Change Detection is one of the most popular topics in the field of Multi-temporal Remote Sensing (RS)
applications. In this paper, a novel approach was introduced for the change detection of the urban area. This
approach adopts the Dempster-Shafer(D-S) algorithm for feature fusion of the multi-temporal RS images. It, in
the first place,,constructs difference images of pixel and context respectively. These two difference images
present the features of changes in different scales. The pixel difference image is obtained by fusing the results
of the subtraction operation and the division operation, while the context difference image is obtained by the
image context. Secondly, by using the difference images, two evidences could be constructed. These
evidences are not certain, but they can give more reliable combination result if considering the average support
of the evidence to different subsets in the assignment framework. And based on these evidences, the
criterion function could be established by the D-S theory. At last, an improved D-S algorithm is applied to fuse
the two different features for detecting the change information of the RS images. An experiment, using the
SPOT and TM images of Wuhan urban area, has compared the accuracy of edge detection by using the new
fusion algorithm and the existent ones. The result shows that the method of improved D-S is solid and
efficacious, which has preferable value in remote sensing applications.
|