|  |
|
[n° ou bulletin]
[n° ou bulletin]
|  |
Exemplaires(1)
| Code-barres | Cote | Support | Localisation | Section | Disponibilité |
|---|---|---|---|---|---|
| 059-03011 | RAB | Revue | Centre de documentation | En réserve L003 | Disponible |
Dépouillements
Ajouter le résultat dans votre panierExpert system house detection in high spatial resolution: Imagery using size, shape, and context / J.A. Tullis in Geocarto international, vol 18 n° 1 (March - May 2003)
Titre : Expert system house detection in high spatial resolution: Imagery using size, shape, and context Type de document : Article/Communication Auteurs : J.A. Tullis, Auteur ; J.R. Jensen, Auteur Année de publication : 2003 Article en page(s) : pp 5 - 15 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] acquisition de connaissances
[Termes IGN] analyse texturale
[Termes IGN] base de connaissances
[Termes IGN] détection du bâti
[Termes IGN] erreur de classification
[Termes IGN] exploration de données
[Termes IGN] fusion d'images
[Termes IGN] image à résolution métrique
[Termes IGN] image Ikonos
[Termes IGN] image multibande
[Termes IGN] image panchromatique
[Termes IGN] luminance lumineuse
[Termes IGN] Normalized Difference Vegetation Index
[Termes IGN] photo-interprétation assistée par ordinateur
[Termes IGN] système expertRésumé : (Auteur) IKONOS 1 x 1 m panchromatic data fused with 4 X 4 m multispectral data were used for residential house detection in three 1 X 1 km study areas of Columbia, South Carolina. One study area contained houses built in the 1940s, another in the 1970s, and another in the 1990s. An expert system was developed to extract individual houses from the imagery. The system employed a data mining algorithm as the core of an automated knowledge acquisition module. Separate knowledge bases were generated for each study area using training samples and the data mining algorithm in two sequential stages. In the first stage, brightness values and NDVI yielded a knowledge base that was used to locate candidate house pixels. In the second stage, region metrics including size, shape, and a series of context variables were employed. Regions of asphalt roads mistakenly identified by the expert system as houses were removed using road buffers. Also, separate knowledge bases were generated both with and without the use of context variables. Each scenario was compared with a point map of photointerpreted (reference) houses. The photointerpreted database was verified against in situ housing counts. There was a strong increasing trend in both machine and photointerpreter accuracy as housing age decreased, with the highest accuracies (79 88%) in the 1990s study area. Numéro de notice : A2003-098 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106040308542258 En ligne : https://doi.org/10.1080/10106040308542258 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=22394
in Geocarto international > vol 18 n° 1 (March - May 2003) . - pp 5 - 15[article]Exemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 059-03011 RAB Revue Centre de documentation En réserve L003 Disponible
Titre : Application of remote sensing to the urban expansion analysis for Nouakchott, Mauritania Type de document : Article/Communication Auteurs : W. Wu, Auteur ; Marie-Françoise Courel, Auteur ; J. Le Rhun, Auteur Année de publication : 2003 Article en page(s) : pp 17 - 24 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection
[Termes IGN] analyse spatiale
[Termes IGN] croissance urbaine
[Termes IGN] dégradation de l'environnement
[Termes IGN] données démographiques
[Termes IGN] image multitemporelle
[Termes IGN] image SPOT-HRV
[Termes IGN] impact sur l'environnement
[Termes IGN] inondation
[Termes IGN] modélisation spatiale
[Termes IGN] Nouakchott
[Termes IGN] planification urbaine
[Termes IGN] risque naturel
[Termes IGN] urbanisationRésumé : (Auteur) Nouakchott, the capital of Mauritania, has stepped into a rapid urbanisation stage since 1980s, especially in the last decade. The population growth in a narrow corner between the Atlantic Ocean and Sahara Desert, exposed to several risks of natural disasters, has produced an overburden to the infertile land and at the same time led to a degradation of the urban environment and difficulty of life. This research is focused on an urban expansion analysis and flood risk assessment by remote sensing techniques utilising multitemporal SPOT/HRV images and demographic data. Our aims are to understand the factors influencing expansion, evaluate the means of controlling environmental impacts and produce useful references for the future urban planning. The results show