Centre dedocumentation
scientifique

MS-RRFSegNetMultiscale regional relation feature segmentation network for semantic segmentation of urban scene point clouds / Haifeng Luo in IEEE Transactions on geoscience and remote sensing, Vol 58 n° 12 (December 2020)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > Vol 58 n° 12 (December 2020) . - pp 8301 - 8315 Titre : MS-RRFSegNetMultiscale regional relation feature segmentation network for semantic segmentation of urban scene point clouds Type de document : Article/Communication Auteurs : Haifeng Luo, Auteur ; Chongcheng Chen, Auteur ; Lina Fang, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 8301 - 8315 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] cognition [Termes descripteurs IGN] données lidar [Termes descripteurs IGN] extraction de traits caractéristiques [Termes descripteurs IGN] représentation multiple [Termes descripteurs IGN] scène urbaine [Termes descripteurs IGN] segmentation sémantique [Termes descripteurs IGN] semis de points Résumé : (auteur) Semantic segmentation is one of the fundamental tasks in understanding and applying urban scene point clouds. Recently, deep learning has been introduced to the field of point cloud processing. However, compared to images that are characterized by their regular data structure, a point cloud is a set of unordered points, which makes semantic segmentation a challenge. Consequently, the existing deep learning methods for semantic segmentation of point cloud achieve less success than those applied to images. In this article, we propose a novel method for urban scene point cloud semantic segmentation using deep learning. First, we use homogeneous supervoxels to reorganize raw point clouds to effectively reduce the computational complexity and improve the nonuniform distribution. Then, we use supervoxels as basic processing units, which can further expand receptive fields to obtain more descriptive contexts. Next, a sparse autoencoder (SAE) is presented for feature embedding representations of the supervoxels. Subsequently, we propose a regional relation feature reasoning module (RRFRM) inspired by relation reasoning network and design a multiscale regional relation feature segmentation network (MS-RRFSegNet) based on the RRFRM to semantically label supervoxels. Finally, the supervoxel-level inferences are transformed into point-level fine-grained predictions. The proposed framework is evaluated in two open benchmarks (Paris-Lille-3D and Semantic3D). The evaluation results show that the proposed method achieves competitive overall performance and outperforms other related approaches in several object categories. An implementation of our method is available at: https://github.com/HiphonL/MS_RRFSegNet . Numéro de notice : A2020-738 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.2985695 date de publication en ligne : 28/04/2020 En ligne : https://doi.org/10.1109/TGRS.2020.2985695 Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96363 [article]

Active and incremental learning for semantic ALS point cloud segmentation / Yaping Lin in ISPRS Journal of photogrammetry and remote sensing, vol 169 (November 2020)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 169 (November 2020) . - pp 73 - 92 Titre : Active and incremental learning for semantic ALS point cloud segmentation Type de document : Article/Communication Auteurs : Yaping Lin, Auteur ; M. George Vosselman, Auteur ; Yanpeng Cao, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 73 - 92 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] classification dirigée [Termes descripteurs IGN] données lidar [Termes descripteurs IGN] données localisées 3D [Termes descripteurs IGN] entropie [Termes descripteurs IGN] incertitude des données [Termes descripteurs IGN] itération [Termes descripteurs IGN] segmentation sémantique [Termes descripteurs IGN] semis de points Résumé : (auteur) Supervised training of a deep neural network for semantic segmentation of point clouds requires a large amount of labelled data. Nowadays, it is easy to acquire a huge number of points with high density in large-scale areas using current LiDAR and photogrammetric techniques. However it is extremely time-consuming to manually label point clouds for model training. In this paper, we propose an active and incremental learning strategy to iteratively query informative point cloud data for manual annotation and the model is continuously trained to adapt to the newly labelled samples in each iteration. We evaluate the data informativeness step by step and effectively and incrementally enrich the model knowledge. The data informativeness is estimated by two data dependent uncertainty metrics (point entropy and segment entropy) and one model dependent metric (mutual information). The proposed methods are tested on two datasets. The results indicate the proposed uncertainty metrics can enrich current model knowledge by selecting informative samples, such as considering points with difficult class labels and choosing target objects with various geometries in the labelled training pool. Compared to random selection, our metrics provide valuable information to significantly reduce the labelled training samples. In contrast with training from scratch, the incremental fine-tuning strategy significantly save the training time. Numéro de notice : A2020-638 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.09.003 date de publication en ligne : 14/09/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.09.003 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96061 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2020111	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2020113	DEP-RECP	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2020112	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Building change detection using a shape context similarity model for LiDAR data / Xuzhe Lyu in ISPRS International journal of geo-information, vol 9 n° 11 (November 2020)  

