摘要
随着城市的快速发展,城市的变化也越来越明显。为了能更好地为城市规划人员、城市管理决策人员及时提供信息,有必要对城市的变化发展进行适时地监测。利用大比例尺的航空影像来对城市地区的人工建筑物的变化进行检测,根据城市地区人工建筑物的变化主要反映在高度上的变化这一特点,利用两个不同时期的立体像对,从而生成两个不同时期的数字表面模型(DSM),在此基础上来检测出城市地区人工建筑物的变化区域。由于DSM影像上不仅有人工建筑物的变化反映在高度变化上,而且也有其它如树木等的变化反映在高度变化上。由于检测的目的是了解城市地区内人工建筑物的变化情况,所以利用DSM提出待选变化区域,在待选变化的区域中利用了梯度方向直方图、灰度匹配、及直线特征匹配等方法来针对城市地区人工建筑物的变化进行进一步的分析。利用日本的两个不同时期的1∶1万的航空影像进行了实验,从实验结果来看,所提出的方法是可行的,同时该方法简单、直观且易于操作。
Rapid development of urban makes the data update more often than ever. It's important to detect changes in urban area in timely for the planner and the manager of urban. In this paper, change detection of man\|made objects in urban area from based on stereo image analysis are introduced. \;In this paper, change detection of man\|made objects based on aerial images is introduced. In this paper, we can apply information of the height of man\|made objects to reinforce theirs change detection, and new and old digital surface models (DSMs) are created automatically respectively by image matching firstly. By comparing the new and old DSMs the changed regions are extracted. As we known, there is not only the information of the height of man\|made objects but also the information of the height of others such as trees. However, it's purpose for us to detect changes of man\|made objects in urban area. We further detect the changes of man\|made objects in the potential changes areas by the means of gradient direction histogram, image matching and line\|feature matching. The experiments in this papapebased on the aerial images from Japan have proven that the algorithm is correct, efficient, simple and easy operation.
出处
《遥感技术与应用》
CSCD
2002年第5期240-244,共5页
Remote Sensing Technology and Application
