Centre de documentation
scientifique

Half a percent of labels is enough: efficient animal detection in UAV imagery using deep CNNs and active learning / Benjamin Kellenberger in IEEE Transactions on geoscience and remote sensing, vol 57 n° 12 (December 2019)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 57 n° 12 (December 2019) . - pp 9524 - 9533 Titre : Half a percent of labels is enough: efficient animal detection in UAV imagery using deep CNNs and active learning Type de document : Article/Communication Auteurs : Benjamin Kellenberger, Auteur ; Diego Marcos, Auteur ; Sylvain Lobry, Auteur ; Devis Tuia, Auteur Année de publication : 2019 Article en page(s) : pp 9524 - 9533 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse d'image orientée objet [Termes IGN] apprentissage profond [Termes IGN] classification orientée objet [Termes IGN] classification par réseau neuronal [Termes IGN] détection d'objet [Termes IGN] données localisées [Termes IGN] échantillonnage de données [Termes IGN] faune locale [Termes IGN] image captée par drone [Termes IGN] Namibie [Termes IGN] objet mobile [Termes IGN] réalité de terrain [Termes IGN] recensement Résumé : (auteur) We present an Active Learning (AL) strategy for reusing a deep Convolutional Neural Network (CNN)-based object detector on a new data set. This is of particular interest for wildlife conservation: given a set of images acquired with an Unmanned Aerial Vehicle (UAV) and manually labeled ground truth, our goal is to train an animal detector that can be reused for repeated acquisitions, e.g., in follow-up years. Domain shifts between data sets typically prevent such a direct model application. We thus propose to bridge this gap using AL and introduce a new criterion called Transfer Sampling (TS). TS uses Optimal Transport (OT) to find corresponding regions between the source and the target data sets in the space of CNN activations. The CNN scores in the source data set are used to rank the samples according to their likelihood of being animals, and this ranking is transferred to the target data set. Unlike conventional AL criteria that exploit model uncertainty, TS focuses on very confident samples, thus allowing quick retrieval of true positives in the target data set, where positives are typically extremely rare and difficult to find by visual inspection. We extend TS with a new window cropping strategy that further accelerates sample retrieval. Our experiments show that with both strategies combined, less than half a percent of oracle-provided labels are enough to find almost 80% of the animals in challenging sets of UAV images, beating all baselines by a margin. Numéro de notice : A2019-598 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2019.2927393 Date de publication en ligne : 20/08/2019 En ligne : http://doi.org/10.1109/TGRS.2019.2927393 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94592 [article]

Improving the prediction of African savanna vegetation variables using time series of MODIS products / Miriam Tsalyuk in ISPRS Journal of photogrammetry and remote sensing, vol 131 (September 2017)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 131 (September 2017) . - pp 77 - 91 Titre : Improving the prediction of African savanna vegetation variables using time series of MODIS products Type de document : Article/Communication Auteurs : Miriam Tsalyuk, Auteur ; Maggi Kelly, Auteur ; Wayne M. Getz, Auteur Année de publication : 2017 Article en page(s) : pp 77 - 91 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Végétation [Termes IGN] Afrique (géographie physique) [Termes IGN] biomasse forestière [Termes IGN] dégradation de la flore [Termes IGN] Enhanced vegetation index [Termes IGN] image Terra-MODIS [Termes IGN] Leaf Area Index [Termes IGN] Namibie [Termes IGN] Normalized Difference Vegetation Index [Termes IGN] prédiction [Termes IGN] savane [Termes IGN] variation Résumé : (Auteur) African savanna vegetation is subject to extensive degradation as a result of rapid climate and land use change. To better understand these changes detailed assessment of vegetation structure is needed across an extensive spatial scale and at a fine temporal resolution. Applying remote sensing techniques to savanna vegetation is challenging due to sparse cover, high background soil signal, and difficulty to differentiate between spectral signals of bare soil and dry vegetation. In this paper, we attempt to resolve these challenges by analyzing time series of four MODIS Vegetation Products (VPs): Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), Leaf Area Index (LAI), and Fraction of Photosynthetically Active Radiation (FPAR) for Etosha National Park, a semiarid savanna in north-central Namibia. We create models to predict the density, cover, and biomass of the main savanna vegetation forms: grass, shrubs, and trees. To calibrate remote sensing data we developed an extensive and relatively rapid field methodology and measured herbaceous and woody vegetation during both the dry and wet seasons. We compared the efficacy of the four MODIS-derived VPs in predicting vegetation field measured variables. We then compared the optimal time span of VP time series to predict ground-measured vegetation. We found that Multiyear Partial Least Square Regression (PLSR) models were superior to single year or single date models. Our results show that NDVI-based PLSR models yield robust prediction of tree density (R2 = 0.79, relative Root Mean Square Error, rRMSE = 1.9%) and tree cover (R2 = 0.78, rRMSE = 0.3%). EVI provided the best model for shrub density (R2 = 0.82) and shrub cover (R2 = 0.83), but was only marginally superior over models based on other VPs. FPAR was the best predictor of vegetation biomass of trees (R2 = 0.76), shrubs (R2 = 0.83), and grass (R2 = 0.91). Finally, we addressed an enduring challenge in the remote sensing of semiarid vegetation by examining the transferability of predictive models through space and time. Our results show that models created in the wetter part of Etosha could accurately predict trees’ and shrubs’ variables in the drier part of the reserve and vice versa. Moreover, our results demonstrate that models created for vegetation variables in the dry season of 2011 could be successfully applied to predict vegetation in the wet season of 2012. We conclude that extensive field data combined with multiyear time series of MODIS vegetation products can produce robust predictive models for multiple vegetation forms in the African savanna. These methods advance the monitoring of savanna vegetation dynamics and contribute to improved management and conservation of these valuable ecosystems. Numéro de notice : A2017-537 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2017.07.012 En ligne : https://doi.org/10.1016/j.isprsjprs.2017.07.012 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=86575 [article]