Public [article]  inISPRS International journal of geo-information > vol 9 n° 11 (November 2020) . - n° 678 Titre : Building change detection using a shape context similarity model for LiDAR data Type de document : Article/Communication Auteurs : Xuzhe Lyu, Auteur ; Ming Hao, Auteur ; Wenzhong Shi, Auteur Année de publication : 2020 Article en page(s) : n° 678 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes descripteurs IGN] analyse d'image orientée objet [Termes descripteurs IGN] détection de changement [Termes descripteurs IGN] détection du bâti [Termes descripteurs IGN] données lidar [Termes descripteurs IGN] fusion d'images [Termes descripteurs IGN] modèle numérique de surface [Termes descripteurs IGN] reconnaissance de formes [Termes descripteurs IGN] segmentation d'image [Termes descripteurs IGN] semis de points Résumé : (auteur) In this paper, a novel building change detection approach is proposed using statistical region merging (SRM) and a shape context similarity model for Light Detection and Ranging (LiDAR) data. First, digital surface models (DSMs) are generated from LiDAR acquired at two different epochs, and the difference data D-DSM is created by difference processing. Second, to reduce the noise and registration error of the pixel-based method, the SRM algorithm is applied to segment the D-DSM, and multi-scale segmentation results are obtained under different scale values. Then, the shape context similarity model is used to calculate the shape similarity between the segmented objects and the buildings. Finally, the refined building change map is produced by the k-means clustering method based on shape context similarity and area-to-length ratio. The experimental results indicated that the proposed method could effectively improve the accuracy of building change detection compared with some popular change detection methods. Numéro de notice : A2020-732 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/ijgi9110678 date de publication en ligne : 15/11/2020 En ligne : https://doi.org/10.3390/ijgi9110678 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96345 [article]

Effects of radiometric correction on cover type and spatial resolution for modeling plot level forest attributes using multispectral airborne LiDAR data / Wai Yeung Yan in ISPRS Journal of photogrammetry and remote sensing, vol 169 (November 2020)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 169 (November 2020) . - pp 152 - 165 Titre : Effects of radiometric correction on cover type and spatial resolution for modeling plot level forest attributes using multispectral airborne LiDAR data Type de document : Article/Communication Auteurs : Wai Yeung Yan, Auteur ; Karin Y. Van Ewijk, Auteur ; Paul M. Treitz, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 152 - 165 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes descripteurs IGN] artefact [Termes descripteurs IGN] classification par forêts aléatoires [Termes descripteurs IGN] correction d'image [Termes descripteurs IGN] correction radiométrique [Termes descripteurs IGN] couvert forestier [Termes descripteurs IGN] délignage [Termes descripteurs IGN] données lidar [Termes descripteurs IGN] données localisées 3D [Termes descripteurs IGN] forêt tempérée [Termes descripteurs IGN] intensité lumineuse [Termes descripteurs IGN] inventaire forestier (techniques et méthodes) [Termes descripteurs IGN] Ontario [Termes descripteurs IGN] peuplement mélangé [Termes descripteurs IGN] restauration d'image [Termes descripteurs IGN] semis de points Résumé : (auteur) In order to use the airborne LiDAR intensity in conjunction with the height-derived information for forest modeling and classification purposes, radiometric correction is deemed to be a critical pre-processing requirement. In this study, we implemented a LiDAR scan line correction (LSLC) and an overlap-driven intensity correction (OIC) to remove the stripe artifacts that appeared within the individual flight lines and overlapping regions of adjacent flight lines of a multispectral LiDAR dataset. We tested the effectiveness of these corrections in various land/forest cover types in a temperate mixed mature forest in Ontario, Canada. Subsequently, we predicted three plot level forest attributes, i.e., basal area (BA), quadratic mean diameter (QMD), and trees per hectare (TPH), using different combinations of height and intensity metrics derived from the multispectral LiDAR data to determine if LiDAR intensity data (corrected and uncorrected) improved predictions over models that utilize LiDAR height-derived information only. The results show that LSLC can reduce the intensity banding effect by 0.19–23.06% in channel 1 (1550 nm) and 4.79–66.87% in channel 2 (1064 nm) at the close-to-nadir region. The combined effect of LSLC and OIC is notable particularly at the swath edges. After implementing both methods, the intensity homogeneity is improved by 5.51–12% in channel 1, 6.37–42.93% in channel 2, and 6.48–33.77% in channel 3 (532 nm). Our results further demonstrate that BA and QMD predictions in our study area gained little from additional LiDAR intensity metrics. Intensity metrics from multiple LiDAR channels and intensity normalized difference vegetation index (NDVI) metrics did improve TPH predictions up to 7.2% in RMSE and 1.8% in Bias. However, our lowest TPH prediction errors (%RMSE) were still approximately 10% larger than for BA and QMD. We observed only minimal differences in plot level BA, QMD, and TPH predictions between models using original and corrected intensity. We attribute this to: (i) the lower effectiveness of radiometric correction in forest versus grassland, bare soil and road land cover types, and (ii) the effect of spatial resolution on intensity noise. Numéro de notice : A2020-640 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.09.001 date de publication en ligne : 22/09/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.09.001 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96063 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2020111	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2020113	DEP-RECP	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2020112	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Indoor point cloud segmentation using iterative Gaussian mapping and improved model fitting / Bufan Zhao in IEEE Transactions on geoscience and remote sensing, vol 58 n° 11 (November 2020)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 58 n° 11 (November 2020) . - pp 7890 - 7907 Titre : Indoor point cloud segmentation using iterative Gaussian mapping and improved model fitting Type de document : Article/Communication Auteurs : Bufan Zhao, Auteur ; Xianghong Hua, Auteur ; Kegen Yu, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 7890 - 7907 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes descripteurs IGN] classification par maximum de vraisemblance [Termes descripteurs IGN] données lidar [Termes descripteurs IGN] itération [Termes descripteurs IGN] modélisation 3D [Termes descripteurs IGN] processus gaussien [Termes descripteurs IGN] reconstruction 3D du bâti [Termes descripteurs IGN] regroupement de points [Termes descripteurs IGN] scène intérieure [Termes descripteurs IGN] segmentation [Termes descripteurs IGN] semis de points Résumé : (auteur) Indoor scene segmentation based on 3-D laser point cloud is important for rebuilding and classification, especially for permanent building structure. However, the existing segmentation methods mainly focus on the large-scale planar structures but ignore the other sharp structures and details, which would cause accuracy degradation in scene reconstruction. To handle this issue, an iterative Gaussian mapping-based segmentation strategy has been proposed in this article, which goes from rough segmentation to refined one iteratively to decompose the indoor scene into detectable point cloud clusters layer by layer. An improved model fitting algorithm based on the maximum likelihood estimation sampling consensus (MLESAC) algorithm is proposed for refined segmentation, which is called the Prior-MLESAC algorithm, to deal with the extraction of both vertical and nonvertical planar and cylindrical structures. The experimental results demonstrate that planar and cylindrical structures are segmented more completely by the proposed strategy, and more details of the indoor structure are restored than other existing methods. Numéro de notice : A2020-681 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.2984943 date de publication en ligne : 16/04/2020 En ligne : https://doi.org/10.1109/TGRS.2020.2984943 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96205 [article]

