Centre de documentation
scientifique

A novel entropy-based method to quantify forest canopy structural complexity from multiplatform lidar point clouds / Xiaoqiang Liu in Remote sensing of environment, vol 282 (December 2022)  

Public [article]  inRemote sensing of environment > vol 282 (December 2022) . - n° 113280 Titre : A novel entropy-based method to quantify forest canopy structural complexity from multiplatform lidar point clouds Type de document : Article/Communication Auteurs : Xiaoqiang Liu, Auteur ; Qin Ma, Auteur ; Xiaoyong wu, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 113280 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] canopée [Termes IGN] Chine [Termes IGN] couvert forestier [Termes IGN] densité des points [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] échantillonnage [Termes IGN] écosystème forestier [Termes IGN] entropie [Termes IGN] estimation par noyau [Termes IGN] image captée par drone [Termes IGN] modèle numérique de surface de la canopée [Termes IGN] semis de points Résumé : (auteur) Forest canopy structural complexity (CSC) describes the three-dimensional (3D) arrangement of canopy elements, and has become an emergent forest attribute mediating forest ecosystem functioning along with species diversity. Light detection and ranging (lidar), especially the emerging near-surface lidar platforms (e.g., terrestrial laser scanning/TLS, backpack laser scanning/BLS, unmanned aerial vehicle laser scanning/ULS), can depict 3D canopy information with high efficiency and accuracy, providing an ideal data source for forest CSC quantification. However, current existing lidar-based CSC quantification indices may share common limitations of getting saturated in structurally complex forest stands and not fully capturing within-canopy structural variations. In this study, we introduced the concept of entropy into forest CSC quantification, and proposed a new forest CSC index, namely canopy entropy (CE). Two major bottlenecks were addressed in the CE calculation procedure, including (1) using a Mann-Kendall (MK) test-based resampling strategy to address the issue of incongruent sampling chances of canopy elements at different locations from different lidar systems, and (2) using a kernel density estimation (KDE)-based method to reduce its dependence on point density. The effectiveness and generality of CE were evaluated by simulating TLS and ULS point clouds from nine forest stands and collecting TLS, BLS, and ULS point clouds from 110 field plots distributed in five forest sites, covering a large variety of forest types and forest CSC conditions. The results showed that CE was an effective forest CSC quantification index that successfully captured CSC variations caused by both tree density and the number of vertical canopy layers. It had significant positive correlations with four widely used CSC indices (i.e., canopy cover, foliage height diversity, canopy top rugosity, and fractal dimension; R2: 0.32 to 0.67), but outperformed them by overcoming their common limitations. CE estimates from multiplatform lidar point clouds agreed well with each other (R2 ≥ 0.70, RMSE ≤0.10), indicating it has generality in cross-platform forest CSC quantification practices. We believe the proposed CE index has great potential to help us unravel the correlations among forest CSC, species diversity, and forest ecosystem functions, and therefore improve our understanding on forest ecosystem processes. Numéro de notice : A2022-795 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.1016/j.rse.2022.113280 Date de publication en ligne : 26/09/2022 En ligne : https://doi.org/10.1016/j.rse.2022.113280 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101930 [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]

Summarizing large scale 3D mesh for urban navigation / Imeen Ben Salah in Robotics and autonomous systems, vol 152 (June 2022)  