Exemplaires(3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2017091	RAB	Revue	Centre de documentation	En réserve L003	Disponible
081-2017093	DEP-EXM	Revue	LASTIG	Dépôt en unité	Exclu du prêt
081-2017092	DEP-EAF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Integration of location information and statistical data : developing the Namibian national spatial data infrastructure / Alex Mudabeti in GIM international, vol 30 n° 4 (April 2016)

Public [article]  inGIM international > vol 30 n° 4 (April 2016) . - pp 29 - 31 Titre : Integration of location information and statistical data : developing the Namibian national spatial data infrastructure Type de document : Article/Communication Auteurs : Alex Mudabeti, Auteur ; Roger Longhorn, Auteur Année de publication : 2016 Article en page(s) : pp 29 - 31 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Infrastructure de données [Termes IGN] données localisées [Termes IGN] données statistiques [Termes IGN] infrastructure nationale des données localisées [Termes IGN] Namibie Résumé : (éditeur) Namibia is establishing its National Spatial Data Infrastructure (NSDI) through the Namibia Statistics Agency (NSA). It has been a deliberate decision by the government of Namibia to marry location information with statistics in order to improve evidence-based development planning and socioeconomic intervention. Numéro de notice : A2016-215 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : sans Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=80682 [article]

Deconstructing the Conservancy Map: Hxaro, N!ore, and Rhizomes in the Kalahari / S. Vermeylen in Cartographica, vol 47 n° 2 (June 2012)  

Public [article]  inCartographica > vol 47 n° 2 (June 2012) . - pp 121 - 134 Titre : Deconstructing the Conservancy Map: Hxaro, N!ore, and Rhizomes in the Kalahari Type de document : Article/Communication Auteurs : S. Vermeylen, Auteur ; G. Davies, Auteur Année de publication : 2012 Article en page(s) : pp 121 - 134 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Cartographie thématique [Termes IGN] approche participative [Termes IGN] colonisation [Termes IGN] ethnographie [Termes IGN] Namibie [Termes IGN] participation du public Résumé : (Auteur) To stand a chance of reclaiming their pre-colonial rights, indigenous peoples often have to deploy the tools and logic of the colonial state. Through a case study of community conservancy in Namibia, we demonstrate that the same holds for the practice of participatory mapping. We engage with J.B. Harley's deconstruction of maps and use our ethnographic data to reveal the silences and lies inherent in the rigid cartographic representations of conservancy maps. The indigenous peoples in our case study are the San, who have been marginalized and displaced from their land. We highlight how these people, once perceived by the colonialists as “rootless,” do have strong relational connections across the landscape. We argue that the practice of counter-mapping, along with its critique, is incomplete without full attention to the silences of the map and the relational rhizomes (across boundaries) of the peoples involved. Numéro de notice : A2012-300 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.3138/carto.47.2.121 En ligne : http://www.utpjournals.press/doi/full/10.3138/carto.47.2.121 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=31746 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
031-2012021	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Digital terrain modelling with 3D visualisation / F. Muyoba in GEO: Geoconnexion international, vol 8 n° 3 (march 2009)

Public [article]  inGEO: Geoconnexion international > vol 8 n° 3 (march 2009) . - pp 26 - 31 Titre : Digital terrain modelling with 3D visualisation Type de document : Article/Communication Auteurs : F. Muyoba, Auteur Année de publication : 2009 Article en page(s) : pp 26 - 31 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique [Termes IGN] écoulement des eaux [Termes IGN] modèle numérique de terrain [Termes IGN] Namibie [Termes IGN] outil d'aide à la décision [Termes IGN] quadrillage [Termes IGN] relief [Termes IGN] visualisation 3D Résumé : (Editeur) Felix Muyoba takes us back to Namibia, demonstrating what 3D visualisation can do for decision makers in government and business. Copyright Geo:Geoconnexion Numéro de notice : A2009-120 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : sans Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=29750 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
062-09031	RAB	Revue	Centre de documentation	En réserve L003	Disponible

N-FindR method versus independent component analysis for lithological identification in hyperspectral imagery / C. Gomez in International Journal of Remote Sensing IJRS, vol 28 n°23-24 (December 2007)  

Permalink

Validation of MERIS Level-2 products in the Baltic Sea, the Namibian coastal area and the Atlantic Ocean / T. Ohde in International Journal of Remote Sensing IJRS, vol 28 n°3-4 (February 2007)  

Permalink

L'affaire du Sud-ouest africain / A. Lejeune (1972)

Permalink