KEYWORDS: Remote sensing, Wavelet transforms, Neural networks, Coastal modeling, Geography, Information science, Information technology, Current controlled current source
Soft classification methods can be used for mixed-pixel classification on remote sensing imagery by estimating different land cover class fractions of every pixel. However, the spatial distribution and location of these class components within the pixel remain unknown. To map land cover at subpixel scale and increase the spatial resolution of land cover classification maps, in this paper, a prediction model combining wavelet transform and Radial Basis Functions (RBF) neural network, abbreviated as Wavelet-RBFNN, is constructed by predicting high-frequency wavelet coefficients from low-frequency coefficients at the same resolution with RBF network and taking wavelet coefficients at coarser resolution as training samples. According to different land cover class fraction images obtained from mixed-pixel classification, based on the assumption of neighborhood dependence of wavelet coefficients, subpixel mapping on remote sensing imagery can be accomplished through two steps, i.e., prediction of land cover class compositions within subpixels and hard classification. The experimental results obtained with artificial images, QuickBird image and Landsat 7 ETM+ image indicate that the subpixel mapping method proposed in this paper can successfully produce super-resolution land cover classification maps from remote sensing imagery, outperforming cubic B-spline and Kriging interpolation method in visual effect and prediction accuracy. The Wavelet-RBFNN model can also be applied to simulate higher spatial resolution image, and automatically identify and locate land cover targets at the subpixel scales, when the cost and availability of high resolution imagery prohibit its use in many areas of work.
This study couples Laplacian-of-Gaussian filter (LoG) and wavelet multi-scale edge detection approaches to extract the waterlines of Chongming Island from Landsat images. The digital elevation model (DEM) of the Chongming tidal flat is constructed by means of the "waterline method". From multi-temporal images obtained under different tidal conditions, it is possible to build up a set of heighted waterlines within the tidal zone, and gridded DEM is then generated by the Australian National University Digital Elevation Model (ANUDEM) method. The results indicate that the methods proposed by this paper can effectively reproduce the coastal near shore topography of Chongming Island, and the precision of the DEM of Dongtan tidal flat is acceptable.
The research on land use / land cover change (LUCC) can provide an important means to understand the relationship between ecological environmental change and human being's activity. The study area, in this paper, Jintai District and Weibin District, is the suburban area of Baoji City, which is located at the frontier of Western Development in China. To explore the typical pattern of land cover change in western China, the LUCC of the study area from 1988 to 2004 is analyzed, using remote sensing technology. Based on these, Markov model is applied to predict the tendency of the LUCC of this area in the next 16 years, and the results indicate that human being's activity, especially in the western cities, will have an increasingly great influence on the regional ecological environment in the current pattern of land use. Faced with the contradiction between land and people and severe ecological environment, establishing land use regulation indices and spatial optimal designs favorable to ecological environment by setting up general land use planning scientifically is important to satisfy reasonable demand of land with economic development and accelerated urbanization and improve ecological environment in western cities in China.
Geospatial information contains not only spatial information and attribute information, but also the information related with spatial information evolvement. As the development of the instruments and technology to acquire geospatial information, more and more geographical information contains spatial-temporal information, as a result, temporal-GIS(Temporal-Geographic Information System, TGIS for short) comes into being. Temporal-GIS could analyze and solve the spatial evolvement characteristics in geographical phenomenon, and reproduce the spatial-temporal scene of real world. This project is focusing on the dynamic visualization of geospatial data based on temporal-GIS, designing the interpreter arithmetic for geospatial polygon dynamic display, building dynamic display model based on temporal-GIS, subsequently, the model is used to analysis and solve the dynamic evolution characteristics of geographic phenomenon, reproduce the real-world temporal -spatial scenes, predict the developing trend of geo-data with the visualization methods.
KEYWORDS: Geographic information systems, Geography, Detection and tracking algorithms, Data modeling, Visual process modeling, Visualization, Information science, Analytical research, Transform theory, Information technology
The majority of geography features has temporal attribute as well as spatial and other attributes and usually changes with
time while the most of current GIS platforms are lack of the ability of dealing with space-time data. Dynamic display
model advanced in this paper is the display manner which takes time as variable and visualizes the dynamic situation of
geography features following time. The shape and position of geography features in the interim could be interpolated
according to the given features. The features mentioned in this paper are 2-D polygonal shapes which are used to express
area features in GIS. The combination of dynamic display model and GIS enhances the expression and analysis ability of
GIS and provides the new approach to geographical research on temporal dimension.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.