基于MSRC的遥感影像面向对象分类研究-计算机技术专业论文.docxVIP

万方数据 万方数据 ABSTRACT The Remote sensing image data, with the advantages of large coverage, information of objective truth, low cost and easy access, has been widely applied in various fields. For the transportation sector, using high-resolution remote sensing technology, combined with the existing means of traffic information collection, can provide effective technical means for comprehensive decision service, such as urban traffic monitoring, road network planning and construction, road traffic running state identification, industry management, leadership decision-making et al. However, with the continuous improvement of remote sensing image resolution, feature information extraction technology is lagging behind the development of remote sensing technology and the application of remote sensing technology in the transportation sector is still in its infancy. High resolution remote sensing image, relative to low resolution remote sensing image has more abundant spatial information, texture information and geometric information of ground surface. With the development of remote sensing technology and the increasing resolution of remote sensing images , the image data information extraction and classification technology is facing new problems and challenges. The traditional classification method based on pixel due to its limitation of low classification accuracy has been unable to meet the needs of the development of remote sensing technology, so the object-oriented classification technique emerge as the times require. When the object-oriented classification technology in the processing of remote sensing image, the minimum information extraction unit is no longer a single image element, rather than the spectrum and texture feature similar homogeneous object , so we can make full use of other structures’ information including spectral features, which greatly improves the classification accuracy and efficiency. On the object-based classification technology, ① We use