Détail de l'auteur
Auteur Bharat Lohani |
Documents disponibles écrits par cet auteur (7)
![](./images/expand_all.gif)
![](./images/collapse_all.gif)
![Tris disponibles](./images/orderby_az.gif)
A multi-faceted CNN architecture for automatic classification of mobile LiDAR data and an algorithm to reproduce point cloud samples for enhanced training / Bhavesh Kumar in ISPRS Journal of photogrammetry and remote sensing, vol 147 (January 2019)
![]()
[article]
Titre : A multi-faceted CNN architecture for automatic classification of mobile LiDAR data and an algorithm to reproduce point cloud samples for enhanced training Type de document : Article/Communication Auteurs : Bhavesh Kumar, Auteur ; Gaurav Pandey, Auteur ; Bharat Lohani, Auteur ; Subhas C. Misra, Auteur Année de publication : 2019 Article en page(s) : pp 80 - 89 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie
[Termes IGN] apprentissage profond
[Termes IGN] classification automatique
[Termes IGN] données lidar
[Termes IGN] données localisées 3D
[Termes IGN] échantillonnage
[Termes IGN] image à haute résolution
[Termes IGN] précision de la classification
[Termes IGN] réseau neuronal convolutif
[Termes IGN] semis de pointsRésumé : (auteur) Mobile Laser Scanning (MLS) data of outdoor environment are typically characterised by occlusion, noise, clutter, large data size and high quantum of information which makes their classification a challenging problem. This paper presents three deep Convolutional Neural Network (CNN) architectures in three dimension (3D), namely single CNN (SCN), multi-faceted CNN (MFC) and MFC with reproduction (MFCR) for automatic classification of MLS data. The MFC uses multiple facets of an MLS sample as inputs to different SCNs, thus providing additional information during classification. The MFC, once trained, is used to reproduce additional samples with the help of existing samples. The reproduced samples are employed to further refine the MFC training parameters, thus giving a new method called MFCR. The three architectures are evaluated on an ensemble of 3D outdoor MLS data consisting of four classes, i.e. tree, pole, house and ground covered with low vegetation along with car samples from KITTI dataset. The total accuracy and kappa values of classifications reached up to (i) 86.0% and 81.3% for the SCN (ii) 94.3% and 92.4% for the MFC and (iii) 96.0% and 94.6% for the MFCR, respectively. The paper has demonstrated the use of multiple facets to significantly improve classification accuracy over the SCN. Finally, a unique approach has been developed for reproduction of samples which has shown potential to improve the accuracy of classification. Unlike previous works on the use of CNN for structured point cloud of indoor objects, this work shows the utility of different proposed CNN architectures for classification of varieties of outdoor objects, viz., tree, pole, house and ground which are captured as unstructured point cloud by MLS. Numéro de notice : A2019-034 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2018.11.006 Date de publication en ligne : 20/11/2018 En ligne : https://doi.org/10.1016/j.isprsjprs.2018.11.006 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=91971
in ISPRS Journal of photogrammetry and remote sensing > vol 147 (January 2019) . - pp 80 - 89[article]Exemplaires(3)
Code-barres Cote Support Localisation Section Disponibilité 081-2019011 RAB Revue Centre de documentation En réserve L003 Disponible 081-2019013 DEP-EXM Revue LASTIG Dépôt en unité Exclu du prêt 081-2019012 DEP-EAF Revue Nancy Dépôt en unité Exclu du prêt A study-based ranking of LiDAR data visualization schemes aided by georectified aerial images / Suddasheel Ghosh in Cartography and Geographic Information Science, vol 41 n° 2 (March 2014)
![]()
[article]
Titre : A study-based ranking of LiDAR data visualization schemes aided by georectified aerial images Type de document : Article/Communication Auteurs : Suddasheel Ghosh, Auteur ; Bharat Lohani, Auteur ; Neeraj Misra, Auteur Année de publication : 2014 Article en page(s) : pp 138 - 150 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie
[Termes IGN] données lidar
[Termes IGN] données localisées 3D
[Termes IGN] extraction de traits caractéristiques
[Termes IGN] orthoimage
[Termes IGN] semis de points
[Termes IGN] Triangulated Irregular Network
[Termes IGN] visualisation de donnéesRésumé : (Auteur) Light Detection and Ranging (LiDAR) collects dense 3D topographic information in the form of points. LiDAR data can be displayed either through direct rendering of the point cloud or by generalizing features extracted through classification or segmentation. We are working in the domain of visualizing LiDAR data sets and have developed certain pipelines for visualization. These pipelines have been presented elsewhere. We present a technique for the evaluation of visualization schemes for LiDAR data, by conducting a visualization experience survey for 13 pre-processing and visualization schemes where 60 participants rated these schemes on a 10 point scale on a questionnaire. The paper establishes a ranking for the different visualization schemes described herein. Finally, this paper establishes that our heuristic-based algorithm (presented elsewhere) performs almost equal to a classification-based visualization pipeline made using professional software. We believe that the presented technique can be used to assess other geospatial visualization schemes. Numéro de notice : A2014-207 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1080/15230406.2014.880071 En ligne : https://doi.org/10.1080/15230406.2014.880071 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=33110
