Multi-temporal multi-spectral remote sensing image change detection method and system

Abstract

The invention discloses a multi-temporal multi-spectral remote sensing image change detection method and system. Firstly, the method utilizes non-negative matrix decomposition to fuse the change vector amplitude of the multi-temporal remote sensing image and the spectral angle mapping map of the multi-temporal phase to obtain a new difference image. Then, the FCM algorithm is used to obtain the unitary energy terms of CRF for the difference images. Secondly, according to the neighborhood and difference images, the binary energy terms of CRF are obtained. Finally, the final change detection result is obtained by minimizing the energy of CRF with the cyclic reliability propagation algorithm. The invention can better depict the relationship between neighborhoods of images, and improves the accuracy of change detection. Change detection results are more reliable and more robust.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a multi-temporal multi-spectral remote sensing image change detection method. Background technique [0002] Change detection of remote sensing images is to quantitatively analyze and determine the characteristics and process of surface changes from remote sensing data of different periods. Scholars from various countries have proposed many effective detection algorithms from different angles and applied research. Generally speaking, according to whether training samples are needed in the detection process, change detection can be divided into three categories: unsupervised change detection algorithms, semi-supervised change detection algorithms Detection algorithms and supervised change detection algorithms. Because unsupervised change detection algorithms do not require training samples, and the modeling process does not require prior knowledge, this type of algorithm ...

AI Technical Summary

Problems solved by technology

[0003] On December 16, 2015, the Chinese patent database disclosed a SAR image change detection method based on non-stationary analysis and conditional random field (patent number: 201510526592.5), but the detection method is supervised change detection, which consumes a lot of time in practical applications Labor costs, etc. to construct training samples

Also disclosed in the prior art is a CRF-based unsupervised change detection method [Guo Cao, Xuesong Li & Licun Zhou. Unsupervised change detection in high spatial resolution remote sensing images based on a conditional randomfield model. European Journal of Remote Sensing, 2016, 49 :225-237.], this detection method is applied in the process of multi-spectral multi-temporal remote sensing image detection, which can improve the detection accuracy, but this method does not make full use of multiple difference information of multi-spectral images in the construction of CRF unary energy items, resulting in Degradation of detection performance

Images