Comparison of Semantic Segmentation Performance of U-Net according to the Ratio of Small Objects for Nuclear Activity Monitoring

Jinmin Lee, Taeheon Kim, Changhui Lee, Hyunjin Lee, Ahram Song, Youkyung Han

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

Monitoring nuclear activity for inaccessible areas using remote sensing technology is essential for nuclear non-proliferation. In recent years, deep learning has been actively used to detect nuclear-activity-related small objects. However, high-resolution satellite imagery containing small objects can result in class imbalance. As a result, there is a performance degradation problem in detecting small objects. Therefore, this study aims to improve detection accuracy by analyzing the effect of the ratio of small objects related to nuclear activity in the input data for the performance of the deep learning model. To this end, six case datasets with different ratios of small object pixels were generated and a U-Net model was trained for each case. Following that, each trained model was evaluated quantitatively and qualitatively using a test dataset containing various types of small object classes. The results of this study confirm that when the ratio of object pixels in the input image is adjusted, small objects related to nuclear activity can be detected efficiently. This study suggests that the performance of deep learning can be improved by adjusting the object pixel ratio of input data in the training dataset.

Original languageEnglish
Pages (from-to)1925-1934
Number of pages10
JournalKorean Journal of Remote Sensing
Volume38
Issue number6
DOIs
StatePublished - Dec 2022

Keywords

  • Class imbalance
  • Nuclear non-proliferation
  • Semantic segmentation
  • Small object
  • U-Net

Fingerprint

Dive into the research topics of 'Comparison of Semantic Segmentation Performance of U-Net according to the Ratio of Small Objects for Nuclear Activity Monitoring'. Together they form a unique fingerprint.

Cite this