Fusion of improved unet and segnet for semantic segmentation of remote sensing images

Abstract

The invention discloses a remote sensing image semantic segmentation method integrating and improving UNet and SegNet. Batch normalization is added between the convolution layer and the activation layer of the UNet neural network, the ELU activation function is used instead of the ReLU activation function, and the training binary classification method is adopted. In the encoding process of the SegNet neural network, after the maximum pooling operation, the results of the previously set layers in the SegNet neural network are introduced to perform the convolution operation. , perform a step short-circuit connection on the result of the convolution operation to reduce the number of partial network layers of SegNet, obtain an improved SegNet neural network, fuse the improved UNet neural network and the improved SegNet neural network, obtain a remote sensing image semantic segmentation model, and perform semantic segmentation, In order to improve the effect of semantic segmentation for remote sensing images.

Description

Technical field [0001] The present invention involves the field of digital image processing technology, especially a remote sensing image semantic division method that integrates UNET and Segnet. Background technique [0002] Remote sensing technology is one of the important signs to measure the scientific and technological level and comprehensive national strength of a country, and it is widely used in many areas of military and civilian use. The essence of remote sensing technology is to extract more effective information from complicated remote sensing images. High -resolution remote sensing image is an important analysis object of remote sensing technology. Under normal circumstances, the intelligent semantic segmentation of remote sensing images requires huge data sets and extremely accurate data labeling to train. The requirements for data sets are extremely high. Satisfying result. Therefore, the semantic segmentation processing problem of high -scoring remote sensing imag...

AI Technical Summary

Problems solved by technology

This method can segment roads and buildings in remote sensing images when the labeling is inaccurate and noisy, but it needs a very large-scale data set as support and cannot play a good role in small data sets.

[0006] In short, the existing high-resolution remote sensing image semantic segmentation methods have many limitations: they need large-scale data as support, and the segmentation effect on small data sets is not ideal; they need accurate manual annotation as the basis, Not ideal for data sets with imprecise labels

It can be seen that the traditional high-resolution remote sensing image semantic segmentation scheme is prone to the problem of poor segmentation effect

Images