Semantic Segmentation of Heterogeneous Unmanned Aerial Vehicle Datasets Using Combined Segmentation Network

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

Unmanned aerial vehicles (UAVs) can capture high-resolution imagery from a variety of viewing angles and altitudes; they are generally limited to collecting images of small scenes from larger regions. To improve the utility of UAV-appropriated datasets for use with deep learning applications, multiple datasets created from various regions under different conditions are needed. To demonstrate a powerful new method for integrating heterogeneous UAV datasets, this paper applies a combined segmentation network (CSN) to share UAVid and semantic drone dataset encoding blocks to learn their general features, whereas its decoding blocks are trained separately on each dataset. Experimental results show that our CSN improves the accuracy of specific classes (e.g., cars), which currently comprise a low ratio in both datasets. From this result, it is expected that the range of UAV dataset utilization will increase.

Original languageEnglish
Pages (from-to)87-97
Number of pages11
JournalKorean Journal of Remote Sensing
Volume39
Issue number1
DOIs
StatePublished - 2023

Keywords

  • Deep learning
  • Semantic drone dataset
  • Semantic segmentation
  • UAVid

Fingerprint

Dive into the research topics of 'Semantic Segmentation of Heterogeneous Unmanned Aerial Vehicle Datasets Using Combined Segmentation Network'. Together they form a unique fingerprint.

Cite this