A method and device for optical remote sensing image segmentation based on multi-granularity network fusion

Abstract

The invention relates to an optical remote sensing image segmentation method and device based on multi-granularity network fusion. The method includes: step 1, collecting at least one optical remote sensing image as a training image, setting at least one image category, and labeling the image category for the training image; step 2, based on the labeled training image, using reverse The propagation algorithm trains the pre-built multi-granularity network fusion model, wherein the multi-granularity network fusion model includes four sub-neural networks; Step 3, input the image to be processed into the trained multi-granularity network fusion model, according to the The four sub-neural networks determine the image category of each pixel in the image to be processed, and output the image category of each pixel in the image to be processed as a segmentation result. The technical scheme of the invention can effectively realize fine segmentation of optical remote sensing images and suppress background interference.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an optical remote sensing image segmentation method and device based on multi-granularity network fusion. Background technique [0002] With the rapid development of remote sensing technology, the spatial resolution of optical remote sensing images is getting higher and higher. Today, high-definition optical remote sensing images have entered the stage of commercialization. Thanks to the high spatial resolution of high-definition optical remote sensing images, many details in the images can be clearly presented, providing strong data support for the fine segmentation of remote sensing images. Deep learning methods have been widely used in remote sensing image segmentation. Common deep learning methods include convolutional neural networks, including VGG, FCN and other networks. For complex optical remote sensing images, the VGG network can achieve fine segmentation of o...

AI Technical Summary

Problems solved by technology

For complex optical remote sensing images, the VGG network can achieve fine segmentation of optical remote sensing images, but at the same time it is greatly disturbed by complex backgrounds, resulting in many false detections.

At the same time, although the FCN network can suppress the interference of complex backgrounds to a large extent, the fineness of optical remote sensing image segmentation is not enough to achieve fine optical remote sensing image segmentation.

Images