Exploration of Remote Sensing Image Processing Method for Glacial Geomorphology Research

2012 ◽  
Vol 500 ◽  
pp. 437-443
Author(s):  
Shang Min Zhao ◽  
Wei Ming Cheng ◽  
Xi Chen
Keyword(s):  
Remote Sensing ◽  
Image Processing ◽  
Remote Sensing Image ◽  
Transformation Method ◽  
Research Area ◽  
Processing Method ◽  
Glacial Geomorphology ◽  
Image Processing Method ◽  
Remote Sensing Image Processing ◽  
Selection Of

Taking Mt. Namjagbarwa region as an example, this paper explores a complete remote sensing image processing method for glacial geomorphology research. Based on the selection of Landsat7 ETM+ images, the remote sensing image processing method such as band selection, overlap, fusion, mosaic and so on is carried out. The result shows: ① right selection of remote sensing images and proper process based on the characteristics of research area and research purpose, not only reduce the process difficulty, but make a firm foundation for subsequent glacial geomorphology research; ②according to the computation of correlation coefficient between fusion images and original multi-spectral images, panchromatic high resolution images, the result shows that the principle component transformation method has better effect than IHS transformation method in remote sensing image fusion process.

scholarly journals Remote Sensing Image Dataset Expansion Based on Generative Adversarial Networks with Modified Shuffle Attention

Sensors ◽  
2021 ◽  
Vol 21 (14) ◽  
pp. 4867
Author(s):  
Lu Chen ◽  
Hongjun Wang ◽  
Xianghao Meng
Keyword(s):  
Remote Sensing ◽  
Neural Networks ◽  
Image Processing ◽  
Remote Sensing Image ◽  
Generative Adversarial Networks ◽  
Generative Adversarial Network ◽  
Evaluation Indexes ◽  
Adversarial Network ◽  
Remote Sensing Image Processing ◽  
Data Expansion

With the development of science and technology, neural networks, as an effective tool in image processing, play an important role in gradual remote-sensing image-processing. However, the training of neural networks requires a large sample database. Therefore, expanding datasets with limited samples has gradually become a research hotspot. The emergence of the generative adversarial network (GAN) provides new ideas for data expansion. Traditional GANs either require a large number of input data, or lack detail in the pictures generated. In this paper, we modify a shuffle attention network and introduce it into GAN to generate higher quality pictures with limited inputs. In addition, we improved the existing resize method and proposed an equal stretch resize method to solve the problem of image distortion caused by different input sizes. In the experiment, we also embed the newly proposed coordinate attention (CA) module into the backbone network as a control test. Qualitative indexes and six quantitative evaluation indexes were used to evaluate the experimental results, which show that, compared with other GANs used for picture generation, the modified Shuffle Attention GAN proposed in this paper can generate more refined and high-quality diversified aircraft pictures with more detailed features of the object under limited datasets.

A dynamic acceleration method for remote sensing image processing based on CUDA

2021 ◽  
Author(s):  
Xianyu Zuo ◽  
Zhe Zhang ◽  
Baojun Qiao ◽  
Junfeng Tian ◽  
Liming Zhou ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Image Processing ◽  
Remote Sensing Image ◽  
Acceleration Method ◽  
Remote Sensing Image Processing
Sign in / Sign up

Export Citation Format

Share Document