An Extended Deep Neural Network Connection Model for Semantic Segmentation of Satellite Images 


Vol. 48,  No. 9, pp. 1072-1074, Sep.  2023
10.7840/kics.2023.48.9.1072


PDF
  Abstract

We propose a novel deep neural network model of encoder-decoder structures to improve the performance of semantic segmentation in satellite images. Existing semantic segmentation has a lot of losses during feature compression and expansion due to its shallow structure. This reduces the accuracy of segmentation and leads to the problem of not being able to distinguish objects properly. The proposed extended connection model improves the loss of spatial information by expanding the existing encoder-decoder model to solve this problem, taking multiple layers of features and creating a structure connected to the decoder. These extended connection models improve feature loss in the feature learning process and improve the accuracy of semantic segmentation by using residual learning for upsampling. Experimental results show that the proposed model achieves significantly better performance than the existing semantic segmentation model.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Related Articles
  Cite this article

[IEEE Style]

J. Jung and Y. Shin, "An Extended Deep Neural Network Connection Model for Semantic Segmentation of Satellite Images," The Journal of Korean Institute of Communications and Information Sciences, vol. 48, no. 9, pp. 1072-1074, 2023. DOI: 10.7840/kics.2023.48.9.1072.

[ACM Style]

Jin-won Jung and Yoan Shin. 2023. An Extended Deep Neural Network Connection Model for Semantic Segmentation of Satellite Images. The Journal of Korean Institute of Communications and Information Sciences, 48, 9, (2023), 1072-1074. DOI: 10.7840/kics.2023.48.9.1072.

[KICS Style]

Jin-won Jung and Yoan Shin, "An Extended Deep Neural Network Connection Model for Semantic Segmentation of Satellite Images," The Journal of Korean Institute of Communications and Information Sciences, vol. 48, no. 9, pp. 1072-1074, 9. 2023. (https://doi.org/10.7840/kics.2023.48.9.1072)
Vol. 48, No. 9 Index

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880