{"title":"Information extraction from high resolution SAR data for urban scene understanding","authors":"M. Quartulli, M. Datcu","doi":"10.1109/DFUA.2003.1219969","DOIUrl":"https://doi.org/10.1109/DFUA.2003.1219969","url":null,"abstract":"The high complexity and the increased importance of geometry in growing resolution synthetic aperture radar (SAR) data in urban environments poses a limit on the usability of lattice-based scene models. Geometrical models based on marked point processes can be employed to provide better descriptions of the scene. A Gibbs potential based on a hierarchical Bayesian description of the direct model of the acquisition is defined on the process: an a-priori measure of plausibility for the scene takes into account interactions between scene objects, while a Bayesian likelihood term is based on the decomposition of scene objects into basic elements and on their mapping in the data space. Multiple reflections of the radar signals are considered and exploited. The resulting detectability measure is compared to a hypothesis in a likelihood ratio. The resulting posterior potential is optimized by Monte Carlo methods. The resulting algorithm is applied on a diverse set of single submeter resolution SAR intensity images on urban scenes, providing descriptions of the 3-d structure of the imaged urban areas in terms of separate objects.","PeriodicalId":308988,"journal":{"name":"2003 2nd GRSS/ISPRS Joint Workshop on Remote Sensing and Data Fusion over Urban Areas","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131908358","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Tiziana Maci-L, Pierfrancesco Lombardo, Marc Meloni, Absiracf
{"title":"Model-based processing of multifrequency polarimetric SAR images of urban areas","authors":"Tiziana Maci-L, Pierfrancesco Lombardo, Marc Meloni, Absiracf","doi":"10.1109/DFUA.2003.1219955","DOIUrl":"https://doi.org/10.1109/DFUA.2003.1219955","url":null,"abstract":"In this paper, we describe a two-step classification scheme for fully polarimetric SAR images. The classification scheme is composed of the cascade of an optimum segmentation stage, and an ML supervised classifier. Different segmentation schemes are described, specifically designed for mono- or multifrequency images. The classification scheme is applied to a set of fully polarimetric, multifrequency SIR-C images of the town of Pavia, in Northern Italy, considering all the possible pairs of polarimetric channels and the two bands individually and jointly, aiming at identifying the best combination for practical applications. Results show that for urban areas, the best performance is achieved by jointly processing the three polarimetric channels, and the minimum performance degradation is achieved considering the HH and the HV channels.","PeriodicalId":308988,"journal":{"name":"2003 2nd GRSS/ISPRS Joint Workshop on Remote Sensing and Data Fusion over Urban Areas","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115719270","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Automatic classification of land cover with high resolution data of the Rio de Janeiro City Brazil","authors":"L. Rego, B. Koch","doi":"10.1109/DFUA.2003.1219981","DOIUrl":"https://doi.org/10.1109/DFUA.2003.1219981","url":null,"abstract":"The city of Rio de Janeiro, with more than 5 million inhabitants, has two big mountains in its centre with natural Atlantic rain forest. The growth of the city around these two mountains puts pressure on this forest. This endangers the remaining Atlantic forest (one of the most endangered forest types of the world) and also causes landslides and mud flows. The city administration carried out a land-cover forest classification with visual interpretation using merged LANDSAT and SPOT data. This work produced a compatible thematic map in the scale 1:50,000. It took about 36 months of intensive work and high costs to produce these maps. The scale of these maps permit to have a global vision of the land change cover but unfortunately do not correspond with the geographic information system of the city, which works with a scale of 1:10,000. The city searched for options to make this work automatically and quickly to get information for planning and to propose solutions. In order to solve this problem high resolution satellite data and automatic classification of land-cover classes are needed. Consequently, images as IKONOS (multispectral with four bands and 4 meters) need to be used to produce a classification, with a scale corresponding to the GIS of the city. The automatic classification of land-cover classes provides a relatively rapid classification. Pixel based classification with high resolution data show some problems because