Centre de documentation
scientifique

Robust vehicle detection in aerial images using bag-of-words and orientation aware scanning / Hailing Zhou in IEEE Transactions on geoscience and remote sensing, vol 56 n° 12 (December 2018)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 56 n° 12 (December 2018) . - pp 7074 - 7085 Titre : Robust vehicle detection in aerial images using bag-of-words and orientation aware scanning Type de document : Article/Communication Auteurs : Hailing Zhou, Auteur ; Lei Wei, Auteur ; Chee Peng Lim, Auteur ; et al., Auteur Année de publication : 2018 Article en page(s) : pp 7074 - 7085 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] accentuation d'image [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] détection d'objet [Termes IGN] extraction de traits caractéristiques [Termes IGN] image captée par drone [Termes IGN] méthode robuste [Termes IGN] modèle sac-de-mots [Termes IGN] objet mobile [Termes IGN] PMVS [Termes IGN] SIFT (algorithme) [Termes IGN] transformation de Radon [Termes IGN] véhicule Résumé : (auteur) This paper presents a novel approach to automatically detect and count cars in different aerial images, which can be satellite or unmanned aerial vehicle (UAV) images. Variations in satellite and/or UAV data make it particularly challenging to have a robust method that works properly on a variety of images. A solution based on the bag-of-words (BoW) model is explored in this paper due to its invariance characteristic and highly stable performance in object/scene categorization. Different from categorization tasks, vehicle detection needs to localize the positions of cars in images. To make BoW suitable for this purpose, we extensively improve the methodology in three aspects, namely, by introducing a recently proposed feature representation, i.e., the local steering kernel descriptor, adding spatial structure constraints, and developing an orientation aware scanning mechanism to produce detection with “one-window-one-car” results. Experiments are conducted on various aerial images with large variations, which consist of data from two public databases, e.g., the Overhead Imagery Research Data Set and Vehicle Detection in Aerial Imagery, as well as other satellite and UAV images. The results demonstrate the effectiveness and robustness of the proposed method. Compared with existing techniques, the proposed method is applicable to a wider range of aerial images. Numéro de notice : A2018-555 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2018.2848243 Date de publication en ligne : 17/07/2018 En ligne : http://dx.doi.org/10.1109/TGRS.2018.2848243 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=91654 [article]

Geometry-information-aided efficient radial velocity estimation for moving target imaging and location based on Radon transform / Xuepan Zhang in IEEE Transactions on geoscience and remote sensing, vol 53 n° 2 (February 2015)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 53 n° 2 (February 2015) . - pp 1105 - 1117 Titre : Geometry-information-aided efficient radial velocity estimation for moving target imaging and location based on Radon transform Type de document : Article/Communication Auteurs : Xuepan Zhang, Auteur ; Guisheng Liao, Auteur ; Shengqi Zhu, Auteur ; et al., Auteur Année de publication : 2015 Article en page(s) : pp 1105 - 1117 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes IGN] géométrie [Termes IGN] image radar moirée [Termes IGN] objet mobile [Termes IGN] transformation de Radon [Termes IGN] vitesse radiale Résumé : (Auteur) Real-time radial velocity estimation is a key challenge for moving target imaging and location in current single-antenna synthetic aperture radar (SAR)-ground moving target indication systems. Since the conventional methods suffer from ambiguity, complexity realization, or heavy computation load for fast moving target motion estimation, this paper emphasizes the estimation efficiency by simple realization. An efficient Radon transform (RT) estimation is proposed to estimate the radial velocity of fast moving target by utilizing the geometry information, and much more geometry information is exploited to realize clutter cancellation, noise cancellation, and estimation error minimizing in the RT domain, which is not proposed by the others. With only two to four angles used to calculate rather than search for the radial velocity of moving targets, the proposed methods simplify the conventional range and angle (2-D) searching procedure into several time range (1-D) searching procedure efficiently. The theoretical and experimental analysis provides qualitative and quantitative evaluations into the effectiveness of the proposed methods. In the single-antenna SAR system, the proposed methods can estimate the radial velocity of fast moving target efficiently and accurately in high signal to clutter plus noise ratio scenarios. Numéro de notice : A2015-110 Affiliation des auteurs : non IGN Thématique : IMAGERIE/POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2014.2334322 En ligne : https://doi.org/10.1109/TGRS.2014.2334322 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=75628 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-2015021	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Indoor radon, action level, and choropleth generalization : the political-scientific construction of an environmental risk map / Mark Monmonier (23/06/1997)

Public contenu dans ICC 97 proceedings 18th ICA/ACI International Cartographic Conference, 1. Volume 1 / L. Ottoson (1997) Titre : Indoor radon, action level, and choropleth generalization : the political-scientific construction of an environmental risk map Type de document : Article/Communication Auteurs : Mark Monmonier, Auteur Editeur : Gävle : Swedish Cartographic Society Année de publication : 23/06/1997 Conférence : ICC 1997, 18th international cartographic conference ICA 23/06/1997 27/06/1997 Stockholm Suède OA Proceedings Importance : pp 377 - 384 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Cartographie thématique [Termes IGN] carte choroplèthe [Termes IGN] cartographie des risques [Termes IGN] généralisation cartographique automatisée [Termes IGN] risque environnemental [Termes IGN] transformation de Radon Résumé : (Auteur) In 1993, the U.S. Environmental Protection Agency (EPA) issued a large (68 by 52 cm) threecolor map that assigned each of the nation's 3,141 counties to a category described in the key merely as "Zone I," "Zone 2," or "Zone 3." Titled "EPA Map of Radon Zones," this vaguely labeled map is an exemplar of environmental propaganda. Brilliant red area symbols in Zone I counties warn of average indoor radon concentrations exceeding the EPA's action level of 4 picocuries per liter (pCi/L), whereas orange and yellow announce lower but nonetheless serious levels of 24 and <2 pCi/L throughout the remainder of the country. This paper examines scientific, political, and cartographic issues underlying a flawed and biased map that was neither wholly unreasonable nor fully adequate. Numéro de notice : C1997-059 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Communication Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=65718

The application of Radon transformation for improved analysis of sparsely sampled data / R.H. Hanssen (1993)

Public Titre : The application of Radon transformation for improved analysis of sparsely sampled data : a feasibility study Type de document : Monographie Auteurs : R.H. Hanssen, Auteur Editeur : Delft [Pays-Bas] : Delft University of Technology Année de publication : 1993 Importance : 145 p. Format : 21 x 30 cm Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Statistiques [Termes IGN] analyse de données [Termes IGN] échantillonnage de données [Termes IGN] étude de faisabilité [Termes IGN] méthode des moindres carrés [Termes IGN] transformation de Radon Numéro de notice : 11761 Affiliation des auteurs : non IGN Thématique : MATHEMATIQUE Nature : Monographie Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=54490

Exemplaires(2)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
11761-01	23.60	Livre	Centre de documentation	Mathématiques	Disponible
11761-02	23.60	Livre	Centre de documentation	Mathématiques	Disponible