Centre dedocumentation
scientifique

Vehicle detection of multi-source remote sensing data using active fine-tuning network / Xin Wu in ISPRS Journal of photogrammetry and remote sensing, vol 167 (September 2020)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 167 (September 2020) . - pp 39 - 53 Titre : Vehicle detection of multi-source remote sensing data using active fine-tuning network Type de document : Article/Communication Auteurs : Xin Wu, Auteur ; Wei Li, Auteur ; Danfeng Hong, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 39 - 53 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes descripteurs IGN] Allemagne [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] détection d'objet [Termes descripteurs IGN] données multisources [Termes descripteurs IGN] étiquette [Termes descripteurs IGN] image aérienne [Termes descripteurs IGN] modèle numérique de surface [Termes descripteurs IGN] modèle stéréoscopique [Termes descripteurs IGN] segmentation [Termes descripteurs IGN] segmentation sémantique [Termes descripteurs IGN] véhicule Résumé : (auteur) Vehicle detection in remote sensing images has attracted increasing interest in recent years. However, its detection ability is limited due to lack of well-annotated samples, especially in densely crowded scenes. Furthermore, since a list of remotely sensed data sources is available, efficient exploitation of useful information from multi-source data for better vehicle detection is challenging. To solve the above issues, a multi-source active fine-tuning vehicle detection (Ms-AFt) framework is proposed, which integrates transfer learning, segmentation, and active classification into a unified framework for auto-labeling and detection. The proposed Ms-AFt employs a fine-tuning network to firstly generate a vehicle training set from an unlabeled dataset. To cope with the diversity of vehicle categories, a multi-source based segmentation branch is then designed to construct additional candidate object sets. The separation of high quality vehicles is realized by a designed attentive classifications network. Finally, all three branches are combined to achieve vehicle detection. Extensive experimental results conducted on two open ISPRS benchmark datasets, namely the Vaihingen village and Potsdam city datasets, demonstrate the superiority and effectiveness of the proposed Ms-AFt for vehicle detection. In addition, the generalization ability of Ms-AFt in dense remote sensing scenes is further verified on stereo aerial imagery of a large camping site. Numéro de notice : A2020-546 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.06.016 date de publication en ligne : 13/07/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.06.016 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95772 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2020091	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2020093	DEP-RECP	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2020092	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Modeling soil erosion after mechanized logging operations on steep terrain in the Northern Black Forest, Germany / Julian Haas in European Journal of Forest Research, vol 139 n°4 (August 2020)  

Public [article]  inEuropean Journal of Forest Research > vol 139 n°4 (August 2020) . - pp 549 – 565 Titre : Modeling soil erosion after mechanized logging operations on steep terrain in the Northern Black Forest, Germany Type de document : Article/Communication Auteurs : Julian Haas, Auteur ; Helmer Schack-Kirchner, Auteur ; Friederike Lang, Auteur Année de publication : 2020 Article en page(s) : pp 549 – 565 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes descripteurs IGN] érosion [Termes descripteurs IGN] exploitation forestière [Termes descripteurs IGN] foresterie [Termes descripteurs IGN] Forêt-Noire, massif de la [Termes descripteurs IGN] pente [Termes descripteurs IGN] ruissellement [Termes descripteurs IGN] sédiment [Vedettes matières IGN] Sylviculture Résumé : (auteur) Climate change makes it necessary to re-evaluate the erosion potential of forest infrastructure. We used the Forest Service WEPP interfaces (FS WEPP) to compare soil erosion potentials of two competing logging practices in steep terrain in the Northern Black Forest, Germany: (1) Felling with harvesters and logging with forwarders in slope line with optional traction supporting winches. (2) Felling by chainsaw, logging with a cable winch, and further transport of logs via forest dirt roads. After forest harvest we measured erosion, runoff, and DOC concentration in runoff from 50 m sections of two machine tracks, two cable tracks, and a dirt road for 2 years. The erosion measurements were used to validate FS WEPP management options and a regionally adjusted CLIGEN input file. With these parameterizations we compared the erosion potential of the two practices on subcatchment scale by modeling return periods and total sediment export with FS WEPP. Model results show that logging operations with heavy machinery in slope line are less prone to soil erosion than logging operations including winch logging and additional dirt roads. The former produces less sediment in its worst-case configuration than the latter in its most moderate configuration by a factor of two. Model results also show that erosion prevention benefits from long periods of 10 years between two harvests. Numéro de notice : A2020-426 Thématique : FORET Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s10342-020-01269-5 date de publication en ligne : 11/03/2020 En ligne : https://doi.org/10.1007/s10342-020-01269-5 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95491 [article]

Genetic variation of introduced red oak (Quercus rubra) stands in Germany compared to North American populations / Tim Pettenkofer in European Journal of Forest Research, vol 139 n° 2 (April 2020)  

