Research On Very High-resolution Remote Sensing Image Change Detection Method Based On Markov Model

High-resolution remote sensing image change detection is a technical means to analyze the images of different time periods in the same area to determine whether the ground features in the area have changed.In land survey,urban expansion analysis,resource exploration,ecosystem of monitoring,disaster monitoring and evaluation,and military reconnaissance have been widely used.In recent years,researchers have been researching new change detection algorithms to further improve the accuracy and accuracy of multi-temporal high-resolution remote sensing image change detection.However,at this stage,there is still no versatile algorithm that can be applied to multi-temporal high-resolution remote sensing images in different sensors,different shooting situations,and different shooting environments.In view of the problems and shortcomings of the current change detection algorithm,this paper has completed the following two aspects of research on how to improve the accuracy and accuracy of change detection:(1)For the traditional change detection algorithm,only the band information of the image is utilized,and it is difficult to obtain the defect of the complete change detection result.Based on the spectral information of the image,the change detection method based on Markov random field model introduces the spatial correlation of pixels,which improves the accuracy of change detection to some extent.However,due to the over-use of spatial correlation in the process of introducing pixel spatial information,these methods have the disadvantage of poor detection results due to the fixed weight parameters in the modeling process.Aiming at the limitations of these methods,this paper proposes a high-resolution remote sensing image change detection method based on the variable weight Markov random field combined with the space gravity model.Using the space gravitation model,the use of pixel spatial information is more reasonable,and the idea of variable weight is introduced to improve the defect that the change detection result is too smooth due to the fixed weight parameter.Experiments on real high-resolution remote sensing image datasets verify the effectiveness and feasibility of the proposed method.(2)Existing change detection methods have carried out in-depth analysis and research on pixel spatial information,or have done a lot of work from the perspective of multi-scale image features,and these studies have contributed to the improvement of the accuracy of change detection.However,since the multi-scale features of the pixel spatial information and the image are not well utilized at the same time,the contradiction between the accurate boundary location and the regional homogeneity in the change detection result cannot be well solved.Aiming at the limitations of these methods,this paper proposes a high-resolution remote sensing image change detection method based on multi-scale Markov random field in wavelet domain.Through wavelet transform theory,multi-scale analysis of images is performed to obtain multi-scale features of images.Then,the Markov random field model is used to model the multi-scale features to introduce the spatial information of the pixels,and achieve the purpose of multi-scale features of high-resolution remote sensing images and efficient use of pixel spatial information.By conducting experiments on different types of high-resolution remote sensing images,the accuracy of high-resolution remote sensing image change detection is effectively improved.