Public [article]  inRobotics and autonomous systems > vol 152 (June 2022) . - n° 104037 Titre : Summarizing large scale 3D mesh for urban navigation Type de document : Article/Communication Auteurs : Imeen Ben Salah, Auteur ; Sébastien Kramm, Auteur ; Cédric Demonceaux, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 104037 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] algorithme ICP [Termes IGN] carte en 3D [Termes IGN] données lidar [Termes IGN] entropie [Termes IGN] image hémisphérique [Termes IGN] image RVB [Termes IGN] information sémantique [Termes IGN] localisation basée vision [Termes IGN] maillage [Termes IGN] navigation autonome [Termes IGN] précision géométrique (imagerie) [Termes IGN] précision radiométrique [Termes IGN] profondeur [Termes IGN] Rouen [Termes IGN] saillance [Termes IGN] zone urbaine Résumé : (auteur) Cameras have become increasingly common in vehicles, smartphones, and advanced driver assistance systems. The areas of application of these cameras in the world of intelligent transportation systems are becoming more and more varied: pedestrian detection, line crossing detection, navigation, …A major area of research currently focuses on mapping that is essential for localization and navigation. However, this step generates an important problem of memory management. Indeed, the memory space required to accommodate the map of a small city is measured in tens gigabytes. In addition, several providers today are competing to produce High-Definition (HD) maps. These maps offer a rich and detailed representation of the environment for highly accurate localization. However, they require a large storage capacity and high transmission and update costs. To overcome these problems, we propose a solution to summarize this type of map by reducing the size while maintaining the relevance of the data for navigation based on vision only. The summary consists in a set of spherical images augmented by depth and semantic information and allowing to keep the same level of visibility in every directions. These spheres are used as landmarks to offer guidance information to a distant agent. They then have to guarantee, at a lower cost, a good level of precision and speed during navigation. Some experiments on real data demonstrate the feasibility for obtaining a summarized map while maintaining a localization with interesting performances. Numéro de notice : A2022-290 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.robot.2022.104037 Date de publication en ligne : 03/02/2022 En ligne : https://doi.org/10.1016/j.robot.2022.104037 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100335 [article]

Probabilistic unsupervised classification for large-scale analysis of spectral imaging data / Emmanuel Paradis in International journal of applied Earth observation and geoinformation, vol 107 (March 2022)  

Public [article]  inInternational journal of applied Earth observation and geoinformation > vol 107 (March 2022) . - n° 102675 Titre : Probabilistic unsupervised classification for large-scale analysis of spectral imaging data Type de document : Article/Communication Auteurs : Emmanuel Paradis, Auteur Année de publication : 2022 Article en page(s) : n° 102675 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse de groupement [Termes IGN] analyse spectrale [Termes IGN] classification barycentrique [Termes IGN] classification ISODATA [Termes IGN] classification non dirigée [Termes IGN] classification par nuées dynamiques [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] détection de changement [Termes IGN] entropie [Termes IGN] image hyperspectrale [Termes IGN] image multibande [Termes IGN] Matlab [Termes IGN] occupation du sol Résumé : (auteur) Land cover classification of remote sensing data is a fundamental tool to study changes in the environment such as deforestation or wildfires. A current challenge is to quantify land cover changes with real-time, large-scale data from modern hyper- or multispectral sensors. A range of methods are available for this task, several of them being based on the k-means classification method which is efficient when classes of land cover are well separated. Here a new algorithm, called probabilistic k-means, is presented to solve some of the limitations of the standard k-means. It is shown that the new algorithm performs better than the standard k-means when the data are noisy. If the number of land cover classes is unknown, an entropy-based criterion can be used to select the best number of classes. The proposed new algorithm is implemented in a combination of R and C computer codes which is particularly efficient with large data sets: a whole image with more than 3 million pixels and covering more than 10,000 km2 can be analysed in a few minutes. Four applications with hyperspectral and multispectral data are presented. For the data sets with ground truth data, the overall accuracy of the probabilistic k-means was substantially improved compared to the standard k-means. One of these data sets includes more than 120 million pixels, demonstrating the scalability of the proposed approach. These developments open new perspectives for the large scale analysis of remote sensing data. All computer code are available in an open-source package called sentinel. Numéro de notice : A2022-193 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.jag.2022.102675 Date de publication en ligne : 06/01/2022 En ligne : https://doi.org/10.1016/j.jag.2022.102675 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99954 [article]

Multi-species individual tree segmentation and identification based on improved mask R-CNN and UAV imagery in mixed forests / Chong Zhang in Remote sensing, vol 14 n° 4 (February-2 2022)  

