Centre dedocumentation
scientifique

Unsupervised semantic and instance segmentation of forest point clouds / Di Wang in ISPRS Journal of photogrammetry and remote sensing, vol 165 (July 2020)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 165 (July 2020) . - pp 86 - 97 Titre : Unsupervised semantic and instance segmentation of forest point clouds Type de document : Article/Communication Auteurs : Di Wang, Auteur Année de publication : 2020 Article en page(s) : pp 86 - 97 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes descripteurs IGN] analyse de groupement [Termes descripteurs IGN] classification non dirigée [Termes descripteurs IGN] données lidar [Termes descripteurs IGN] étiquetage sémantique [Termes descripteurs IGN] hauteur des arbres [Termes descripteurs IGN] houppier [Termes descripteurs IGN] indice foliaire [Termes descripteurs IGN] interprétation automatique [Termes descripteurs IGN] segmentation sémantique [Termes descripteurs IGN] semis de points [Termes descripteurs IGN] télémètre laser terrestre Résumé : (auteur) Terrestrial Laser Scanning (TLS) has been increasingly used in forestry applications including forest inventory and plant ecology. Tree biophysical properties such as leaf area distributions and wood volumes can be accurately estimated from TLS point clouds. In these applications, a prerequisite is to properly understand the information content of large scale point clouds (i.e., semantic labelling of point clouds), so that tree-scale attributes can be retrieved. Currently, this requirement is undergoing laborious and time consuming manual works. In this work, we jointly address the problems of semantic and instance segmentation of forest point clouds. Specifically, we propose an unsupervised pipeline based on a structure called superpoint graph, to simultaneously perform two tasks: single tree isolation and leaf-wood classification. The proposed method is free from restricted assumptions of forest types. Validation using simulated data resulted in a mean Intersection over Union (mIoU) of 0.81 for single tree isolation, and an overall accuracy of 87.7% for leaf-wood classification. The single tree isolation led to a relative root mean square error (RMSE%) of 2.9% and 19.8% for tree height and crown diameter estimations, respectively. Comparisons with existing methods on other benchmark datasets showed state-of-the-art results of our method on both single tree isolation and leaf-wood classification tasks. We provide the entire framework as an open-source tool with an end-user interface. This study closes the gap for using TLS point clouds to quantify tree-scale properties in large areas, where automatic interpretation of the information content of TLS point clouds remains a crucial challenge. Numéro de notice : A2020-347 Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.04.020 date de publication en ligne : 28/05/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.04.020 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95228 [article]