the level of information in the data produce a lot of incorrect classified pixels. The solution to perform this classification uses the new approach that makes one \"pre-classification\" (classification), which transforms the pixel information in objects as well as the feature in the vector representation.","PeriodicalId":308988,"journal":{"name":"2003 2nd GRSS/ISPRS Joint Workshop on Remote Sensing and Data Fusion over Urban Areas","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114424280","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Fusion of LIDAR data and aerial imagery for automatic reconstruction of building surfaces","authors":"M. Huber, W. Schickler, S. Hinz, A. Baumgartner","doi":"10.1109/DFUA.2003.1219962","DOIUrl":"https://doi.org/10.1109/DFUA.2003.1219962","url":null,"abstract":"An approach for building reconstruction based on fused information extracted from different data sources, namely LIDAR data (light detection and ranging) and aerial imagery, is proposed. The building reconstruction is performed within the scope of a general surface estimation process. This surface estimation aims at generating a DTM including buildings and vegetation removed. The buildings are reconstructed by applying polyhedral models. Thus a large variety of building types can be described with the only limitation, that the roof surface consists of planes.","PeriodicalId":308988,"journal":{"name":"2003 2nd GRSS/ISPRS Joint Workshop on Remote Sensing and Data Fusion over Urban Areas","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116869730","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Ecological evaluation of urban biotope types using airborne hyperspectral HyMap data","authors":"U. Heiden, K. Segl, S. Roessner, H. Kaufmann","doi":"10.1109/DFUA.2003.1219950","DOIUrl":"https://doi.org/10.1109/DFUA.2003.1219950","url":null,"abstract":"Urban biotype mapping is the most important database for ecological urban planning. The mapping contains complex information about the outfit and structure of biotopes in the form of descriptive parameters. However, quantitative parameters are limited to a manual estimation of the five levels of surface sealing. Therefore, municipal authorities are interested in quantitative parameters for an advanced GIS-based evaluation of urban biotopes. In this study airborne hyperspectral HyMap data are analyzed to identify urban surface materials based on their material specific reflectance features. The small urban structures and the high spectral information content of the hyperspectral image data require advanced methods for surface identification. Thus, a combined classification and unmixing approach was applied [S. Roessner et al., 2001]. The resulting dataset includes surface abundances of spectrally different materials and forms the basis for the derivation of quantitative parameters for each biotope, such as the weighted surface sealing and the portion of overbuilt area. Spatial and statistical analyses show that the results represent a contribution towards an improved quantitative evaluation of biotopes. In this way valuable remote sensing based parameters can be integrated into ecological urban planning processes.","PeriodicalId":308988,"journal":{"name":"2003 2nd GRSS/ISPRS Joint Workshop on Remote Sensing and Data Fusion over Urban Areas","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130954295","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"QuickBird high resolution satellite data for urban applications","authors":"Volpe F, Rossi L","doi":"10.1109/DFUA.2003.1219946","DOIUrl":"https://doi.org/10.1109/DFUA.2003.1219946","url":null,"abstract":"The full commercial availability of a very high resolution satellite data has disclosed a large number of new opportunities for the use of the Earth observation data. It is now possible to carry out, with EO data, many applications that in the past were exclusive to airborne and on site surveys. Due to the high geometrical resolution, and the wide area that can be imaged within a single scene, QuickBird data appears as a suitable source of information for a wide range of applications to the urban area.","PeriodicalId":308988,"journal":{"name":"2003 2nd GRSS/ISPRS Joint Workshop on Remote Sensing and Data Fusion over Urban Areas","volume":"32 9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131480149","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Change detection of structures in the earthquake hazard zoning map of Eskisehir City, Turkey, by using satellite images","authors":"H. A. Nefeslioglu, M. Tun, C. Ayday, R. M. Goktan","doi":"10.1109/DFUA.2003.1219982","DOIUrl":"https://doi.org/10.1109/DFUA.2003.1219982","url":null,"abstract":"Geological