learning / Peiyuan Li in Computers, Environment and Urban Systems, vol 94 (June 2022)  

Public [article]  inComputers, Environment and Urban Systems > vol 94 (June 2022) . - n° 101796 Titre : Multi-objective optimization of urban environmental system design using machine learning Type de document : Article/Communication Auteurs : Peiyuan Li, Auteur ; Tianfang Xu, Auteur ; Shiqi Wei, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 101796 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique [Termes IGN] algorithme génétique [Termes IGN] apprentissage automatique [Termes IGN] dioxyde de carbone [Termes IGN] ilot thermique urbain [Termes IGN] indicateur environnemental [Termes IGN] milieu urbain [Termes IGN] optimisation (mathématiques) [Termes IGN] planification urbaine [Termes IGN] processus gaussien [Termes IGN] régression [Termes IGN] végétation Résumé : (auteur) The efficacy of urban mitigation strategies for heat and carbon emissions relies heavily on local urban characteristics. The continuous development and improvement of urban land surface models enable rather accurate assessment of the environmental impact on urban development strategies, whereas physically-based simulations remain computationally costly and time consuming, as a consequence of the increasing complexity of urban system dynamics. Hence it is imperative to develop fast, efficient, and economic operational toolkits for urban planners to foster the design, implementation, and evaluation of urban mitigation strategies, while retaining the accuracy and robustness of physical models. In this study, we adopt a machine learning (ML) algorithm, viz. Gaussian Process Regression, to emulate the physics of heat and biogenic carbon exchange in the built environment. The ML surrogate is trained and validated on the simulation results generated by a state-of-the-art single-layer urban canopy model over a wide range of urban characteristics, showing high accuracy in capturing heat and carbon dynamics. Using the validated surrogate model, we then conduct multi-objective optimization using the genetic algorithm to optimize urban design scenarios for desirable urban mitigation effects. While the use of urban greenery is found effective in mitigating both urban heat and carbon emissions, there is manifest trade-offs among ameliorating diverse urban environmental indicators. Numéro de notice : A2022-244 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/INFORMATIQUE/URBANISME Nature : Article DOI : 10.1016/j.compenvurbsys.2022.101796 Date de publication en ligne : 18/03/2022 En ligne : https://doi.org/10.1016/j.compenvurbsys.2022.101796 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100184 [article]

Context-dependent detection of non-linearly distributed points for vegetation classification in airborne LiDAR / Denis Horvat in ISPRS Journal of photogrammetry and remote sensing, vol 116 (June 2016)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 116 (June 2016) . - pp 1 – 14 Titre : Context-dependent detection of non-linearly distributed points for vegetation classification in airborne LiDAR Type de document : Article/Communication Auteurs : Denis Horvat, Auteur ; Borut Žalik, Auteur ; Domen Mongus, Auteur Année de publication : 2016 Article en page(s) : pp 1 – 14 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] analyse de sensibilité [Termes IGN] classification dirigée [Termes IGN] détection automatique [Termes IGN] distribution spatiale [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] méthode robuste [Termes IGN] morphologie mathématique [Termes IGN] prise en compte du contexte [Termes IGN] végétation [Termes IGN] zone rurale Résumé : (auteur) This paper proposes a new method for the detection of vegetation in LiDAR data. As vegetation points are characterised by non-linear distributions, they are efficiently recognised based-on large errors obtained when applying the local fitting of planar surfaces. In addition, three contextual filters are introduced capable of dealing with those exceptions that do not conform with previous interpretations. Namely, they are designed for detecting overgrowing vegetation, small objects attached to the planar surfaces (such as balconies, chimneys, and noise within the buildings) and small objects that do not belong to vegetation (vehicles, statues, fences). During the validation, the proposed method achieved over 97% correctness as well as completeness of vegetation recognition in rural areas while its average accuracy in urban settings was 90.7% in terms of F1F1-scores. The method uses only three input parameters and allows for efficient compensation between completeness and correctness, without significantly affecting the F1F1-score. Sensitivity analysis of the method also confirmed the robustness against a sub-optimal definition of the input parameters. Numéro de notice : A2016-576 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2016.02.011 En ligne : https://doi.org/10.1016/j.isprsjprs.2016.02.011 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=81706 [article]

Vector attribute profiles for hyperspectral image classification / Erchan Aptoula in IEEE Transactions on geoscience and remote sensing, vol 54 n° 6 (June 2016)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 54 n° 6 (June 2016) . - pp 3208 - 3220 Titre : Vector attribute profiles for hyperspectral image classification Type de document : Article/Communication Auteurs : Erchan Aptoula, Auteur ; Mauro Dalla Mura, Auteur ; Sébastien Lefèvre, Auteur Année de publication : 2016 Article en page(s) : pp 3208 - 3220 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] classification automatique [Termes IGN] image hyperspectrale [Termes IGN] morphologie mathématique [Termes IGN] niveau de gris (image) [Termes IGN] vecteur propre [Termes IGN] végétation Résumé : (Auteur) Morphological attribute profiles are among the most prominent spectral-spatial pixel description methods. They are efficient, effective, and highly customizable multiscale tools based on hierarchical representations of a scalar input image. Their application to multivariate images in general and hyperspectral images in particular has been so far conducted using the marginal strategy, i.e., by processing each image band (eventually obtained through a dimension reduction technique) independently. In this paper, we investigate the alternative vector strategy, which consists in processing the available image bands simultaneously. The vector strategy is based on a vector-ordering relation that leads to the computation of a single max and min tree per hyperspectral data set, from which attribute profiles can then be computed as usual. We explore known vector-ordering relations for constructing such max trees and, subsequently, vector attribute profiles and introduce a combination of marginal and vector strategies. We provide an experimental comparison of these approaches in the context of hyperspectral classification with common data sets, where the proposed approach outperforms the widely used marginal strategy. Numéro de notice : A2016-850 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2015.2513424 En ligne : https://doi.org/10.1109/TGRS.2015.2513424 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82932 [article]