Under-canopy UAV laser scanning for accurate forest field measurements / Eric Hyyppä in ISPRS Journal of photogrammetry and remote sensing, vol 164 (June 2020)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 164 (June 2020) . - pp 41 - 60 Titre : Under-canopy UAV laser scanning for accurate forest field measurements Type de document : Article/Communication Auteurs : Eric Hyyppä, Auteur ; Juha Hyyppä, Auteur ; Teemu Hakala, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 41 - 60 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes descripteurs IGN] balayage laser [Termes descripteurs IGN] canopée [Termes descripteurs IGN] densité du bois [Termes descripteurs IGN] diamètre à hauteur de poitrine [Termes descripteurs IGN] données lidar [Termes descripteurs IGN] erreur moyenne quadratique [Termes descripteurs IGN] Finlande [Termes descripteurs IGN] forêt boréale [Termes descripteurs IGN] hauteur à la base du houppier [Termes descripteurs IGN] hauteur des arbres [Termes descripteurs IGN] image de drone [Termes descripteurs IGN] inventaire forestier local [Termes descripteurs IGN] modèle de croissance [Termes descripteurs IGN] semis de points [Termes descripteurs IGN] Simultaneous Localisation And Mapping [Termes descripteurs IGN] télédétection aérienne [Termes descripteurs IGN] télémètre laser terrestre [Termes descripteurs IGN] télémétrie laser aéroporté [Termes descripteurs IGN] tronc Résumé : (auteur) Surveying and robotic technologies are converging, offering great potential for robotic-assisted data collection and support for labour intensive surveying activities. From a forest monitoring perspective, there are several technological and operational aspects to address concerning under-canopy flying unmanned airborne vehicles (UAV). To demonstrate this emerging technology, we investigated tree detection and stem curve estimation using laser scanning data obtained with an under-canopy flying UAV. To this end, we mounted a Kaarta Stencil-1 laser scanner with an integrated simultaneous localization and mapping (SLAM) system on board an UAV that was manually piloted with the help of video goggles receiving a live video feed from the onboard camera of the UAV. Using the under-canopy flying UAV, we collected SLAM-corrected point cloud data in a boreal forest on two 32 m 32 m test sites that were characterized as sparse ( = 42 trees) and obstructed ( = 43 trees), respectively. Novel data processing algorithms were applied for the point clouds in order to detect the stems of individual trees and to extract their stem curves and diameters at breast height (DBH). The estimated tree attributes were compared against highly accurate field reference data that was acquired semi-manually with a multi-scan terrestrial laser scanner (TLS). The proposed method succeeded in detecting 93% of the stems in the sparse plot and 84% of the stems in the obstructed plot. In the sparse plot, the DBH and stem curve estimates had a root-mean-squared error (RMSE) of 0.60 cm (2.2%) and 1.2 cm (5.0%), respectively, whereas the corresponding values for the obstructed plot were 0.92 cm (3.1%) and 1.4 cm (5.2%). By combining the stem curves extracted from the under-canopy UAV laser scanning data with tree heights derived from above-canopy UAV laser scanning data, we computed stem volumes for the detected trees with a relative RMSE of 10.1% in both plots. Thus, the combination of under-canopy and above-canopy UAV laser scanning allowed us to extract the stem volumes with an accuracy comparable to the past best studies based on TLS in boreal forest conditions. Since the stems of several spruces located on the test sites suffered from severe occlusion and could not be detected with the stem-based method, we developed a separate work flow capable of detecting trees with occluded stems. The proposed work flow enabled us to detect 98% of trees in the sparse plot and 93% of the trees in the obstructed plot with a 100% correction level in both plots. A key benefit provided by the under-canopy UAV laser scanner is the short period of time required for data collection, currently demonstrated to be much faster than the time required for field measurements and TLS. The quality of the measurements acquired with the under-canopy flying UAV combined with the demonstrated efficiency indicates operational potential for supporting fast and accurate forest resource inventories. Numéro de notice : A2020-240 Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.03.021 date de publication en ligne : 11/04/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.03.021 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94994 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2020061	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2020063	DEP-RECP	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2020062	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Delineating minor landslide displacements using GPS and terrestrial laser scanning-derived terrain surfaces and trees: a case study of the Slumgullion landslide, Lake City, Colorado / Jin Wang in Survey review, vol 52 n° 372 (May 2020)  

Public [article]  inSurvey review > vol 52 n° 372 (May 2020) . - pp 215 - 223 Titre : Delineating minor landslide displacements using GPS and terrestrial laser scanning-derived terrain surfaces and trees: a case study of the Slumgullion landslide, Lake City, Colorado Type de document : Article/Communication Auteurs : Jin Wang, Auteur ; Duo Wang, Auteur ; Shengqi Liu, Auteur ; Boyu Jia, Auteur Année de publication : 2020 Article en page(s) : pp 215 - 223 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes descripteurs IGN] algorithme ICP [Termes descripteurs IGN] analyse comparative [Termes descripteurs IGN] arbre (flore) [Termes descripteurs IGN] Colorado (Etats-Unis) [Termes descripteurs IGN] effondrement de terrain [Termes descripteurs IGN] Ransac (algorithme) [Termes descripteurs IGN] semis de points [Termes descripteurs IGN] télémétrie laser terrestre Résumé : (Auteur) Multi-temporal high-density terrestrial laser scanning (TLS) datasets are processed to delineating possible movements from terrain surfaces and trees. Terrain surface movements are estimated with the help of segmentation and random sample consensus (RANSAC) algorithm. Tree movements are interpreted by iterative closest point (ICP) solved translations and rotations of tree point clouds. The capabilities of the proposed methodology were tested using a case study of the Slumgullion landslide, where the trees without clear trunks cover the terrain surfaces. The displacements from the terrain surfaces and trees are similar with the results observed using our global positioning system (GPS) and historic results. Numéro de notice : A2020-177 Thématique : IMAGERIE/POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/00396265.2018.1558580 date de publication en ligne : 25/12/2018 En ligne : https://doi.org/10.1080/00396265.2018.1558580 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94835 [article]

