Remote sensing image adaptive feature selection segmentation method and system

Abstract

The invention provides a remote sensing image adaptive feature selection segmentation method and system. The method comprises the steps of performing data preparation, high-resolution image cutting and data preprocessing; improving a model, arranging a self-adaptive feature selection module additionally based on a basic model network, the self-adaptive feature selection module being used for carrying out feature extraction on different feature maps, and performing global average pooling feature extraction on the feature maps of multiple different scales or different receptive fields obtained through the basic model network; learning weight distribution of importance degrees of different feature maps by using a full connection layer and an activation function, and performing feature screening according to the weight distribution to realize an adaptive feature selection process; training the obtained optimized deep learning model; and processing the segmentation result of the input visible light image according to the optimized deep learning model obtained by training. The invention not only can effectively improve the precision of the segmentation model, but also can reduce the calculation amount of the model, and has the advantages of universality, simple operation, strong performance and the like.

Description

technical field [0001] The invention belongs to the field of satellite remote sensing image processing, particularly relates to a segmentation scheme of high-resolution remote sensing images, and proposes a new deep learning model to realize an adaptive feature selection scheme of remote sensing images. Background technique [0002] In recent years, with the deepening of the application of deep learning in the field of image processing, semantic segmentation, as an important research direction in image processing, has developed rapidly. For remote sensing image segmentation, it is of great significance to the subsequent processing of remote sensing images. Especially on the satellite platform, the image is segmented in advance, and the target area of ​​interest is extracted to provide prior knowledge for image understanding. Applying artificial intelligence and computer vision to the on-orbit satellite platform can provide real-time intelligent services for global remote se...

AI Technical Summary

Problems solved by technology

At present, there is no good solution to the problem of scale selection and authorized patents in China.

Images