that Nouakchott had extended by 36 km2 at an annual growth rate of 5.3% and an average extension rate of 3.6 km2/yr corresponding to a population growth about 380,000 people from 1989 to 1999. Regression analysis suggests that the latter is the main dynamics driving the urban expansion (R' = 0.9873). Furthermore, the littoral depression, a belt in peril of seawater inundation between the coastal sandbar and urban districts, where future urban construction is recommended to avoid, was analysed and three risk degrees graded by spatial modelling. And finally, three inneglected points proposed for consideration in the future urban planning were discussed in this paper. Numéro de notice : A2003-099 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106040308542259 En ligne : https://doi.org/10.1080/10106040308542259 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=22395
in Geocarto international > vol 18 n° 1 (March - May 2003) . - pp 17 - 24[article]Exemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 059-03011 RAB Revue Centre de documentation En réserve L003 Disponible
Titre : The potential of virtual reality technology for analysis of remotely sensed data: a Lidar case study Type de document : Article/Communication Auteurs : T. Warner, Auteur ; M.D. Nellis, Auteur ; T. Brandtberg, Auteur ; J.B. Mc Graw, Auteur ; J.V. Gardner, Auteur Année de publication : 2003 Article en page(s) : pp 25 - 32 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection
[Termes IGN] analyse de données
[Termes IGN] couvert forestier
[Termes IGN] données lidar
[Termes IGN] feuillu
[Termes IGN] forêt tempérée
[Termes IGN] image à haute résolution
[Termes IGN] interactivité
[Termes IGN] interpolation spatiale
[Termes IGN] lissage de données
[Termes IGN] orthophotographie
[Termes IGN] photo-interprétation assistée par ordinateur
[Termes IGN] réalité virtuelle
[Termes IGN] système d'information géographique
[Termes IGN] Virgine Occidentale
[Termes IGN] visualisation 3DRésumé : (Auteur) Although the GIS community has been quick to exploit the advantages of virtual reality (VR) for display and analysis of spatial data, VR does not appear to have been exploited widely for remote sensing data analysis. A case study of high resolution lidar data acquired over a deciduous forest near Morgantown, WV was used to investigate the potential and limitations of current VR software for remote sensing analysis. The functionality within a standard remote sensing software package was found to provide a good overview of interpolated, smoothed lidar data, but was less useful for gridded data that had not been interpolated. With gridded data, it was possible to drape orthophotographs or other images over the lidar data, providing a useful method for investigating relationships between lidar and other data. Alternatively, using a commercial VR package, it was possible to view the original lidar point data, and thus visualize the multiple returns from within the canopy of each tree. The point data were preferable for identification of surfaces within the data cloud, especially the ground surface. For a fully integrated remote sensing VR package, functionality will be needed to link point and interpolated coverages, and also to enhance the interactive selection of data for further statistical analysis, Numéro de notice : A2003-100 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106040308542260 En ligne : https://doi.org/10.1080/10106040308542260 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=22396
in Geocarto international > vol 18 n° 1 (March - May 2003) . - pp 25 - 32[article]Exemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 059-03011 RAB Revue Centre de documentation En réserve L003 Disponible
Titre : A very quick neural network algorithm for cloud detection Type de document : Article/Communication Auteurs : K.R. Al-Rawi, Auteur ; José Luis Casanova, Auteur ; A. Vasileisky, Auteur Année de publication : 2003 Article en page(s) : pp 45 - 50 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection
[Termes IGN] classification par réseau neuronal
[Termes IGN] image NOAA-AVHRR
[Termes IGN] nuage
[Termes IGN] radianceRésumé : (Auteur) A very quick neural network algorithm for cloud detection, based on a neural network, is developed. Cloud detection is speeded up through the use of the Class Assigning Space (CAS). The CAS is a classified Radiance Space (RS), which has been built using the trained neural network. The GAS is used to assign a class for each pixel in the image instead of using the ANN to treat every single pixel. The detection time is approximately one second. Channel 1 and channel 5 of N0AA-AVHRR images have been used. The Supervised ARTII artificial neural network has been employed. The system performance has been tested with different training sets and different input data. Numéro de notice : A2003-101 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106040308542262 En ligne : https://doi.org/10.1080/10106040308542262 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=22397
