Fast Unmixing and Change Detection in Multitemporal Hyperspectral Data

Borsoi, Ricardo Augusto; Imbiriba, Tales; Bermudez, J.C.M.; Richard, Cédric

doi:10.1109/tci.2021.3112118

Cited by 15 publications

(9 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This way, spectral unmixing [28] is used to estimate the endmembers at different time instants from low resolution images, while using different strategies to mitigate the spectral variability of a single material [30,33,34]. However, abrupt abundance variations (originating from, e.g., land cover changes) are commonly found in multitemporal image streams [35,36,37,38], which may negatively impact the performance of such methods and can be particularly challenging to address when occurring jointly with finer endmember variations [35]. Thus, special care is required when fusing images which are temporally distant from one another [39], motivating the development of strategies using, e.g., spatially adaptive quantification of the reliability of the input images to guide unmixing based image fusion strategies [40].…”

Section: Introductionmentioning

confidence: 99%

Online Fusion of Multi-resolution Multispectral Images with Weakly Supervised Temporal Dynamics

Li¹,

Duvvuri²,

Borsoi³

et al. 2023

Preprint

View full text Add to dashboard Cite

Real-time satellite imaging has a central role in monitoring, detecting and estimating the intensity of key natural phenomena such as floods, earthquakes, etc. One important constraint of satellite imaging is the trade-off between spatial/spectral resolution and their revisiting time, a consequence of design and physical constraints imposed by satellite orbit among other technical limitations. In this paper, we focus on fusing multi-temporal, multi-spectral images where data acquired from different instruments with different spatial resolutions is used. We leverage the spatial relationship between images at multiple modalities to generate high-resolution image sequences at higher revisiting rates. To achieve this goal, we formulate the fusion method as a recursive state estimation problem and study its performance in filtering and smoothing contexts. Furthermore, a calibration strategy is proposed to estimate the time-varying temporal dynamics of the image sequence using only a small amount of historical image data. Differently from the training process in traditional machine learning algorithms, which usually require large datasets and computation times, the parameters of the temporal dynamical model are calibrated based on an analytical expression that uses only two of the images in the historical dataset. A distributed version of the Bayesian filtering and smoothing strategies is also proposed to reduce its computational complexity. To evaluate the proposed methodology we consider a water mapping task where real data acquired by the Landsat and MODIS instruments are fused generating high spatial-temporal resolution image estimates. Our experiments show that the proposed methodology outperforms the competing methods in both estimation accuracy and water mapping tasks.

show abstract

Section: Introductionmentioning

confidence: 99%

Online Fusion of Multi-resolution Multispectral Images with Weakly Supervised Temporal Dynamics

Li¹,

Duvvuri²,

Borsoi³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The analysis of multitemporal or time-series data is of increasing interest for RS applications (Johnson and Iizuka, 2016;Kuenzer et al, 2015). Exploiting multitemporal data makes it possible to improve the performance of tasks such as classification (Deng et al, 2019;Gómez et al, 2016) or spectral mixture analysis (Borsoi et al, 2021a;Halabisky et al, 2016) due to its temporal correlation, while at the same time supplying the end-user with a more complete product that shows the spatial as well as the temporal distribution of land classes or their proportions. The simplest approach to perform multitemporal land cover mapping is to apply a static classifier to each image in the sequence, being spectral indices such as the NDVI a popular choice (Jeevalakshmi et al, 2016;Sun et al, 2018).…”

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

“…Addressing both the spatial and temporal spectral variability of the EMs is challenging, and has only been done in MTHU by supervised techniques [10], [16]. However, supervised MTHU techniques require prior knowledge of libraries containing spectral signatures which can accurately represent the endmembers for each image in the time sequence.…”

Section: Introductionmentioning

confidence: 99%

Dynamical Hyperspectral Unmixing with Variational Recurrent Neural Networks

Borsoi¹,

Imbiriba²,

Closas³

2023

Preprint

View full text Add to dashboard Cite

Multitemporal hyperspectral unmixing (MTHU) is a fundamental tool in the analysis of hyperspectral image sequences. It reveals the dynamical evolution of the materials (endmembers) and of their proportions (abundances) in a given scene. However, adequately accounting for the spatial and temporal variability of the endmembers in MTHU is challenging, and has not been fully addressed so far in unsupervised frameworks. In this work, we propose an unsupervised MTHU algorithm based on variational recurrent neural networks. First, a stochastic model is proposed to represent both the dynamical evolution of the endmembers and their abundances, as well as the mixing process. Moreover, a new model based on a low-dimensional parametrization is used to represent spatial and temporal endmember variability, significantly reducing the amount of variables to be estimated. We propose to formulate MTHU as a Bayesian inference problem. However, the solution to this problem does not have an analytical solution due to the nonlinearity and non-Gaussianity of the model. Thus, we propose a solution based on deep variational inference, in which the posterior distribution of the estimated abundances and endmembers is represented by using a combination of recurrent neural networks and a physically motivated model. The parameters of the model are learned using stochastic backpropagation. Experimental results show that the proposed method outperforms state of the art MTHU algorithms.

show abstract

Fast Unmixing and Change Detection in Multitemporal Hyperspectral Data

Cited by 15 publications

References 57 publications

Online Fusion of Multi-resolution Multispectral Images with Weakly Supervised Temporal Dynamics

Online Fusion of Multi-resolution Multispectral Images with Weakly Supervised Temporal Dynamics

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

Dynamical Hyperspectral Unmixing with Variational Recurrent Neural Networks

Contact Info

Product

Resources

About