File Download

There are no files associated with this item.

  • Find it @ UNIST can give you direct access to the published full text of this article. (UNISTARs only)
Related Researcher

임정호

Im, Jungho
Intelligent Remote sensing and geospatial Information Science Lab.
Read More

Views & Downloads

Detailed Information

Cited time in webofscience Cited time in scopus
Metadata Downloads

SAMBA: Synthetic Data-Augmented Mamba-Based Change Detection Algorithm Using KOMPSAT-3A Imagery

Author(s)
Tobias, Rogelio RuzckoBae, SejeongCho, HwanheeIm, Jungho
Issued Date
2024-12
DOI
10.7780/kjrs.2024.40.6.3.11
URI
https://scholarworks.unist.ac.kr/handle/201301/85458
Citation
KOREAN JOURNAL OF REMOTE SENSING, v.40, no.6-3, pp.1505 - 1521
Abstract
Change detection is essentialfor applicationssuch as urban planning, environmental monitoring, and disasterresponse. Despite advancementsin high-resolution satellite imagery, accurate change detection remains challenging due to increased landscape heterogeneity and variable atmospheric conditions. The Mamba model, an efficient state-space model-based architecture, has shown promise in capturing spatiotemporalrelationshipsin high-resolution datasets, addressing the limitations of traditional methods thatstrugglewith the diverse appearances of urban structures. Thisresearch investigates applying Mamba to multitemporal Korea Multi-Purpose Satellite (KOMPSAT)imagery, using both real and synthetic data from SyntheWorld, a dataset developed to simulate various change scenarios. This study introduces a synthetic data-augmented mamba-based change detection algorithm (SAMBA), designed to detect structural changes in urban environments using KOMPSAT-3A satellite imagery. The main objectives are to evaluate the Mamba binary change detection (MambaBCD) model’s ability to detect building changesin KOMPSAT-3Aimages and assessthe impact ofsynthetic data augmentation on performance. Experimentalresults with MambaBCD-Small and MambaBCD-Tiny modelsindicate thatsynthetic data incorporation improves generalization in complex settings, achieving high performance across multiple data and model configurations. Notably, the MambaBCD-Tiny model, with or without synthetic augmentation, outperformed the larger-parameter MambaBCD-Small model, demonstrating enhanced sensitivity in detecting satellite image changes. Performance evaluation metrics yielded an overall accuracy of 99.73%, precision of 98.34%, recall of 96.54%, F1-score of 97.43%, intersection over union of 95.00%, and Kappa coefficient of 97.29%. These metrics were similarly used to test the SAMBA algorithm’sgeneralization on benchmark change detection datasets,showcasing its potential as a robust tool for highresolution image change detection.
Publisher
KOREAN SOC REMOTE SENSING
ISSN
1225-6161
Keyword (Author)
Artificial intelligenceChange detectionComputer visionKOMPSATMambaRemote sensing

qrcode

Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.