Decision Tree Classification (DTC) is one organizational form of the multi-level recognition system, which changes the
complicated classification into simple categories, and then gradually resolves it. The paper does LULC Decision Tree
Classification research on some areas of Gansu Province in the west of China. With the mid-resolution remote sensing
data as the main data resource, the authors adopt decision-making classification technology method, taking advantage of
its character that it imitates the processing pattern of human judgment and thinking and its fault-tolerant character, and
also build the decision tree LULC classical pattern. The research shows that the methods and techniques can increase the
level of automation and accuracy of LULC information extraction, and better carry out LULC information extraction on
the research areas. The main aspects of the research are as follows: 1. We collected training samples firstly, established a
comprehensive database which is supported by remote sensing and ground data; 2. By utilizing CART system, and
based on multiply sources and time phases remote sensing data and other assistance data, the DTC's technology
effectively combined the unsupervised classification results with the experts' knowledge together. The method and
procedure for distilling the decision tree information were specifically developed. 3. In designing the decision tree, based
on the various object of types classification rules, we established and pruned DTC'S model for the purpose of achieving
effective treatment of subdivision classification, and completed the land use and land cover classification of the research
areas. The accuracy of evaluation showed that the classification accuracy reached upwards 80%.
The high spatial resolution Remote Sensing image has richer information than the low or middle resolution image, such
as structure and texture information. Traditional image classification technology which only uses spectral information of
pixels is not suitable for the high resolution image. In order to make full use of the rich information, object-oriented
thought is introduced into the high resolution information extraction. In contrast to traditional methods, the basic
processing units of object oriented image analysis are image objects, and not single pixels. It could fully integrate
spectral values and spatial information such as: shape, size and contextual relationship. The objective of this study is to
extract kinds of information from QuickBird image of the urban area using the object-oriented information extraction
approaches. Image processing includes geometric correction, HIS fusion, image segmentation and classification using
the integration of fuzzy classification and the nearest neighbor (NN). 84.82% overall accuracy is achieved with this
approach, while only 73.87% is achieved with traditional pixel-based method. It shows that object-oriented approach is
promising in providing detailed and accurate information about the physical structure of urban areas from the high
With the development of technology of remote sensing and computer, the quantity of data and information is increased greatly. After a long-time research, we find that it is impracticable to manage and handle information only using information. Only decision-making system can do it, Decision Tree is an important method in classification of land use and land cover. This paper gives the formation process from building synthetic database to designing decision tree model, knowledge base to provide some forms of data for extracting LUCC information, there are three aspect data include about: 1) grid data such as remote sensing data TM, SPOT, 2) Ground-measured data such as DEM, and 3) thematic Vector data such as land use data and so on. Regularity base consists of all the transformation rules from the source state to the destination of the problem, each dot include at least one rule, the foundation can resolve recognize where change in land area and type. At last, according to the level of complexity of the change of LUCC, it gives two kinds of decision tree models: the classified comparative between single result and the synchronic analysis with multi-temporal images.
(1) The classified comparison between single results. We take the information extracting for ice changes as an example, and the result is very ideal. (2) The synchronic analysis with multi-temporal images. We construct decision tree in Hei bei, the condition include the grey value and the other features such as slope gradient and GIS thematic supported data, the result shows that the biggest change type is that other lands are transferred to the forest. The area precision is excess to 85%, and the sort precision 90%.
Recently, when the ninth and tenth were mined in Feiching city mining area, several mine wells occurred on water invasion. Based on systematic interpretation of TMimages in Fei Cheng mining area, authors find that there are five zones of NS trending lineaments, which nearly distribute in radial in TM images. Image processing can be divided into three types, they are spectrum enhancement, spatial filtering and data fusion, the useful methods in this area are auto-adaptive enhancement, density slicing and K-L transform. With ninth and tenth seam coals mined, three mines of east area have broken out serious accidents of water. Statistical materials and the test of water quality drawing off five limestone indicates water-yielding zone near NS, NNE, and NW trending faults, or near intersection point of its and others. In order to solve the problem, using remote sensing and other techniques, we try to find some influential factors on mine flow. Further analyses, such as, the exploration of geology on earth, and microcosmic from rock slice, the authors find that there are some reasons which lead to water invasion such as geological structure, karsts, index and so on, in which the main reason might be north-south deep fracture which is the pathway of well water's distribution, migration and recharge of mine water. There being more complicate geologic structure in the west of mine area, at last, with RS authors point out important zone of mine water invasion which the prevention-control of hazards from mine water and some measures to avoid water blast in future.
The purpose of the project is to find information of LUCC (land use and land cover change) from 1985 to 2000 interval two periods in study area. Such as Changjiang delta, Shiyanghe drainage, Huanghuaihai district, these results will be provided to build LUCC database in our country next project. The remote sensing main data include ETM+, TM and parts of SPOT, because study area is very extensive, time is short too, it is very important to explore and develop extraction methods of LUCC information.
Through making some experiments, the author finds some methods effectively base on study area as follows:
(1) Methods of change detection efficiently are change identification methods in spectral feature, such as Image Subtraction and Threshold, PCA, Multi-temporal false color composite, bands ratio and so on.
(2) Using ancillary data. Remote sensing allows large area to be monitored quickly, but GIS information provide source of very valuable information, which has great advantages over direct field surveying. Such as DEM, land use special subject information, vegetation cover. The use of these information, and remote sensing can together greatly attain changed information. To build new decision tree improve the efficiently of land use/land cover analyses too.
Through making systematic interpretation of TM images, more and more attentions are paid to North-South trending lineaments in diverse radial, which has the nature of deep fracture. The main application are in follow fields: (1) Establishment of minerogenetic model -- the deep fracture controls not only magmatic intrusion, the distribution of chromium-pyrope and diamond, but also the gold and multi-metal deposit. Thus, this paper gives five kinds of mierogentic models. (2) Exploration of groundwater -- first, at the area lacking of water nearby Zoucheng, it is discovered that plentiful groundwater show a positive correlation with N-S treedig lineaments or with the intersection of two lineaments in North-South and other directions. Second, it is found the terrestrial heat has relation with the fracture, which provides a channel for groundwater. (3) Prevention and harnessment of mine water -- in Fei cheng coal mine, the deep fractures in N-S direction, take disadvantageous part in exploring, in which most of outburst of water occur. The results present a new law for prevention and harnessment water.
The principle of tunnel coupling between single-mode optical fiber and thin-film waveguide and the designing method of the coupler are analyzed for light wave tunneling. A new structure of coupler is proposed, which has advantages of high coupling efficiency, integration and pragmatization.