遥感影像提取数据的后处理技术研究

Research on Post-processing of Remote Sensing Image Data Extraction

遥感信息的自动提取是当今空间信息领域的研究难点和重点,常见的提取方法能在一定程度上实现自动提取,但提取后的空间数据如道路、建筑物,存在着属性信息缺失、质量不高等问题,无法直接用于实际生产。为了解决这个问题,本文对遥感影像提取数据后处理过程进行研究,基于自动提取结果,借鉴制图综合领域中的算子和算法,并根据典型矢量要素的自身特征,制定规则库进行制图综合处理。同时引入OpenStreetMap数据进行多源数据融合,解决提取信息属性不足的问题,最终形成一套适合半自动生产加工的遥感影像数据提取后处理方法。与传统后处理方法相比,本文提出的方法可以大大提高系列比例尺地形图制作速度和自动化水平,提升基础地理信息数据快速生产更新效率。

The automatic extraction of remote sensing information is the research difficulty and focus in the field of spatial information.The usual remote sensing information extraction methodscan achieve automatic extraction of remote sensing information to a certain extent.However,the extracted spatial data,such as road sand buildings,cannot be directly applied to actual production due to problems such as the lack of attribute information and low quality of the original data.In order to solve this problem,this paper studies the post-processing process of remote sensing image data extraction,based on the automatically extracted remote sensing information,draws on relevant operators and algorithms in the field of cartography generalization,and formulates special rules according to the characteristics of typical vector features.At the same time,the introduction of OpenStreetMap data for multi-source data fusion to solve the problem of insufficient information attribute extraction.The article carries out generalization processing of drawing,and finally forms a set of post-processing methods for remote sensing extraction datasuitable for semi-automatic production and processing.Compared with the traditional post-processing method,the method proposed in this paper can greatly improve the production speed and automation level of series scale topographic map production,and improve the efficiency of rapid production and update of basic geographic information data.