Contextual band addition and multi-look inferencing to improve semantic segmentation model performance on satellite images

In this study, we introduce two spatial approaches to enhance semantic segmentation accuracy in remote sensing imagery in resource-constrained computational environments, with a focus on edge regions. The first approach, Contextual Bands Addition, integrates overview, incorporating essential context...

Full description

Saved in:
Bibliographic Details
Published inJournal of spatial science Vol. 69; no. 3; pp. 849 - 872
Main Authors Shah, Syed Roshaan Ali, Rehman, Obaid-Ur, Shabbir, Yasir, Ishaq, Rana AhmadFaraz
Format Journal Article
LanguageEnglish
Published Taylor & Francis 02.07.2024
Subjects
AI4EO
buildings
built-up
context
field boundaries
multi-look inference
Remote sensing
Online AccessGet full text

Cover

More Information
Summary:In this study, we introduce two spatial approaches to enhance semantic segmentation accuracy in remote sensing imagery in resource-constrained computational environments, with a focus on edge regions. The first approach, Contextual Bands Addition, integrates overview, incorporating essential contextual information. The second approach, multi-look inferencing, utilises multiple spatial perspectives to refine segmentation. Our results show significant improvements: Contextual Band Addition with tile overlaps increases IoU scores by 4-5%. Multi-look inferencing enhances IoU scores by 2.5% post-training. Combined, these strategies yield a 6-7% overall performance boost, valuable for semantic segmentation on limited training samples from satellite imagery datasets.
ISSN:1449-8596
1836-5655
DOI:10.1080/14498596.2024.2305124