Public [article]  inRemote sensing > vol 14 n° 4 (February-2 2022) . - n° 874 Titre : Multi-species individual tree segmentation and identification based on improved mask R-CNN and UAV imagery in mixed forests Type de document : Article/Communication Auteurs : Chong Zhang, Auteur ; Jiawei Zhou, Auteur ; Huiwen Wang, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 874 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] Chine [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] détection de contours [Termes IGN] échantillonnage de données [Termes IGN] entropie [Termes IGN] estimation quantitative [Termes IGN] feuillu [Termes IGN] hauteur des arbres [Termes IGN] image captée par drone [Termes IGN] peuplement mélangé [Termes IGN] Pinophyta [Termes IGN] segmentation d'image Résumé : (auteur) High-resolution UAV imagery paired with a convolutional neural network approach offers significant advantages in accurately measuring forestry ecosystems. Despite numerous studies existing for individual tree crown delineation, species classification, and quantity detection, the comprehensive situation in performing the above tasks simultaneously has rarely been explored, especially in mixed forests. In this study, we propose a new method for individual tree segmentation and identification based on the improved Mask R-CNN. For the optimized network, the fusion type in the feature pyramid network is modified from down-top to top-down to shorten the feature acquisition path among the different levels. Meanwhile, a boundary-weighted loss module is introduced to the cross-entropy loss function Lmask to refine the target loss. All geometric parameters (contour, the center of gravity and area) associated with canopies ultimately are extracted from the mask by a boundary segmentation algorithm. The results showed that F1-score and mAP for coniferous species were higher than 90%, and that of broadleaf species were located between 75%–85.44%. The producer’s accuracy of coniferous forests was distributed between 0.8–0.95 and that of broadleaf ranged in 0.87–0.93; user’s accuracy of coniferous was distributed between 0.81–0.84 and that of broadleaf ranged in 0.71–0.76. The total number of trees predicted was 50,041 for the entire study area, with an overall error of 5.11%. The method under study is compared with other networks including U-net and YOLOv3. Results in this study show that the improved Mask R-CNN has more advantages in broadleaf canopy segmentation and number detection. Numéro de notice : A2022-168 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.3390/rs14040874 Date de publication en ligne : 11/02/2022 En ligne : https://doi.org/10.3390/rs14040874 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99793 [article]

Domain adaptation for urban scene segmentation / Antoine Saporta (2022)  

Permalink

Exploring data fusion for multi-object detection for intelligent transportation systems using deep learning / Amira Mimouna (2022)  

Permalink

Towards expressive graph neural networks : Theory, algorithms, and applications / Georgios Dasoulas (2022)  

Permalink

Evaluation of watershed soil erosion hazard using combination weight and GIS: a case study from eroded soil in Southern China / Shifa Chen in Natural Hazards, vol 109 n° 2 (November 2021)  

Permalink

Unsupervised band selection of hyperspectral data based on mutual information derived from weighted cluster entropy for snow classification / Divyesh Varade in Geocarto international, vol 36 n° 15 ([15/08/2021])  

Permalink

SemiCDNet: A semisupervised convolutional neural network for change detection in high resolution remote-sensing images / Daifeng Peng in IEEE Transactions on geoscience and remote sensing, Vol 59 n° 7 (July 2021)  

Permalink

Using information entropy and a multi-layer neural network with trajectory data to identify transportation modes / Qingying Yu in International journal of geographical information science IJGIS, vol 35 n° 7 (July 2021)  

Permalink

Domain adaptive transfer attack-based segmentation networks for building extraction from aerial images / Younghwan Na in IEEE Transactions on geoscience and remote sensing, vol 59 n° 6 (June 2021)  

Permalink

Extraction of sea ice cover by Sentinel-1 SAR based on support vector machine with unsupervised generation of training data / Xiao-Ming Li in IEEE Transactions on geoscience and remote sensing, vol 59 n° 4 (April 2021)  

Permalink

Correntropy-based spatial-spectral robust sparsity-regularized hyperspectral unmixing / Xiaorun Li in IEEE Transactions on geoscience and remote sensing, vol 59 n° 2 (February 2021)  

Permalink