in Geocarto international > vol 18 n° 1 (March - May 2003) . - pp 45 - 50[article]Exemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 059-03011 RAB Revue Centre de documentation En réserve L003 Disponible
Titre : Remote sensing based detection of minefields Type de document : Article/Communication Auteurs : B.H. Maathuis, Auteur Année de publication : 2003 Article en page(s) : pp 51 - 60 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection
[Termes IGN] armement
[Termes IGN] guerre
[Termes IGN] image à basse résolution
[Termes IGN] image multitemporelle
[Termes IGN] image satellite
[Termes IGN] photographie aérienne
[Termes IGN] risque majeur
[Termes IGN] ZimbabweRésumé : (Auteur) In this article the use of remote sensing techniques to locate minefields over a number of selected areas in Zimbabwe is discussed, representing different types of landmine deployment, climatic zones, natural environments, etc. In order to detect the minefields use is made of indirect indicators as the detail of the images did not allow direct identification of landmines. The work conducted is focussing on the suitability of multitemporal aerial photographs and satellite images for the detection of minefields together with ancillary (conflict) information. Analysis of the images acquired showed that, even at lower spatial resolutions, but through the use of multitemporal images, important minefield related indicators could be identified, providing important information for the mine action process. For validation of the interpretations use was made of a minefield map book that was available for these border minefields. Numéro de notice : A2003-105 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106040308542263 En ligne : https://doi.org/10.1080/10106040308542263 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=22401
in Geocarto international > vol 18 n° 1 (March - May 2003) . - pp 51 - 60[article]Exemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 059-03011 RAB Revue Centre de documentation En réserve L003 Disponible
Titre : Multi-temporal study and detailed photogeological mapping of the Armero debris flow (Colombia), using Landsat TM5 images Type de document : Article/Communication Auteurs : H. Villegas, Auteur Année de publication : 2003 Article en page(s) : pp 67 - 74 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection
[Termes IGN] analyse diachronique
[Termes IGN] cartographie géologique
[Termes IGN] Colombie
[Termes IGN] dommage matériel
[Termes IGN] données géologiques
[Termes IGN] éruption volcanique
[Termes IGN] fusion d'images
[Termes IGN] image à haute résolution
[Termes IGN] image en couleur composée
[Termes IGN] image Landsat-TM
[Termes IGN] magnitude
[Termes IGN] risque naturel
[Termes IGN] sédimentRésumé : (Auteur) On November the 13th of 1985, the City of Armero (Colombia) was destroyed by debris flows generated by a reactivation of the Nevado del Ruiz Volcano. The flows ocurred in at least three principal pulses, as was observed by the disater's survivors. Landsat TM 5 data processing was carried out in subscenes taken before and after the lahar sedimentation. False color composites were generated and combined with the geological information available in order to visualize the magnitude of the catastrophe and the flow characteristics. Taking advantage of Landsat TM 5 images with high spectral resolution, a detailed photogeological mapping of the three principal pulses of the debris flows was carried out. Landsat TM 5 proved to be a powerful complementary source of information for hazard assesment of these catastrophic debris flows. The images were used in addition to groundbased information, and were an easy way to help ordinary people and decision makers understand such hazardous volcanic situations. Numéro de notice : A2003-106 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106040308542265 En ligne : https://doi.org/10.1080/10106040308542265 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=22402
in Geocarto international > vol 18 n° 1 (March - May 2003) . - pp 67 - 74[article]Exemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 059-03011 RAB Revue Centre de documentation En réserve L003 Disponible