in Cartography and Geographic Information Science > vol 41 n° 2 (March 2014) . - pp 138 - 150[article]Exemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 032-2014021 RAB Revue Centre de documentation En réserve L003 Disponible LAS and LASUtility: Lidar data file format freeware / Bharat Lohani in GIM international, vol 23 n° 8 (August 2009)
[article]
Titre : LAS and LASUtility: Lidar data file format freeware Type de document : Article/Communication Auteurs : Bharat Lohani, Auteur ; R.K. Mishra, Auteur Année de publication : 2009 Article en page(s) : pp 13 - 15 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie
[Termes IGN] données lidar
[Termes IGN] format d'échange
[Termes IGN] standardRésumé : (Auteur) Light Detection and Ranging, or Lidar technology has become an industry-standard high-speed tool for collecting dense and accurate topographic data. However, proprietary or ASCII file format for storing Lidar limit the scope of data sharing and result in time-consuming data processing and loss of integrity. Instead, the industry recommends an American Society of Photogrammetry and Remote Sensing standard data exchange format, Lidar Standard or LAS, which requires dedicated processing software. Existing image-processing and GIS software are being updated to include LAS, but so slowly that some users are converting their data from LAS to more convenient formats. We have filled the gap with the free software tool 'LASUtility'. Copyright Reed Business Numéro de notice : A2009-283 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : sans Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=29913
in GIM international > vol 23 n° 8 (August 2009) . - pp 13 - 15[article]Exemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 061-09081 RAB Revue Centre de documentation En réserve L003 Disponible Effect of data density, scan angle, and flying height on the accuracy of building extraction using LiDAR data / Bharat Lohani in Geocarto international, vol 23 n° 2 (April - May 2008)
![]()
[article]
Titre : Effect of data density, scan angle, and flying height on the accuracy of building extraction using LiDAR data Type de document : Article/Communication Auteurs : Bharat Lohani, Auteur ; Ranjit Singh, Auteur Année de publication : 2008 Article en page(s) : pp 81 - 94 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie
[Termes IGN] angle de visée
[Termes IGN] densité des points
[Termes IGN] détection du bâti
[Termes IGN] données lidar
[Termes IGN] hauteur de vol
[Termes IGN] simulation 3D
[Termes IGN] transformation de HoughRésumé : (Auteur) A Hough transform based approach for extraction of buildings using LiDAR data is presented. It is argued that LiDAR data should be smoothed and sparsed prior to Hough transform for better result. Algorithms to realize this are presented. Further, an algorithm which fits a vector model to extracted buildings is outlined. Simulated LiDAR data have been used to investigate the effect of three parameters (data density, flying height, and scan angle) on the quality of buildings extracted. A set of accuracy indices is proposed for this purpose. It is shown that the data density is the most significant parameter affecting the accuracy of building identification. Copyright Taylor & Francis Numéro de notice : A2008-077 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106040701207100 En ligne : https://doi.org/10.1080/10106040701207100 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=29072
in Geocarto international > vol 23 n° 2 (April - May 2008) . - pp 81 - 94[article]Exemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 059-08021 RAB Revue Centre de documentation En réserve L003 Disponible 3D Visualisation of Lidar data: state of the art and proposed system / S. Ghosh in GIM international, vol 21 n° 2 (February 2007)
[article]
Titre : 3D Visualisation of Lidar data: state of the art and proposed system Type de document : Article/Communication Auteurs : S. Ghosh, Auteur ; Bharat Lohani, Auteur Année de publication : 2007 Article en page(s) : pp 15 - 17 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie
[Termes IGN] données lidar
[Termes IGN] entrepôt de données localisées
[Termes IGN] état de l'art
[Termes IGN] photographie aérienne
[Termes IGN] réalité virtuelle
[Termes IGN] Triangulated Irregular Network
[Termes IGN] visualisation 3DRésumé : (Editeur) Over recent years the geo-community has used advances in hardware, software and memory to develop software for visualising remotely sensed data. Its 3D nature and capability for integration with other remotely sensed data at high resolution renders Lidar data ideal for 3D visualisation, particularly in an immersive environment. The authors review the state of the art in (geo-)visualisation techniques and propose a system, effectively an algorithm warehouse for an immersive visualisation interface for Lidar data. Copyright Reed Business Information Numéro de notice : A2007-018 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : sans Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=28384
in GIM international > vol 21 n° 2 (February 2007) . - pp 15 - 17[article]Exemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 061-07021 RAB Revue Centre de documentation En réserve L003 Disponible Extraction of tidal channel networks from aerial photographs alone and combined with laser altimetry / Bharat Lohani in International Journal of Remote Sensing IJRS, vol 27 n°1-2 (January 2006)
PermalinkApplication of airborne scanning laser altimetry to the study of the tidal channel geomorphology / Bharat Lohani in ISPRS Journal of photogrammetry and remote sensing, vol 56 n° 2 (December 2001 - March 2002)
Permalink