Remote sensing image segmentation has always been an important research direction in the field of remote sensing image
processing, and it is a key step in the further understanding and analysis of remote sensing images. Image semantic
segmentation is the process of classifying each pixel to form several sub-regions with respective characteristics, and
extracting the objects of interest among them. However, due to the complex boundary and scale difference of the remote
sensing image, the traditional algorithm can not meet the actual needs well, resulting in low segmentation accuracy. In
order to further improve the accuracy of remote sensing image segmentation, this paper combines deep convolutional
neural network with remote sensing image, based on the U-Net, firstly compares the model's segmentation accuracy under
different learning strategies, and introduces a new learning strategy to improve the learning effect of the model; secondly,
in the loss function part of the model, a new compound loss function is proposed to speed up the convergence of the
network and improve the segmentation accuracy. Based on full experimental research on the WHDLD remote sensing
image dataset, the results show that the improved method has 1.5% accuracy improvement compare to the U-Net.
In order to solve the problems of unstable training and texture blurring of generated images, we proposed a generative adversarial network combining residual and attention block. The attention module is added to the network, which reduces the dependence on the network depth and reduces the depth of the model. The dense connection in the residual module can extract richer image details. The number of parameters is reduced and the calculation efficiency is greatly improved. Generative adversarial network is used to further improve the texture details of the image. Generator loss functions include a content loss, a perceptual loss, a texture loss and an adversarial loss. The texture loss is used to enhance the matching degree of local information, and the perceptual loss is used to obtain more detailed features by using the feature information before an activation layer. The experimental results show that the peak signal to noise ratio is 32.10 dB, and the structural similarity is 0.92. Compared with bicubic, SRCNN, VDSR and SRGAN, the proposed algorithm improves the texture details of reconstructed images.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.