Centre dedocumentation
scientifique

Improving trajectory estimation using 3D city models and kinematic point clouds / Lucas Lucks in Transactions in GIS, Vol 25 n° 1 (February 2021)  

Public [article]  inTransactions in GIS > Vol 25 n° 1 (February 2021) . - pp 238 - 260 Titre : Improving trajectory estimation using 3D city models and kinematic point clouds Type de document : Article/Communication Auteurs : Lucas Lucks, Auteur ; Lasse Klingbeil, Auteur ; Lutz Plümer, Auteur ; Youness Dehbi, Auteur Année de publication : 2021 Article en page(s) : pp 238 - 260 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Navigation et positionnement [Termes IGN] algorithme ICP [Termes IGN] bruit (théorie du signal) [Termes IGN] centrale inertielle [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] interpolation [Termes IGN] milieu urbain [Termes IGN] modèle 3D de l'espace urbain [Termes IGN] modèle sémantique de données [Termes IGN] navigation autonome [Termes IGN] semis de points Résumé : (Auteur) Accurate and robust positioning of vehicles in urban environments is of high importance for autonomous driving or mobile mapping. In mobile mapping systems, a simultaneous mapping of the environment using laser scanning and an accurate positioning using global navigation satellite systems are targeted. This requirement is often not guaranteed in shadowed cities where global navigation satellite system signals are usually disturbed, weak or even unavailable. We propose a novel approach which incorporates prior knowledge (i.e., a 3D city model of the environment) and improves the trajectory. The recorded point cloud is matched with the semantic city model using a point‐to‐plane iterative closest point method. A pre‐classification step enables an informed sampling of appropriate matching points. Random forest is used as classifier to discriminate between facade and remaining points. Local inconsistencies are tackled by a segmentwise partitioning of the point cloud where an interpolation guarantees a seamless transition between the segments. The general applicability of the method implemented is demonstrated on an inner‐city data set recorded with a mobile mapping system. Numéro de notice : A2021-188 Affiliation des auteurs : non IGN Thématique : IMAGERIE/POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/tgis.12719 Date de publication en ligne : 02/01/2021 En ligne : https://doi.org/10.1111/tgis.12719 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97157 [article]

Counting of grapevine berries in images via semantic segmentation using convolutional neural networks / Laura Zabawa 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 73 - 83 Titre : Counting of grapevine berries in images via semantic segmentation using convolutional neural networks Type de document : Article/Communication Auteurs : Laura Zabawa, Auteur ; Anna Kicherer, Auteur ; Lasse Klingbeil, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 73 - 83 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] apprentissage profond [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] comptage [Termes IGN] échantillon [Termes IGN] extraction de traits caractéristiques [Termes IGN] extraction semi-automatique [Termes IGN] régression [Termes IGN] rendement agricole [Termes IGN] segmentation sémantique [Termes IGN] traitement d'image [Termes IGN] viticulture Résumé : (auteur) The extraction of phenotypic traits is often very time and labour intensive. Especially the investigation in viticulture is restricted to an on-site analysis due to the perennial nature of grapevine. Traditionally skilled experts examine small samples and extrapolate the results to a whole plot. Thereby different grapevine varieties and training systems, e.g. vertical shoot positioning (VSP) and semi minimal pruned hedges (SMPH) pose different challenges. In this paper we present an objective framework based on automatic image analysis which works on two different training systems. The images are collected semi automatic by a camera system which is installed in a modified grape harvester. The system produces overlapping images from the sides of the plants. Our framework uses a convolutional neural network to detect single berries in images by performing a semantic segmentation. Each berry is then counted with a connected component algorithm. We compare our results with the Mask-RCNN, a state-of-the-art network for instance segmentation and with a regression approach for counting. The experiments presented in this paper show that we are able to detect green berries in images despite of different training systems. We achieve an accuracy for the berry detection of 94.0% in the VSP and 85.6% in the SMPH. Numéro de notice : A2020-252 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.04.002 Date de publication en ligne : 22/04/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.04.002 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94996 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2020061	RAB	Revue	Centre de documentation	En réserve 3L	Disponible
081-2020063	DEP-RECP	Revue	LaSTIG	Dépôt en unité	Exclu du prêt
081-2020062	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Accurate georeferencing of TLS point clouds with short GNSS observation durations even under challenging measurement conditions / Florian Zimmermann in Journal of applied geodesy, vol 12 n° 4 (October 2018)  

