期刊名称：Archiwum Fotogrametrii, Kartografii i Teledetekcji
印刷版ISSN：2083-2214
出版年度：2006
卷号：16
语种：English
出版社：Main Board of Association of Polish Surveyors
摘要：Flood protection research requires building mathematic models of flood flows. Hydraulic calculations are carried out on the basis of geometrical description of the valley as well as on surface roughness which depends on a land cover. Currently,geometric description of the modeling area in the form of cross-sections is often replaced with a digital terrain model (DTM). The data which is required to build DTM can be collected with photogrammetry or the airborne laser scanning method. An attempt at using airborne laser scanning data which was made for DTM and digital surface model (DSM) interpolation,for supervised classification of land cover was discussed. The classification was based on feed-forward artificial neural networks. Two cases were investigated: variant I - overall classification using one artificial neural network with 2 hidden layers of 10 neurons and variant II - individual recognition using different networks with one hidden layer of 10 neurons for each class. The feature vector of classified object (per-pixel classification) included: data concerning vegetation height,color aerial photographs,texture features and laser wave intensities. Heights of vegetation were calculated on the basis of DTM and DSM which were created for hydrodynamic modelling. Non-metric aerial photographs were taken by digital camera. After calibration and mosaic they served as sources of information about the lightness of objects. It was also a basis of GLCM (Grey Level Co-occurrence Matrix) texture feature calculations. Ten training fields of 400 m2 were chosen as training vectors. Five of them represented various types of high vegetation. The collected data were visualized and computed numerically. A Kappa (κ) coefficient built on the basis of a confusion matrix was used for the quantitative assessment. The high similarity of the obtained results and reference data was confirmed by the value of the calculated kappa coefficient. Better results were obtained for individual classification (variant II) when the kappa value was 0.86.
其他摘要：Badania nad problematyką zapobiegania powodzi wymagają budowy modeli matematycznych przepływów wezbraniowych. Obliczenia hydrodynamiczne wykonywane są w oparciu o dane charakteryzujące geometrię doliny rzeki oraz opory przepływu,które zaleŜą od pokrycia t
