High-resolution remote sensing image ground object change detection method based on multi-task learning

Abstract

The invention belongs to the technical field of remote sensing image ground object change detection, and particularly relates to a remote sensing image ground object change detection method based on multi-task learning, which is used for solving the problem of error accumulation caused by the fact that the ground object change detection precision depends on the ground object classification precision in the prior art. A multi-task learning ground object change detection model is adopted and comprises two semantic segmentation model branches and a change detection model branch. A semantic segmentation model is constructed through a segmentation network, a feature extraction module of the model can effectively extract features of a remote sensing image, then a twin network is constructed to train a ground object change detection model, and a multi-task learning mechanism is constructed. In conclusion, the ground object change detection area can be determined, change detection results of different ground objects and ground object types before and after area change can be obtained, meanwhile, the problem of error accumulation is avoided, and the change detection precision is improved.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image feature change detection, and more specifically, relates to a remote sensing image feature change detection based on multi-task learning under the requirement of feature interpretation, which integrates remote sensing image semantic segmentation tasks and ground features. The object change detection task can not only determine the change detection area, but also obtain the change detection results of different ground objects, and detect the change process of the earth's surface objects through remote sensing images of the same geographical area at different times. Background technique [0002] The ground object change detection technology for monitoring specific areas has been widely used in various applications such as land surveying, illegal construction monitoring, and natural disaster estimation, especially for timely detection of illegal construction outside the planning area. Th...

AI Technical Summary

Problems solved by technology

The traditional ground object change detection technology mainly uses the grayscale matching and difference change detection algorithm to perform histogram matching on the remote sensing images of the same area at different times that have undergone ground object registration and geometric correction, so as to ensure the grayscale of the two images. degree of consistency, and then use the difference method to extract areas with drastic changes in gray levels as ground object change areas; this method has the problems of low detection accuracy and is easily affected by external factors such as weather and light, and it also needs to be manually set. Threshold, the results obtained are only two types of results: changed and unchanged, and cannot classify remote sensing images, and cannot obtain change detection images of different ground objects.

[0003] Another common method for detecting changes in ground features is the method of classification first and then comparison. First, superpixel segmentation or pixel-level semantic segmentation is used to classify remote sensing images of the same area at different times, and then two semantic segmentation results are obtained. By pixel-by-pixel comparison, the difference images are constructed for different types of ground objects, and the pixel areas with inconsistent results are considered as changed areas; the advantage of this method is that it can obtain the change detection images of different ground objects, but this method has the problem of error accumulation. The problem is that the accuracy of object change detection depends on the accuracy of object classification

Images