Aiming at the problems existing in the current change detection of high-resolution remote sensing images,this paper propo-ses an illegal land use change detection method based on the distribution characteristics of ground objects. In order to improve the ac-curacy and robustness of illegal land use detection,the knowledge of illegal land use discrimination features is added to the change de-tection model,and different change detection methods are used for different image spectral and spatial feature areas. Two groups of high-resolution remote sensing images of a certain place in Hangzhou are selected for the experiment. The results show that compared with the other two methods,this method has higher accuracy in the detection of illegal land,and can quickly locate the suspected ille-gal map spots. Taking this method as an auxiliary to the detection of changes related to illegal land can effectively reduce the manual workload and improve the operation efficiency.
关键词
高分辨率/影像/分布特征/面向对象/改进形态学建筑物指数
Key words
high resolution/images/distribution characteristics/object-oriented/improved morphological building index
维普
万方数据