Public [article]  inEuropean Journal of Forest Research > vol 139 n° 2 (April 2020) . - pp 321 – 331 Titre : Genetic variation of introduced red oak (Quercus rubra) stands in Germany compared to North American populations Type de document : Article/Communication Auteurs : Tim Pettenkofer, Auteur ; Reiner Finkeldey, Auteur ; Markus Müller, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 321 – 331 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes descripteurs IGN] Allemagne [Termes descripteurs IGN] Amérique du nord [Termes descripteurs IGN] analyse comparative [Termes descripteurs IGN] génétique forestière [Termes descripteurs IGN] quercus rubra [Termes descripteurs IGN] variation Résumé : (auteur) Although Northern red oak (Quercus rubra L.) is the most important introduced deciduous tree species in Germany, only little is known about its genetic variation. For the first time, we describe patterns of neutral and potentially adaptive nuclear genetic variation in Northern red oak stands across Germany. For this purpose, 792 trees were genotyped including 611 trees from 12 stands in Germany of unknown origin and 181 trees from four populations within the natural distribution area in North America. Our marker set included 12 potentially adaptive (expressed sequence tag-derived simple sequence repeat = EST SSR) and 8 putatively selectively neutral nuclear microsatellite (nSSR) markers. Our results showed that German stands retain comparatively high levels of genetic variation at both EST-SSRs and nSSRs, but are more similar to each other than to North American populations. These findings are in agreement with earlier chloroplast DNA analyses which suggested that German populations originated from a limited geographic area in North America. The comparison between potentially adaptive and neutral microsatellite markers did not reveal differences in the analyzed diversity and differentiation measures for most markers. However, locus FIR013 was identified as a potential outlier locus. Due to the absence of signatures of selection in German stands, we suggest that introduced populations were established with material from provenances that were adapted to environmental conditions similar to those in Germany. However, we analyzed only a limited number of loci which are unlikely to be representative of adaptive genetic differences among German stands. Our results suggest that the apparent introduction from a limited geographic range in North America may go along with a reduced adaptive potential. Numéro de notice : A2020-345 Thématique : FORET Nature : Article DOI : 10.1007/s10342-019-01256-5 date de publication en ligne : 18/01/2020 En ligne : https://doi.org/10.1007/s10342-019-01256-5 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95225 [article]

Spatio-Temporal Prediction of the Epidemic Spread of Dangerous Pathogens Using Machine Learning Methods / Wolfgang B. Hamer in ISPRS International journal of geo-information, Vol 9 n° 1 (January 2020)  

Public [article]  inISPRS International journal of geo-information > Vol 9 n° 1 (January 2020) Titre : Spatio-Temporal Prediction of the Epidemic Spread of Dangerous Pathogens Using Machine Learning Methods Type de document : Article/Communication Auteurs : Wolfgang B. Hamer, Auteur ; Tim Birr, Auteur ; Joseph-Alexander Verreet, Auteur ; et al., Auteur Année de publication : 2020 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes descripteurs IGN] Allemagne [Termes descripteurs IGN] apprentissage automatique [Termes descripteurs IGN] classification par forêts aléatoires [Termes descripteurs IGN] diffusion spatiale [Termes descripteurs IGN] données localisées [Termes descripteurs IGN] données météorologiques [Termes descripteurs IGN] géostatistique [Termes descripteurs IGN] maladie phytosanitaire [Termes descripteurs IGN] modèle de simulation [Termes descripteurs IGN] modèle dynamique [Termes descripteurs IGN] rendement agricole [Termes descripteurs IGN] risque environnemental [Termes descripteurs IGN] temps réel Résumé : (auteur) Real-time identification of the occurrence of dangerous pathogens is of crucial importance for the rapid execution of countermeasures. For this purpose, spatial and temporal predictions of the spread of such pathogens are indispensable. The R package papros developed by the authors offers an environment in which both spatial and temporal predictions can be made, based on local data using various deterministic, geostatistical regionalisation, and machine learning methods. The approach is presented using the example of a crops infection by fungal pathogens, which can substantially reduce the yield if not treated in good time. The situation is made more difficult by the fact that it is particularly difficult to predict the behaviour of wind-dispersed pathogens, such as powdery mildew (Blumeria graminis f. sp. tritici). To forecast pathogen development and spatial dispersal, a modelling process scheme was developed using the aforementioned R package, which combines regionalisation and machine learning techniques. It enables the prediction of the probability of yield- relevant infestation events for an entire federal state in northern Germany at a daily time scale. To run the models, weather and climate information are required, as is knowledge of the pathogen biology. Once fitted to the pathogen, only weather and climate information are necessary to predict such events, with an overall accuracy of 68% in the case of powdery mildew at a regional scale. Thereby, 91% of the observed powdery mildew events are predicted Numéro de notice : A2020-116 Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/ijgi9010044 date de publication en ligne : 15/01/2020 En ligne : https://doi.org/10.3390/ijgi9010044 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94723 [article]

