利用面向对象方法监测东北三省水体信息动态变化及驱动力分析

Monitoring the dynamic change of water body information and analyzing its driving force in three northeast provinces based on Object-Oriented method

首先采用几何精校正、图像镶嵌等方法,对东北三省2005—2015年共三期遥感数据进行预处理操作;然后使用面向对象方法进行水体信息提取,并利用监督分类方法和主成分变换融合方法分别对提取出的水体信息进行精度评价及信息融合;最后通过对比多期数据,对2005—2015年东北三省水体信息的动态变化趋势及引起其变化的驱动力进行探讨分析.同时根据精度评价方法得出利用面向对象方法对水体分类提取具有较高的精度和可靠性.

Firstly,three periods of remote sensing data from 2005 to 2015 were preprocessed by geometric precision correction and image mosaic,and then the water information was extracted by Object-Oriented Method. The precision of the extracted water information was evaluated and fused by the supervised classification method and the principal component transform fusion method. Finally,the multi-period data were compared. The dynamic change trend of water information in three provinces of Northeast China from 2005 to 2015 and its driving force were discussed and analyzed. The results showed that the area of water body in the three provinces of Northeast China was decreasing year by year due to the factors of barren vegetation,decreasing precipitation,waste of surface water and industrial water pollution,and the fluctuation was obvious.At the same time,according to the accuracy evaluation method,it was concluded that the Object-Oriented Method had high accuracy and reliability for water body classification and extraction.