Assessing the effects of thinning on stem growth allocation of individual Scots pine trees / Ninni Saarinen in Forest ecology and management, vol 474 ([15/10/2020])  

Permalink

Comparing features of single and multi-photon lidar in boreal forests / Xiaowei Yu in ISPRS Journal of photogrammetry and remote sensing, vol 168 (October 2020)  

Permalink

Compensation of geometric parameter errors for terrestrial laser scanner by integrating intensity correction / Wanli Liu in IEEE Transactions on geoscience and remote sensing, vol 58 n° 10 (October 2020)  

Permalink

Hierarchical instance recognition of individual roadside trees in environmentally complex urban areas from UAV laser scanning point clouds / Yongjun Wang in ISPRS International journal of geo-information, vol 9 n° 10 (October 2020)  

Permalink

A preliminary exploration of the cooling effect of tree shade in urban landscapes / Qiuyan Yu in International journal of applied Earth observation and geoinformation, vol 92 (October 2020)  

Permalink

See the forest and the trees: Effective machine and deep learning algorithms for wood filtering and tree species classification from terrestrial laser scanning / Zhouxin Xi in ISPRS Journal of photogrammetry and remote sensing, vol 168 (October 2020)  

Permalink

The effect of leaf-on and leaf-off forest canopy conditions on LiDAR derived estimations of forest structural diversity / Sophie Davison in International journal of applied Earth observation and geoinformation, vol 92 (October 2020)  

Permalink

Towards an Optimization of Sample Plot Size and Scanner Position Layout for Terrestrial Laser Scanning in Multi-Scan Mode / Tim Ritter in Forests, vol 11 n° 10 (October 2020)  

Permalink

Tree species classification using structural features derived from terrestrial laser scanning / Louise Terryn in ISPRS Journal of photogrammetry and remote sensing, vol 168 (October 2020)  

Permalink

Weighted spherical sampling of point clouds for forested scenes / Alex Fafard in Photogrammetric Engineering & Remote Sensing, PERS, vol 86 n° 10 (October 2020)  

Permalink