Changes in thermal infrared spectra of plants caused by temperature and water stress / Maria F. Buitrago in ISPRS Journal of photogrammetry and remote sensing, vol 111 (January 2016)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 111 (January 2016) . - pp 22 – 31 Titre : Changes in thermal infrared spectra of plants caused by temperature and water stress Type de document : Article/Communication Auteurs : Maria F. Buitrago, Auteur ; Thomas A. Groen, Auteur ; Christoph A. Hecker, Auteur ; Andrew K. Skidmore, Auteur Année de publication : 2016 Article en page(s) : pp 22 – 31 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] bruit thermique [Termes IGN] détection de changement [Termes IGN] feuille (végétation) [Termes IGN] image thermique [Termes IGN] végétation Résumé : (auteur) Environmental stress causes changes in leaves and the structure of plants. Although physiological adaptations to stress by plants have been explored, the effect of stress on the spectral properties in the thermal part of the electromagnetic spectrum (3–16 μm) has not yet been investigated. In this research two plant species (European beech, Fagus sylvatica and rhododendron, Rhododendron cf. catawbiense) that both grow naturally under temperature limited conditions were selected, representing deciduous and evergreen plants respectively. Besides TIR spectra, Leaf Water Content (LWC) and cuticle thickness were measured as possible variables that can explain the changes in TIR spectra. The results demonstrated that both species, when exposed to either water or temperature stress, showed significant changes in their TIR spectra. The changes in TIR in response to stress were similar within a species, regardless of the stress imposed on them. However, changes in TIR spectra differed between species. For rhododendron emissivity in TIR increased under stress while for beech it decreased. Both species showed depletion of Leaf Water Content (LWC) under stress, ruling LWC out as a main cause for the change in the TIR spectra. Cuticle thickness remained constant for beech, but increased for rhododendron. This suggests that changes in emissivity may be linked to changes in the cuticle thickness and possibly the structure of cuticle. It is known that spectral changes in this region have a close connection with microstructure and biochemistry of leaves. We propose detailed measurements of these changes in the cuticle to analyze the effect of microstructure on TIR spectra. Numéro de notice : A2016-038 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2015.11.003 Date de publication en ligne : 08/12/2015 En ligne : https://doi.org/10.1016/j.isprsjprs.2015.11.003 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=79517 [article]

Passive microwave remote sensing of soil moisture based on dynamic vegetation scattering properties for AMSR-E / Jinyang Du in IEEE Transactions on geoscience and remote sensing, vol 54 n° 1 (January 2016)  

Permalink

Impact of diurnal variation in vegetation water content on radar backscatter from maize during water stress / Tim Van Emmerik in IEEE Transactions on geoscience and remote sensing, vol 53 n° 7 (July 2015)    

Permalink

A Landsat data tiling and compositing approach optimized for change detection in the conterminous United States / Kurtis J. Nelson in Photogrammetric Engineering & Remote Sensing, PERS, vol 81 n° 7 (July 2015)  

Permalink

Vegetation sensing using GPS-interferometric reflectometry: theoretical effects of canopy parameters on signal-to-noise ratio data / C.C. Chew in IEEE Transactions on geoscience and remote sensing, vol 53 n° 5 (mai 2015)  

Permalink

A tale of two cities / Michel Mouléry in GEO: Geoconnexion international, vol 14 n° 3 (March 2015)

Permalink

Spectral-angle-based Laplacian Eigenmaps for non linear dimensionality reduction of hyperspectral imagery / L. Yan in Photogrammetric Engineering & Remote Sensing, PERS, vol 80 n° 9 (September 2014)  

Permalink

Combining hyperspectral and Lidar data for vegetation mapping in the Florida Everglades / Caiyun Zhang in Photogrammetric Engineering & Remote Sensing, PERS, vol 80 n° 8 (August 2014)  

Permalink

An extended approach for biomass estimation in a mixed vegetation area using ASAR and TM data / Minfeng Xing in Photogrammetric Engineering & Remote Sensing, PERS, vol 80 n° 5 (May 2014)  

Permalink

Indoor and outdoor depth imaging of leaves with time-of-flight and stereo vision sensors: Analysis and comparison / Wajahat Kazmi in ISPRS Journal of photogrammetry and remote sensing, vol 88 (February 2014)  

Permalink

Steering global mapping project and developing global map version 2 / Taro Ubukawa in Bulletin of the GeoSpatial Information authority of Japan, vol 61 (December 2013)  

Permalink