A Method of Remote Sensing Image Change Detection

Abstract

The invention discloses a remote sensing image change detection method, comprising: acquiring two-temporal high-resolution optical remote sensing images X1 and X2; performing image registration on X1 and X2; using the multiple change detection method X1 and X2 to perform radiation normalization Correction; Calculate the change vector magnitude XM and spectral angle information XSA according to X1 and X2 after radiation normalization correction; calculate the optimal segmentation threshold T according to XM by using Bayes principle and maximum expectation algorithm; select pseudo-training according to T and XM Sample area; the combination of XM and XSA is used as the input of kernel FCM, and the kernel FCM is combined with the spatial neighborhood information model to carry out optimal model parameter value selection according to the pseudo-training sample area; according to the selected optimal model parameter value, the kernel FCM is adopted Combining the method of spatial neighborhood information to determine the changing area and non-changing area of ​​optical remote sensing images. The invention is more stable and has higher precision.

Description

technical field [0001] The invention relates to the technical field of remote sensing image change detection, in particular to a remote sensing image change detection method. Background technique [0002] With the continuous accumulation of multi-temporal high-resolution remote sensing data and the successive establishment of spatial databases, how to extract and detect change information from these remote sensing data has become an important research topic in remote sensing science and geographic information science. According to remote sensing images of different time phases in the same area, dynamic information such as cities and environments can be extracted to provide scientific decision-making basis for resource management and planning, environmental protection and other departments. my country's "Twelfth Five-Year Plan" will increase and expand the implementation of high-resolution earth observation projects that have been launched during the "Eleventh Five-Year Plan"...

AI Technical Summary

Problems solved by technology

In this type of technology, the disadvantage of using FCM is that it is only suitable for spherical or ellipsoidal clustering, and is extremely sensitive to noise and its outlier (Outlier)

In addition, only the magnitude of the change vector is used, so that the original multispectral information is not fully mined, not robust enough, and the accuracy is not high

[0004] In response to the above problems, many scholars have tried to solve them by adding different spatial neighborhood constraints to the FCM objective function, but the complexity of the high-resolution image detection environment and the lack of prior information of the target have led to certain limitations in these algorithms. limitations, the accuracy is not high

Images