Centre de documentation
scientifique

Dépouillements

A relative evaluation of random forests for land cover mapping in an urban area / Di Shi in Photogrammetric Engineering & Remote Sensing, PERS, vol 83 n° 8 (August 2017)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 83 n° 8 (August 2017) . - pp 541 - 552 Titre : A relative evaluation of random forests for land cover mapping in an urban area Type de document : Article/Communication Auteurs : Di Shi, Auteur ; Xiaojun Yang, Auteur Année de publication : 2017 Article en page(s) : pp 541 - 552 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] analyse comparative [Termes IGN] carte d'occupation du sol [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] classification par maximum de vraisemblance [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] objet géographique complexe [Termes IGN] occupation du sol [Termes IGN] Perceptron multicouche [Termes IGN] zone urbaine Résumé : (auteur) Random forests as a novel ensemble learning algorithm have significant potential for land cover mapping in complex areas but have not been sufficiently tested by the remote sensing community relative to some more popular pattern classifiers. In this research, we implemented random forests as a pattern classifier for land cover mapping from a satellite image covering a complex urban area, and evaluated the performance relative to several popular classifiers including Gaussian maximum likelihood (GML), multi-layer-perceptron networks (MLP), and support vector machines (SVM). Each classifier was carefully configured with the parameter settings recommended by recent literature, and identical training data were used in each classification. The accuracy of each classified map was further evaluated using identical reference data. Random forests were slightly more accurate than SVM and MLP but significantly better than GML in the overall map accuracy. Random forests and support vector machines generated almost identical overall map accuracy, but the former produced a smaller standard deviation of categorical accuracies, suggesting its better overall capability in classifying both homogeneous and heterogeneous land cover classes. Random forests have shown its robustness due to the most accurate classification on the whole, relatively balanced performance across all land cover categories, and relatively easier to implement. These findings should help promote the use of random forests for land cover classification in complex areas. Numéro de notice : A2017-435 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/IMAGERIE Nature : Article DOI : 10.14358/PERS.83.8.541 En ligne : https://doi.org/10.14358/PERS.83.8.541 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=86339 [article]

Retrieving grassland canopy water content by considering the information from neighboring pixels / Binbin He in Photogrammetric Engineering & Remote Sensing, PERS, vol 83 n° 8 (August 2017)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 83 n° 8 (August 2017) . - pp 553 - 565 Titre : Retrieving grassland canopy water content by considering the information from neighboring pixels Type de document : Article/Communication Auteurs : Binbin He, Auteur ; Xingwen Quan, Auteur ; Dasong Xu, Auteur ; et al., Auteur Année de publication : 2017 Article en page(s) : pp 553 - 565 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] Chine [Termes IGN] classification barycentrique [Termes IGN] classification pixellaire [Termes IGN] modèle de transfert radiatif [Termes IGN] prairie [Termes IGN] réponse spectrale [Termes IGN] teneur en eau liquide Résumé : (auteur) Accurate and robust retrieval of grassland canopy water content (CWC) using a radiative transfer model (RTM) is generally affected by the ill-posed inversion problem due to the lack of enough available a priori information. To alleviate this problem when inversing the RTM, a two-step inversion method was proposed. The key point of this method was to simultaneously consider the spectral information from neighboring pixels and the spatial dependency among these pixels, with the purpose to win more information from these neighboring pixels. The proposed methodology was then applied to retrieve CWC using the PROSAIL RTM from Landsat-8 OLI data for a plateau grassland in China. The results showed that the estimated CWC using the proposed method (RMSE = 67.31 g m-2 and R2 = 0.81) was better than that from the traditional method (RMSE = 80.11 g m-2 and R2 = 0.78) which only considered the information of single pixel. Numéro de notice : A2017-436 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.14358/PERS.83.8.553 En ligne : https://doi.org/10.14358/PERS.83.8.553 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=86340 [article]

Economics of mapping using small manned and unmanned aerial vehicles / Orrin H. Thomas in Photogrammetric Engineering & Remote Sensing, PERS, vol 83 n° 8 (August 2017)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 83 n° 8 (August 2017) . - pp 581 - 591 Titre : Economics of mapping using small manned and unmanned aerial vehicles Type de document : Article/Communication Auteurs : Orrin H. Thomas, Auteur ; Charlie E. Smith, Auteur ; Benjamin E. Wilkinson, Auteur Année de publication : 2017 Article en page(s) : pp 581 - 591 Note générale : biblographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques [Termes IGN] acquisition d'images [Termes IGN] cartographie [Termes IGN] complètement [Termes IGN] couplage GNSS-INS [Termes IGN] coût [Termes IGN] drone [Termes IGN] photogrammétrie aérienne [Termes IGN] véhicule aérien Résumé : (auteur) Specific professional bids to perform aerial data collection using large manned aerial vehicles (LMAV), small manned aerial vehicles (SMAV), and small unmanned aerial systems (UAS) were used to generate general bid models. From these bid models, it was determined what collection methods were competitive for particular jobs based on the project area, distance from the airport or office, and the modeled bids from competing methods. This approach is followed by a discussion of each platform's limitations and versatility. Results indicate that UAS and SMAV and can compete efficiently on aerial photogrammetric mapping up to at least 1,000 acres when the equipment gets enough usage. It is conjectured that this methodology will exert significant downward pressure on the cost of high-end sensors. Numéro de notice : A2017-437 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.14358/PERS.83.8.581 En ligne : https://doi.org/10.14358/PERS.83.8.581 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=86341 [article]