Filtering of airborne LiDAR bathymetry based on bidirectional cloth simulation / Anxiu Yang in ISPRS Journal of photogrammetry and remote sensing, vol 163 (May 2020)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 163 (May 2020) . - pp 49 - 61 Titre : Filtering of airborne LiDAR bathymetry based on bidirectional cloth simulation Type de document : Article/Communication Auteurs : Anxiu Yang, Auteur ; Fanlin Yang, Auteur ; Dianpeng Su, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 49 - 61 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes descripteurs IGN] ajustement de paramètres [Termes descripteurs IGN] Chine [Termes descripteurs IGN] courbe de Gauss [Termes descripteurs IGN] données lidar [Termes descripteurs IGN] filtrage de points [Termes descripteurs IGN] itération [Termes descripteurs IGN] lidar bathymétrique [Termes descripteurs IGN] relief sous-marin [Termes descripteurs IGN] semis de points [Termes descripteurs IGN] télémétrie laser aéroporté Résumé : (auteur) Current filtering methods of airborne LiDAR bathymetry (ALB) point clouds cannot identify negative anomalies or avoid over-filtering of the data. To overcome these problems, we propose a bidirectional cloth simulation filtering (BCSF) method and verify it using captured data. First, a transfer iterative trend surface is established to eliminate the negative anomalies and realize the continuous expression of the seafloor topography. The terrain complexities of the seafloor points are calculated using four extracted feature factors: slope, standard deviation of depth, Gaussian curvature, and roughness. We then calculate the sub-regional terrain complexity and the adaptive distance threshold and obtain user-defined parameters. Finally, sub-regional filtering is carried out, and a filtered surface is established to solve the over-filtering problem of convex and concave seafloor topographies based on the BCSF correction model. To evaluate the performance of the proposed method, the BCSF method was applied to ALB data captured around Yuanzhi Island in the South China Sea. The experimental results show that the BCSF method effectively filters out non-seafloor points and fully preserves the seafloor microtopography to realize the integrity of the seafloor topography. The proposed BCSF method outperforms the cloth simulation filtering method in terms of the elimination rate, which decreases from 38.78% to 2.52% and from 29.52% to 0.70% in the whole study area and local study area, respectively. Consequently, the BCSF method that combines forward filtering with inverse filtering exhibits complementary advantages, avoids over-filtering, and demonstrates strong adaptability and robustness for ALB data. Numéro de notice : A2020-137 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.03.004 date de publication en ligne : 09/03/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.03.004 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94755 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2020051	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2020053	DEP-RECP	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2020052	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Improved supervised learning-based approach for leaf and wood classification from LiDAR point clouds of forests / Sruthi M. Krishna Moorthy in IEEE Transactions on geoscience and remote sensing, vol 58 n° 5 (May 2020)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 58 n° 5 (May 2020) . - pp 3057 - 3070 Titre : Improved supervised learning-based approach for leaf and wood classification from LiDAR point clouds of forests Type de document : Article/Communication Auteurs : Sruthi M. Krishna Moorthy, Auteur ; Kim Calders, Auteur ; Matheus B. Vicari, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 3057 - 3070 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes descripteurs IGN] apprentissage automatique [Termes descripteurs IGN] apprentissage dirigé [Termes descripteurs IGN] atmosphère terrestre [Termes descripteurs IGN] canopée [Termes descripteurs IGN] classification dirigée [Termes descripteurs IGN] classification par forêts aléatoires [Termes descripteurs IGN] données lidar [Termes descripteurs IGN] faisceau laser [Termes descripteurs IGN] feuille (végétation) [Termes descripteurs IGN] foresterie [Termes descripteurs IGN] forêt feuillue [Termes descripteurs IGN] forêt tropicale [Termes descripteurs IGN] plus proche voisin (algorithme) [Termes descripteurs IGN] précision de la classification [Termes descripteurs IGN] Python (langage de programmation) [Termes descripteurs IGN] semis de points [Termes descripteurs IGN] transfert radiatif Résumé : (auteur) Accurately classifying 3-D point clouds into woody and leafy components has been an interest for applications in forestry and ecology including the better understanding of radiation transfer between canopy and atmosphere. The past decade has seen an increase in the methods attempting to classify leaves and wood in point clouds based on radiometric or geometric features. However, classification purely based on radiometric features is sensor-specific, and the method by which the local neighborhood of a point is defined affects the accuracy of classification based on geometric features. Here, we present a leaf-wood classification method combining geometrical features defined by radially bounded nearest neighbors at multiple spatial scales in a machine learning model. We compared the performance of three different machine learning models generated by the random forest (RF), XGBoost, and lightGBM algorithms. Using multiple spatial scales eliminates the need for an optimal neighborhood size selection and defining the local neighborhood by radially bounded nearest neighbors makes the method broadly applicable for point clouds of varying quality. We assessed the model performance at the individual tree- and plot-level on field data from tropical and deciduous forests, as well as on simulated point clouds. The method has an overall average accuracy of 94.2% on our data sets. For other data sets, the presented method outperformed the methods in literature in most cases without the need for additional postprocessing steps that are needed in most of the existing methods. We provide the entire framework as an open-source python package. Numéro de notice : A2020-232 Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2019.2947198 date de publication en ligne : 31/10/2019 En ligne : https://doi.org/10.1109/TGRS.2019.2947198 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94970 [article]

