Centre de documentation
scientifique

Dépouillements

Texture feature fusion with neighborhood oscillating tabu search for high resolution image classification / L. Zhang in Photogrammetric Engineering & Remote Sensing, PERS, vol 74 n° 3 (March 2008)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 74 n° 3 (March 2008) . - pp 323 - 331 Titre : Texture feature fusion with neighborhood oscillating tabu search for high resolution image classification Type de document : Article/Communication Auteurs : L. Zhang, Auteur ; Y. Zhao, Auteur ; et al., Auteur Année de publication : 2008 Article en page(s) : pp 323 - 331 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse texturale [Termes IGN] champ aléatoire de Markov [Termes IGN] filtrage du bruit [Termes IGN] filtre de Gabor [Termes IGN] image à résolution métrique [Termes IGN] image Brodatz [Termes IGN] image Ikonos [Termes IGN] image Quickbird [Termes IGN] oscillation Résumé : (Auteur) Multi-channel Gabor filters (MGFs) and Markov random fields (MRFs) are two common methods for texture analysis. This paper investigates their integration through a novel algorithm using the neighborhood-oscillating tabu search (NOTS) for high-resolution image classification. The NOTS algorithm fuses the texture features extracted by MGF and MRF. This algorithm has been compared with classical methods such as sequential forward selection, sequential forward floating selection, and oscillating search. Experimental results show that the fused MGF/MRF features have much higher discrimination than pure features, and NOTS outperforms other algorithms with either pure or fused features. The stability and effectiveness of the proposed algorithm have been verified using Brodatz, Ikonos, and QuickBird images. Copyright ASPRS Numéro de notice : A2008-074 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.14358/PERS.74.3.323 En ligne : https://doi.org/10.14358/PERS.74.3.323 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=29069 [article]

Land-cover classification using ASTER: multi-band combinations based on wavelet fusion and SOM neural network / H. Bagan in Photogrammetric Engineering & Remote Sensing, PERS, vol 74 n° 3 (March 2008)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 74 n° 3 (March 2008) . - pp 333 - 342 Titre : Land-cover classification using ASTER: multi-band combinations based on wavelet fusion and SOM neural network Type de document : Article/Communication Auteurs : H. Bagan, Auteur ; Q. Wang, Auteur ; et al., Auteur Année de publication : 2008 Article en page(s) : pp 333 - 342 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] carte de Kohonen [Termes IGN] classification par réseau neuronal [Termes IGN] fusion d'images [Termes IGN] image multibande [Termes IGN] image Terra-ASTER [Termes IGN] occupation du sol [Termes IGN] précision de la classification Résumé : (Auteur) In this study, we developed a land-cover classification methodology using Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) visible near-infrared (VNIR), shortwave infrared (SWIR), and thermal infrared (TIR) band combinations based on wavelet fusion and the selforganizing map (SOM) neural network methods, and compared the classification accuracies of different combinations of ASTER multi-band data. A wavelet fusion concept named ARSIS (Amélioration de la Résolution Spatiale par Injection de Structures) was used to fuse ASTER data in the preprocessing stage. In order to apply the wavelet fusion method to ASTER data, the principal components of ASTER VNIR data were computed. The first principal component was used as the base image for wavelet fusion. In our experiments, the spatial resolution of ASTER VNIR, SWIR, and TIR data was adjusted to the same 15 m. SOM classification accuracy was increased from 83 percent to 93 percent by this fusion, and classification accuracy increased along with the increase of band numbers. Classification accuracy reaches the highest value when all 14 bands are used, but classification accuracy closely approached the highest value when three VNIR bands, three SWIR bands, and two TIR bands were used. A similar tendency was also obtained by the maximum likelihood classification (MLC) method, but the classification accuracies of MLC over all band combinations were considerably obviously lower than those obtained by the SOM method. Copyright ASPRS Numéro de notice : A2008-075 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.14358/PERS.74.3.333 En ligne : https://doi.org/10.14358/PERS.74.3.333 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=29070 [article]

Parametric investigation of the performance of Lidar filters using different surface contexts / S. Seo in Photogrammetric Engineering & Remote Sensing, PERS, vol 74 n° 3 (March 2008)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 74 n° 3 (March 2008) . - pp 343 - 362 Titre : Parametric investigation of the performance of Lidar filters using different surface contexts Type de document : Article/Communication Auteurs : S. Seo, Auteur ; C. O'hara, Auteur Année de publication : 2008 Article en page(s) : pp 343 - 362 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] analyse comparative [Termes IGN] données lidar [Termes IGN] filtrage du signal [Termes IGN] modèle numérique de terrain [Termes IGN] surface du sol Résumé : (Auteur) Lidar technology has provided an accurate and efficient way to obtain digital elevation models. While digital terrain models (DTMs) are essential products for three-dimensional spatial applications, extraction of ground points from a mixture of ground and non-ground points is not straightforward, and interactive classification of massive point data sets is prohibitive. To automate the filtering process, many algorithms have been proposed and demonstrated to produce satisfactory results when applied with suitably tuned parameters. For obtaining quality products using lidar filters, however, not only to figure out their optimal performance, but also to analyze the cause and effect relationships between filtering steps and their effects under variable conditions is important. Hence, this study examined the performance of three popular surface models for lidar data filtering: morphological operations, triangulation, and linear prediction. For the test, consistent setting of parameters was applied across considerably different landscape datasets. The strengths and weaknesses of the test filters were investigated by comparing the metrics of omission and commission errors and volumetric distortions, and by observing resulting DTMs and relevant surface profiles. Copyright ASPRS Numéro de notice : A2008-076 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.14358/PERS.74.3.343 En ligne : https://doi.org/10.14358/PERS.74.3.343 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=29071 [article]