Post-processing method of remote sensing image change detection based on multi-scale segmentation-maximum expectation

Abstract

The invention discloses a remote sensing image change detection post-processing method based on multi-scale segmentation-maximum expectation. Step a: perform spatial position registration on the image before the landslide and the image after the landslide in the landslide area, and obtain the changed image by solving; step b: based on After the landslide, perform multi-scale segmentation to obtain its multi-scale segmented image object set S, step c: take the i-th object Oi in S, perform spatial overlay analysis with the initial change detection results in step a, and count the objects Oi separately The number of internal changed pixels and unchanged pixels; Step d: Use the algorithm of maximum expectation to refine the pixel attributes in the object Oi again; Step e: Let j=i+1; if j≤n, then take S For the jth object Oj of , execute step c and step d in sequence until j>n; step f: get the final change detection result. This method has strong universality and obvious effect based on multi-scale segmentation-maximum expectation post-processing method of remote sensing image change detection.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image processing, in particular to a remote sensing image change detection post-processing method based on multi-scale segmentation-maximum expectation. Background technique [0002] Human activities and natural disasters are constantly changing the surface information of the earth, and timely and effective acquisition of information on changes in the earth's surface is of great significance to many aspects such as environmental monitoring, urban management, and disaster emergency response. Although with the rapid development of satellite and aerial remote sensing technology, the time resolution and spatial resolution of images have been greatly improved, making it possible to quickly and effectively obtain information on land cover changes. However, the detection results obtained by traditional change detection methods still have a lot of noise, which greatly reduces the reliability and de...

AI Technical Summary

Problems solved by technology

However, the detection results obtained by the traditional change detection method still have a lot of noise, which greatly reduces the reliability and detection accuracy of the detection results.

Images