Public [article]  inJournal of applied geodesy > vol 12 n° 4 (October 2018) . - pp. 289 - 302 Titre : Accurate georeferencing of TLS point clouds with short GNSS observation durations even under challenging measurement conditions Type de document : Article/Communication Auteurs : Florian Zimmermann, Auteur ; Christoph Holst, Auteur ; Lasse Klingbeil, Auteur ; Heiner Kuhlmann, Auteur Année de publication : 2018 Article en page(s) : pp. 289 - 302 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] altitude [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] géoréférencement [Termes IGN] paramètre de temps [Termes IGN] point d'appui [Termes IGN] positionnement par GNSS [Termes IGN] précision des mesures [Termes IGN] semis de points Résumé : (auteur) The accuracy of georeferenced TLS point clouds is directly influenced by site-dependent GNSS effects, deteriorating the accuracy of the ground control point coordinate estimation. Especially under challenging GNSS conditions, this is a crucial problem. One common approach is to minimize these effects by longer observation durations, which in turn increases the effort in time and cost. In this paper, an algorithm is proposed that provides accurate georeferencing results, even under challenging measurement conditions and short observation durations. It iteratively improves the georeferencing accuracy by determining and applying obstruction adaptive elevation masks to the GNSS observations. The algorithm is tested and assessed using the data of a field test. It is demonstrated that after only 5 minutes observation duration, the ground control point coordinates can be estimated with an accuracy of 1 to 2 cm, independent from the GNSS measurement conditions. Initial states of the elevation masks are determined from a point cloud that is georeferenced using coordinates from a single point positioning solution, enhanced by a RAIM-FDE approach. Afterwards, the coordinates are estimated in a weighted least-squares baseline solution and both, the elevation masks and the coordinate estimation, are iteratively improved. Besides the significant reduction of measurement time, the proposed algorithm allows for increasing the amount of ground control points and can be applied to other direct or indirect GNSS-based georeferencing approaches. Numéro de notice : A2018-433 Affiliation des auteurs : non IGN Thématique : IMAGERIE/POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1515/jag-2018-0013 Date de publication en ligne : 29/08/2018 En ligne : https://doi.org/10.1515/jag-2018-0013 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=91000 [article]

Development, calibration and evaluation of a portable and direct georeferenced laser scanning system for kinematic 3D mapping / Erik Heinz in Journal of applied geodesy, vol 9 n° 4 (December 2015)  

Public [article]  inJournal of applied geodesy > vol 9 n° 4 (December 2015) . - pp 227 - 243 Titre : Development, calibration and evaluation of a portable and direct georeferenced laser scanning system for kinematic 3D mapping Type de document : Article/Communication Auteurs : Erik Heinz, Auteur ; Christian Eling, Auteur ; Markus Wieland, Auteur ; Lasse Klingbeil, Auteur ; Heiner Kuhlmann, Auteur Année de publication : 2015 Article en page(s) : pp 227 - 243 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] étalonnage d'instrument [Termes IGN] géoréférencement direct [Termes IGN] semis de points [Termes IGN] système de numérisation mobile [Termes IGN] télémètre laser [Termes IGN] variance Résumé : (auteur) In recent years, kinematic laser scanning has become increasingly popular because it offers many benefits compared to static laser scanning. The advantages include both saving of time in the georeferencing and a more favorable scanning geometry. Often mobile laser scanning systems are installed on wheeled platforms, which may not reach all parts of the object. Hence, there is an interest in the development of portable systems, which remain operational even in inaccessible areas. The development of such a portable laser scanning system is presented in this paper. It consists of a lightweight direct georeferencing unit for the position and attitude determination and a small low-cost 2D laser scanner. This setup provides advantages over existing portable systems that employ heavy and expensive 3D laser scanners in a profiling mode. A special emphasis is placed on the system calibration, i. e. the determination of the transformation between the coordinate frames of the direct georeferencing unit and the 2D laser scanner. To this end, a calibration field is used, which consists of differently orientated georeferenced planar surfaces, leading to estimates for the lever arms and boresight angles with an accuracy of mm and one-tenth of a degree. Finally, point clouds of the mobile laser scanning system are compared with georeferenced point clouds of a high-precision 3D laser scanner. Accordingly, the accuracy of the system is in the order of cm to dm. This is in good agreement with the expected accuracy, which has been derived from the error propagation of previously estimated variance components. Numéro de notice : A2015--011 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1515/jag-2015-0011 En ligne : http://dx.doi.org/ 10.1515/jag-2015-0011 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=80763 [article]

UAV real-time: Data use in a lightweight direct georeferencing system / Christian Eling in GPS world, vol 26 n° 11 (November 2015)  

Public [article]  inGPS world > vol 26 n° 11 (November 2015) . - pp 44 - 55 Titre : UAV real-time: Data use in a lightweight direct georeferencing system Type de document : Article/Communication Auteurs : Christian Eling, Auteur ; Lasse Klingbeil, Auteur ; Markus Wieland, Auteur ; Erik Heinz, Auteur ; Heiner Kuhlmann, Auteur Année de publication : 2015 Article en page(s) : pp 44 - 55 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Acquisition d'image(s) et de donnée(s) [Termes IGN] drone [Termes IGN] géoréférencement direct [Termes IGN] GPS en mode cinématique [Termes IGN] GPS-INS [Termes IGN] magnétomètre [Termes IGN] positionnement cinématique en temps réel [Termes IGN] trajectographie par GPS Résumé : (auteur) Direct georeferencing with onboard sensors is less time-consuming for data processing than indirect georeferencing using ground control points, and can supply real-time navigation capability to a UAV. This is very useful for surveying, precision farming or infrastructure inspection. An onboard system for position and attitude determination of lightweight UAVs weighs 240 grams and produces position accuracies better than 5 centimeters and attitude accuracies better than 1 degree. Numéro de notice : A2015--087 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : sans En ligne : http://gpsworld.com/uav-real-time-data-use-in-a-lightweight-direct-georeferencin [...] Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=84804 [article]