Remote sensing image semantic segmentation method fusing improved UNet and SegNet

Abstract

The invention discloses a remote sensing image semantic segmentation method fusing improved UNet and SegNet. Batch processing standardization is added between a convolution layer and an activation layer of the UNet neural network; an ELU activation function is adopted to replace a ReLU activation function; respectively training each semantic segmentation category by adopting a binary classification training mode; combining the models trained by the binary classification; in the coding process of the SegNet neural network, the coding speed is improved; performing a maximum pooling operation; introducing a result of a front setting layer in the SegNet neural network to carry out convolution operation; step short-circuit connection is carried out on a convolution operation result; the remotesensing image semantic segmentation method comprises the steps of obtaining an improved SegNet neural network by reducing the number of partial network layers of SegNet, fusing the improved UNet neural network and the improved SegNet neural network to obtain a remote sensing image semantic segmentation model, and performing semantic segmentation to improve the effect of performing semantic segmentation on a remote sensing image.

Description

technical field [0001] The invention relates to the technical field of digital image processing, in particular to a remote sensing image semantic segmentation method which integrates and improves UNet and SegNet. Background technique [0002] Remote sensing technology is one of the important symbols to measure a country's scientific and technological level and comprehensive national strength, and it has been widely used in many military and civilian fields. 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 datasets and extremely precise data annotations to train, and the requirements for datasets are extremely high, while datasets with imprecise annotations or small samples cannot achieve impressive res...

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