and geotechnical studies play a key role in the successful planning of urban areas. The importance of these studies gains more importance for countries which are under the threat of natural hazards, such as earthquakes. The _zmit earthquake of 17 August 1999 has shown that the interpretation and analyses of geological and geotechnical data is also important for the planning of the urban areas of Turkey. The city of Eskisehir has also suffered from the _zmit earthquake. Therefore, it was found necessary to conduct such an investigation in the Eskisehir urban area. To achieve this goal, geological and geotechnical studies were started soon after the earthquake. Earthquake is a phenomenon which is related to the amplification of earthquake energy, liquefaction and occurrence of fault zones. Therefore, the studied area was subdivided into four different classes according to their soil types and their convenience for construction purposes. Change detection of these area were then performed by using the satellite images of the years 1987 and 1999, related with the structures occupied in these areas. Finally, an interpretation was made for the whole studied area and structural changes in each class were determined for the analyzed years.","PeriodicalId":308988,"journal":{"name":"2003 2nd GRSS/ISPRS Joint Workshop on Remote Sensing and Data Fusion over Urban Areas","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122012699","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Infrastructure analysis from high resolution SAR and InSAR imagery","authors":"Andrew J. Bennett, David Blacknell","doi":"10.1109/DFUA.2003.1219993","DOIUrl":"https://doi.org/10.1109/DFUA.2003.1219993","url":null,"abstract":"In this paper, we present a methodology for the extraction of building dimensions from high resolution SAR and 3-d (InSAR) imagery. For flat and sloping roof buildings we show how differing imaging geometries produce fundamental limitations on the structural information that may be obtained. The procedure is applied real imagery and initial results are discussed.","PeriodicalId":308988,"journal":{"name":"2003 2nd GRSS/ISPRS Joint Workshop on Remote Sensing and Data Fusion over Urban Areas","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129145556","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Evaluation of the quality of panchromatic/multispectral fusion algorithms performed on images simulating the future Pleiades satellites","authors":"F. Laporterie-Déjean, C. Latry, H. De Boissezon","doi":"10.1109/DFUA.2003.1219965","DOIUrl":"https://doi.org/10.1109/DFUA.2003.1219965","url":null,"abstract":"This paper presents the results of a study led by the CNES (French Space Agency) to compare several panchromatic/multispectral fusion methods. Five fusion methods have been selected and evaluated quantitatively and qualitatively. The quantitative results are obtained through analysis of variance; while fusion is evaluated qualitatively by visual experts. Finally, correlations are sought between the two kinds of evaluations.","PeriodicalId":308988,"journal":{"name":"2003 2nd GRSS/ISPRS Joint Workshop on Remote Sensing and Data Fusion over Urban Areas","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126605471","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Extraction of urban features in Strasbourg, France: comparison of two fusion algorithms for Quickbird MS and pan data","authors":"C. Weber, T. Ranchin, A. Puissant, A. Serradj","doi":"10.1109/DFUA.2003.1219988","DOIUrl":"https://doi.org/10.1109/DFUA.2003.1219988","url":null,"abstract":"Urban areas might be defined as complex and dynamic system that needs specific and reliable products to be observed and managed. Very high resolution (VHR) satellite, such as Quickbird image, provides sub-meter spatial resolution images in the panchromatic mode and multispectral images. Hence, the idea of fusing synthetic multispectral images with a highest spatial resolution, enable the creation of usable products for urban planning and operational purposes. Such kind of techniques provides imagery products that need to be assessed in terms of quality and reliability towards urban practices and purposes. This paper compares quantitatively and qualitatively two fusion methods over the Strasbourg area (France). It defines a more complete set of parameters for the use of fusion in urban areas studies and leads to quality conclusions regarding global and local assessments.","PeriodicalId":308988,"journal":{"name":"2003 2nd GRSS/ISPRS Joint Workshop on Remote Sensing and Data Fusion over Urban Areas","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130418852","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}