Centre de documentation
scientifique

Rotation-and-scale-invariant airplane detection in high-resolution satellite images based on deep-Hough-forests / Yongtao Yu in ISPRS Journal of photogrammetry and remote sensing, vol 112 (February 2016)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 112 (February 2016) . - pp 50 – 64 Titre : Rotation-and-scale-invariant airplane detection in high-resolution satellite images based on deep-Hough-forests Type de document : Article/Communication Auteurs : Yongtao Yu, Auteur ; Haiyan Guan, Auteur ; Dawei Zai, Auteur ; Zheng Ji, Auteur Année de publication : 2016 Article en page(s) : pp 50 – 64 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] aéronef [Termes IGN] détection d'objet [Termes IGN] invariant [Termes IGN] Rotation Forest classification [Termes IGN] transformation de Hough Résumé : (auteur) This paper proposes a rotation-and-scale-invariant method for detecting airplanes from high-resolution satellite images. To improve feature representation capability, a multi-layer feature generation model is created to produce high-order feature representations for local image patches through deep learning techniques. To effectively estimate airplane centroids, a Hough forest model is trained to learn mappings from high-order patch features to the probabilities of an airplane being present at specific locations. To handle airplanes with varying orientations, patch orientation is defined and integrated into the Hough forest to augment Hough voting. The scale invariance is achieved by using a set of scale factors embedded in the Hough forest. Quantitative evaluations on the images collected from Google Earth service show that the proposed method achieves a completeness, correctness, quality, and F1-measure of 0.968, 0.972, 0.942, and 0.970, respectively, in detecting airplanes with arbitrary orientations and sizes. Comparative studies also demonstrate that the proposed method outperforms the other three existing methods in accurately and completely detecting airplanes in high-resolution remotely sensed images. Numéro de notice : A2016-139 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2015.04.014 En ligne : https://doi.org/10.1016/j.isprsjprs.2015.04.014 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=80313 [article]

3D visualization of building from Lidar and Ikonos image / Zheng Ji (2002)  

Public Titre : 3D visualization of building from Lidar and Ikonos image Type de document : Article/Communication Auteurs : Zheng Ji, Auteur ; Jianqing Zhang, Auteur Editeur : International Society for Photogrammetry and Remote Sensing ISPRS Année de publication : 2002 Collection : International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, ISSN 1682-1750 num. 34-2 Conférence : ISPRS 2002, Commission 2 symposium, Integrated System for Spatial Data Production, Custodian and Decision Support 20/08/2002 23/08/2002 Xi'an Chine OA ISPRS Archives Importance : 4 p. Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques [Termes IGN] données lidar [Termes IGN] image Ikonos [Termes IGN] impulsion laser [Termes IGN] modèle numérique de surface [Termes IGN] reconstruction 3D du bâti [Termes IGN] superposition d'images [Termes IGN] visualisation 3D Résumé : (Auteur) Laser Scanner can measure the direct distance from the aircraft to the terrain surface by run-time emitting and reflecting laser pulse. DEM can be available with lower costs and sort period than over ways. IKONOS Satellite can get high resolution image. Combining DEM from laser scanning and texture from IKONOS image in the same region can provide a low-cost way to realize 3D-visualization to a certain extent. Registring IKONOS image and LIDAR image is the most important procedure. Two algorithms are adopted in the registration of IKONOS image as texture information and LIDAR image as three-dimensional spatial information. Numéro de notice : C2002-032 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Communication DOI : sans En ligne : https://www.isprs.org/proceedings/XXXIV/part2/paper/036_050.pdf Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=64380