SAR Image Change Detection Method Based on Threshold Optimization

Abstract

The invention discloses a synthetic aperture radar SAR image change detection threshold method based on threshold optimization. The method comprises the following steps: (1) inputting a synthetic aperture radar SAR image and a change reference map; (2) carrying out image preprocessing; (3) constructing a difference map; (4) generating an initial threshold; (5) generating a change detection map; (6) calculating the fitness of the initial threshold; (7) generating a current update threshold; (8) calculating the fitness of the current update threshold; (9) judging whether the termination condition is reached or not; (10) generating an optimal threshold; (11) obtaining a change detection map. A model needs not to be established in advance to carry out the hypothetical distribution of the changed pixels and the unchanged pixels in the difference map histogram, a non-integer threshold value can be obtained, and the method can be applied to the monitoring of the change of the ground object before and after the earthquake, the dynamic monitoring of the growth state of the crops, and the like.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a synthetic aperture radar SAR (Synthetic Aperture Radar) image change detection method based on threshold optimization in the technical field of image segmentation and image classification and recognition. This method can quickly detect the change information of the two-time-phase synthetic aperture radar image, and can be applied to the monitoring of ground object changes before and after earthquakes and the dynamic monitoring of crop growth status. Background technique [0002] With the development of remote sensing technology and information technology, change detection based on synthetic aperture radar SAR images has received extensive attention in recent years because the sensor has excellent characteristics such as not being affected by time periods and weather conditions. One of the key technologies, the threshold technology is very important in the field o...

AI Technical Summary

Problems solved by technology

Although this method can better fit the histogram distribution of the difference map and reduce the error rate of change detection, the disadvantage of this method is that it needs to use the Gaussian logarithmic model to curve the histogram curve of the unilateral histogram area. Rate fitting, and the Gaussian logarithmic model cannot fully fit the histogram curve of the difference map histogram, which affects the detection accuracy of SAR image changes

Although this method can reduce the impact of seasonal changes of natural features on the image, the method still has the disadvantage that when using the threshold segmentation method to process the difference map, since the threshold used is an integer, the integer threshold The shortcomings of the division boundary between the changed area and the unchanged area in the segmentation difference map are not accurate enough

Images