A point cloud feature regularization method by fusing judge criterion of field force / Xijiang Chen in IEEE Transactions on geoscience and remote sensing, vol 58 n° 5 (May 2020)  

Permalink

La télédétection aéroportée pour la gestion des territoires forestiers de montagne / Jean-Matthieu Monnet in Sciences, eaux & territoires, n° 33 (avril 2020)  

Permalink

Directionally constrained fully convolutional neural network for airborne LiDAR point cloud classification / Congcong Wen in ISPRS Journal of photogrammetry and remote sensing, vol 162 (April 2020)  

Permalink

Using multi-scale and hierarchical deep convolutional features for 3D semantic classification of TLS point clouds / Zhou Guo in International journal of geographical information science IJGIS, vol 34 n° 4 (April 2020)  

Permalink

Classification and segmentation of mining area objects in large-scale spares Lidar point cloud using a novel rotated density network / Yueguan Yan in ISPRS International journal of geo-information, vol 9 n° 3 (March 2020)  

Permalink

Comparison and analysis of results of 3D modelling of complex cultural and historical objects using different types of terrestrial laser scanner / Admir Mulahusic in Survey review, vol 52 n° 371 (March 2020)  

Permalink

A discriminative tensor representation model for feature extraction and classification of multispectral LiDAR data / Qingwang Wang in IEEE Transactions on geoscience and remote sensing, vol 58 n° 3 (March 2020)  

Permalink

Generation of digital terrain model for forest areas using a new particle swarm optimization on LiDAR data / Behnaz Bigdeli in Survey review, vol 52 n° 371 (March 2020)  

Permalink

Hierarchical classification of pole‐like objects in mobile laser scanning point clouds / Rufei Liu in Photogrammetric record, vol 35 n° 169 (March 2020)  

Permalink

Learning sequential slice representation with an attention-embedding network for 3D shape recognition and retrieval in MLS point clouds / Zhipeng Luo in ISPRS Journal of photogrammetry and remote sensing, vol 161 (March 2020)  

Permalink