Remote sensing image change detection method, device and equipment and readable storage medium

Abstract

The invention discloses a remote sensing image change detection method, device and equipment and a computer readable storage medium; the method comprises the steps: obtaining at least two time sequence images of a to-be-detected region, and carrying out the preprocessing of each time sequence image; inputting the preprocessed time sequence image into a pre-established remote sensing image detection model to obtain a remote sensing image change detection result; wherein the process of establishing the remote sensing image detection model comprises the following steps of: acquiring sample time sequence images before and after surface feature change, and preprocessing each sample time sequence image; and training the constructed detection model which takes the full convolutional network as a framework and internally comprises RNN by using the preprocessed sample time sequence image to obtain a remote sensing image detection model. According to the technical scheme, the RNN is utilized to perform time sequence feature extraction on the time sequence image so as to ensure the accuracy of remote sensing image change detection, and direct processing on each pixel in the time sequence image is realized through the full convolutional network so as to improve the efficiency of remote sensing image change detection.

Description

technical field [0001] The present application relates to the technical field, and more specifically, to a remote sensing image change detection method, device, equipment, and computer-readable storage medium. Background technique [0002] For the remote sensing community, change detection has become one of the key concerns of the remote sensing community because it provides an effective way to monitor the earth. [0003] At present, in the existing remote sensing image change detection, the two time-phase images are generally sent in parallel to a series of convolutional layers to extract features, and then the features are sent to the cyclic neural network sub-module to learn time-series features. Finally, a fully-connected layer is connected to obtain the change prediction map. However, since the above method needs to expand each pixel in the temporal image, that is, it needs to process the neighborhood of each pixel to combine the neighborhood with the pixel. Therefore,...

AI Technical Summary

Problems solved by technology

[0003] At present, in the existing remote sensing image change detection, the two time-phase images are generally sent in parallel to a series of convolutional layers to extract features, and then the features are sent to the cyclic neural network sub-module to learn time-series features. Finally, a fully-connected layer is connected to obtain the change prediction map. However, since the above method needs to expand each pixel in the temporal image, that is, it needs to process the neighborhood of each pixel to combine the neighborhood with the pixel. Judgment and processing, therefore, its processing capacity will be greatly increased, which will lead to a relatively low efficiency of change detection

Images