Object-based change detection method for high-resolution remote sensing image combining shadow compensation and multi-scale fusion

As an interpreting symbol of remote sensing images,shadow,however,brings about “pseudo changes”,which is one of the main sources leading to error detection in high-resolution remote sensing image change detection.For this issue,an object-based high-resolution remote sensing image change detection method was proposed combining with shadow compensation and multi-scale fusion.In the object orientation detection framework,the shadows in the remote sensing images were extracted.Then multi-scale change detection was conducted with shadow compensation.In the process,an objective function was constructed of mutual scale information minimization to realize the adaptive extraction of scale parameters.Based on this,combined with the shadow compensation factor,a multi-scale decision-level fusion strategy built on D-S theory of evidence was designed,and the levels of change intensity were further divided.The experiments show that the method is effective in solving the error detection problem caused by shadow,significantly improving the precision of change detection.