Multispectral Image Change Detection Method Based on Generative Adversarial Network

Abstract

The invention discloses a multi-spectral image change detection method based on a generative confrontation network, which solves the problems of low detection accuracy and sensitivity to noise in the prior method. The implementation steps are: 1) setting the structure and objective function of the discriminative classification network D and the generating network G, and the distance coefficient λ between the image generated by the generating network G and the real image; 2) obtaining the difference map of two images in different phases I D ; 3) for I D Divide and obtain the initial change detection result, and according to the result, divide the two different phases into labeled and unlabeled data to form a training set; 4) Use the discriminative classification network D and the generation network G to form a classification network W, and use The training set is trained on it, and the trained discriminant classification network D' is obtained; 5) Two different phase images are input into the discriminative classification network D' to obtain the final change detection result. The invention has the advantages of high detection accuracy and strong robustness, and can be applied to image understanding or pattern recognition.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a method for detecting changes in image multispectral images, which can be used for pattern recognition or target detection. Background technique [0002] Image change detection is a technique that can identify areas of change between images of the same region at different times. With the rapid development of remote sensing technology, multispectral images with high resolution have become easy to obtain. Change detection in high-resolution multispectral images has been given more attention. [0003] At present, the multispectral image change detection method widely used in disaster assessment, video detection and other fields is based on the method of image difference map, which can be divided into three steps: 1. Preprocessing the multispectral images in different phases, Mainly including noise removal and registration; 2. Generate difference maps of multi...

AI Technical Summary

Problems solved by technology

However, most of these methods deal with SAR images, and high-resolution multispectral images have more spectral channels. When this method is applied to high-resolution multispectral images, the detection accuracy is low, and the detection results contain many noise problem

Images