Change Detection in Urban Areas Based on DSM and Image Features

Abstract

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.