Knowing is not enough: exploring the missing link between climate change knowledge and action of German forest owners and managers / Yvonne Hengst-Ehrhart in Annals of Forest Science [en ligne], Vol 76 n° 4 (December 2019)  

Public [article]  inAnnals of Forest Science [en ligne] > Vol 76 n° 4 (December 2019) Titre : Knowing is not enough: exploring the missing link between climate change knowledge and action of German forest owners and managers Type de document : Article/Communication Auteurs : Yvonne Hengst-Ehrhart, Auteur Année de publication : 2019 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes descripteurs IGN] Allemagne [Termes descripteurs IGN] foresterie [Termes descripteurs IGN] gestion forestière [Termes descripteurs IGN] industrie forestière [Termes descripteurs IGN] politique forestière [Termes descripteurs IGN] propriétaire forestier [Termes descripteurs IGN] régression multiple [Vedettes matières IGN] Végétation et changement climatique Résumé : (auteur) Key message : Adaptation to climate change is a complex but urgent task in forest management; however, a lack of action is widely reported. This study shows that adaptive action on both stand and business levels is missing in forest management. Beyond the cognitive dimension, affective and conative aspects should be promoted through awareness-raising initiatives specific to different target groups. Context : Adaptation to climate change is a complex but urgent task in forest management. A lack of action is widely reported combined with a call for awareness-raising and better knowledge transfer to bridge the gap between knowledge and action. Aims : Based on an understanding of awareness encompassing cognitive, affective, and conative dimensions, the paper aims to clarify (1) what kind of adaptive measures are missing in forest management and (2) if there is a gap in climate change awareness of forest owners and managers hindering adaptive action. Methods : An online survey among German forest owners and managers was conducted. The theory of planned behavior was selected to examine variables which support the implementation of adaptive measures and to examine different awareness dimensions. Data was analyzed using descriptive statistics and multiple linear regression analysis. Results : Adaptive measures on stand level were more often implemented than those on business level. All awareness dimensions were influential for the intention to implement adaptive measures. Experience and attitude towards adaptive measures were most important while social norm and perceived behavioral control were influential in some groups. Conclusion : The potential of adaptive measures on stand level and particularly on business level is not fully exploited. Based on these findings, awareness-raising initiatives and forest consultancy can be adapted to consider the specific perspectives of target groups as a means of promoting the implementation of adaptive measures. Numéro de notice : A2019-532 Thématique : FORET Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s13595-019-0878-z date de publication en ligne : 16/10/2019 En ligne : https://doi.org/10.1007/s13595-019-0878-z Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94120 [article]

Accurate modelling of canopy traits from seasonal Sentinel-2 imagery based on the vertical distribution of leaf traits / Tawanda W. Gara in ISPRS Journal of photogrammetry and remote sensing, vol 157 (November 2019)  

Permalink

Mapping leaf chlorophyll content from Sentinel-2 and RapidEye data in spruce stands using the invertible forest reflectance model / Roshanak Darvishzadeh in International journal of applied Earth observation and geoinformation, vol 79 (July 2019)  

Permalink

Multiscale cartographic visualization of harmonized datasets / Peter Kunz in International journal of cartography, vol 5 n° 2-3 (July - November 2019)  

Permalink

CNN-based dense image matching for aerial remote sensing images / Shunping Ji in Photogrammetric Engineering & Remote Sensing, PERS, vol 85 n° 6 (June 2019)  

Permalink

Virtual Support Vector Machines with self-learning strategy for classification of multispectral remote sensing imagery / Christian Geiss in ISPRS Journal of photogrammetry and remote sensing, vol 151 (May 2019)  

Permalink

Climate change and mixed forests: how do altered survival probabilities impact economically desirable species proportions of Norway spruce and European beech? / Carola Paul in Annals of Forest Science [en ligne], vol 76 n° 1 (March 2019)  

Permalink

Temporal and spatial high-resolution climate data from 1961 to 2100 for the German National Forest Inventory (NFI) / Helge Dietrich in Annals of Forest Science [en ligne], vol 76 n° 1 (March 2019)  

Permalink

Variation of leaf angle distribution quantified by terrestrial LiDAR in natural European beech forest / Jing Liu in ISPRS Journal of photogrammetry and remote sensing, vol 148 (February 2019)  

Permalink

Forest conversion from Norway spruce to European beech increases species richness and functional structure of aboveground macrofungal communities / Peggy Heine in Forest ecology and management, vol 432 (15 January 2019)  

Permalink

Evaluating the capability of the Sentinel 2 data for soil organic carbon prediction in croplands / Fabio Castaldi in ISPRS Journal of photogrammetry and remote sensing, vol 147 (January 2019)  

Permalink