Online Multi-resolution Fusion of Space-borne Multispectral Images

Li, Haoqing; Duvviri, Bhavia; Borsoi, Ricardo Augusto; Imbiriba, Tales; Beighley, E.; Erdoğmuş, Deni̇z; Closas, Pau

doi:10.1109/aero53065.2022.9843578

Cited by 1 publication

(1 citation statement)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, their spatial resolution is significantly low, being in the order of hundreds of meters. Considering this and in order to combine images with different spatial and temporal resolutions, multimodal image fusion techniques have been developed to generate high spatio-temporal image sequences, contributing to generate a wealth of RS data (Li et al, 2022;Zhu et al, 2010Zhu et al, , 2018. Spectral indices are one of the main land cover mapping tools given their simplicity and required low computational cost.…”

Section: Introductionmentioning

confidence: 99%

Recursive classification of satellite imaging time-series: An application to water and land cover mapping

Calatrava¹,

Duvvuri²,

Li³

et al. 2023

Preprint

View full text Add to dashboard Cite

A wide variety of applications of fundamental importance for security, environmental protection and urban development need access to accurate land cover monitoring and water mapping, for which the analysis of optical remote sensing imagery is key. Classification of time-series images, particularly with recursive methods, is of increasing interest in the current literature. Nevertheless, existing recursive approaches typically require large amounts of training data. This paper introduces a recursive classification framework that provides high accuracy while requiring low computational cost and minimal supervision. The proposed approach transforms a static classifier into a recursive one using a probabilistic framework that is robust to non-informative image variations. A water mapping and a land cover experiment are conducted analyzing Sentinel-2 satellite data covering two areas in the United States. The performance of three static classification algorithms and their recursive versions is compared, including a Gaussian Mixture Model (GMM), Logistic Regression (LR) and Spectral Index Classifiers (SICs). SICs consist in a new approach that we introduce to convert the Modified Normalized Difference Water Index (MNDWI) and the Normalized Difference Vegetation Index (NDVI) into probabilistic classification results. Two state-of-the-art deep learning-based classifiers are also used as benchmark models. Results show that the proposed method significantly increases the robustness of existing static classifiers in multitemporal settings. Our method also improves the performance of deep learning-based classifiers without the need of additional training data.

show abstract

Section: Introductionmentioning

confidence: 99%