Remote sensing image change detection method and system based on conditional random field

Abstract

The invention discloses a remote sensing image change detection method and system based on a conditional random field. The method comprises the following steps: calculating the change vector amplitudeof a remote sensing image; according to the amplitude of the change vector, using the FCM algorithm to obtain the one-dimensional energy term of CRF; obtaining the binary energy terms of CRF from theneighborhood of each node, spectral angle information and the amplitude of the change vector of the remote sensing image; obtaining the change detection results by minimizing the energy of CRF usingthe cyclic reliability propagation algorithm. The regularization parameters of CRF energy function are selected by the pseudo-training sample set in the detection process, and the corresponding finalchange detection results are obtained under the optimal regularization parameters. The invention can make the result of the change detection more reliable and more robust, and improves the precision of the change detection.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a remote sensing image change detection method and system based on a conditional random field. 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 knowl...

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 and multi-temporal remote sensing image detection, which can improve the detection accuracy, but in the CRF energy function of this method, the regularization parameter is obtained by trial and error, which is not robust Rod

Images