Abstract:
Abstract: The rapid development of RS、GIS, and GPS technology provide a fast and effective means for the dynamic monitoring of land-cover change detection. Many scholars have researched constructing a land-cover change dynamic database with various remote sensing imageries. In conclusion, the main sources to date are abroad remote sensing imagery, while the Chinese HJ-CCD imageries rarely are used in cover-wetlands information extraction. More important, the traditional pixel-based methods which have been universally applied in land-cover/land-use information extraction for many years cannot meet the application need of land-cover/land-use information extraction because it only uses the spectral features of imagery, ignoring other information that the remote sensing imagery carries. The object-oriented technology not only uses spectral features, but also makes full use of texture features、spatial features, spatial relationship, color space, and the band ration of remote sensing imagery. Based on the data of HJ-CCD imagery in 2010, ETM imagery in 2005, and TM imagery in 2000, integrated into RS、GIS, and GPS technology, an object-oriented method was applied to the remote sensing image classification of land-cover/land-use in Hubei province. First, we achieved land-cover/land-use results as the basal map of a database using object-oriented technology in Hubei province in the e-Cognition software. After checking and improving the results, the Similarity Vectors Change Detection Approach was used to compare with the spectral difference the corresponding objects by segmentation from 2000 to 2005, and from 2005 to 2010. We needed to classify the changed area of two change periods, so the Nearest Neighbor Classification Approach belonging to object-oriented technology was applied to extract land-cover/land-use information. This process in the research contained two key steps: choosing samples and optimizing feature space. Optimizing feature space allowed us to get perfect feature extracting object information. All the results in the unchanged area in 2010 were transformed into the sample Nearest Neighbor Classification Approach needed. We used so many samples that the computer could determine the regulation of every class by detailed analysis. Fusing the classification results in the change area and the unchanged area, the land-cover/land-use results all over Hubei province can be completed successfully according to the districts now. We constructed the land-cover change database in Hubei province in the end. The classification accuracy was assessed using error matrixes though wild samples which were obtained from experimental area by GPS. The research showed that, compared with the traditional classification methods, which only consider the spectral characteristics of the targets, an object-oriented international carbon budget certification classification system comprehensively utilizes more detailed information of the remote sensing imagery including spectral characteristics, texture feature, spatial relationship, color space, and band ratio. Thus, it yields a higher accuracy of classification. The object-oriented method extracted the so-called "object," which consists of some homogeneous pixels in the process of classification, and the objects showed a low degree of fragmentation .Therefore, this method significantly reduced the disturbance of salt-and-pepper noise in the classification results and can keep the similarity in shape with the natural objects. The research showed that this process and method using RS, GIS, GPS, object-oriented technology based on TM, ETM and Chinese HJ-CCD imagery for monitoring land-cover change information is fast, efficient, high automation, and accurate. However, we found that object-oriented technology has some disadvantages where landscape fragmentation is high.