The complementary nature of different modalities and multiple bands used in remote sensing data is helpful for tasks such as change detection and the prediction of agricultural variables. Nonetheless, correctly processing a multi-modal dataset is not a simple task, owing to the presence of different data resolutions and formats. In the past few years, graph-based methods have proven to be a useful tool in capturing inherent data similarity, in spite of different data formats, and preserving relevant topological and geometric information. In this paper, we propose a graph-based data fusion algorithm for remotely sensed images applied to (i) data-driven semi-unsupervised change detection and (ii) biomass estimation in rice crops. In order to detect the change, we evaluated the performance of four competing algorithms on fourteen datasets. To estimate biomass in rice crops, we compared our proposal in terms of root mean squared error (RMSE) concerning a recent approach based on vegetation indices as features. The results confirm that the proposed graph-based data fusion algorithm outperforms state-of-the-art methods for change detection and biomass estimation in rice crops.

Graph-based methods are promising approaches for traditional and modern techniques in change detection (CD) applications. Nonetheless, some graph-based approaches omit the existence of useful priors that account for the structure of a scene, and the inter- and intra-relationships between the pixels are analyzed. To address this issue, in this article, we propose a framework for CD based on graph fusion and driven by graph signal smoothness representation. In addition to modifying the graph learning stage, in the proposed model, we apply a Gaussian mixture model for superpixel segmentation (GMMSP) as a downsampling module to reduce the computational cost required to learn the graph of the entire images. We carry out tests on 14 real cases of natural disasters, farming, and construction. The dataset contains homogeneous cases with multispectral (MS) and synthetic aperture radar (SAR) images, along with heterogeneous cases that include MS/SAR images. We compare our approach against probabilistic thresholding, unsupervised learning, deep learning, and graph-based methods. In terms of Cohen’s kappa coefficient, our proposed model based on graph signal smoothness representation outperformed state-of-the-art approaches in ten out of 14 datasets.

Traditional methods to measure spatio-temporal variations in above-ground biomass dynamics (AGBD) predominantly rely on the extraction of several vegetation-index features highly associated with AGBD variations through the phenological crop cycle. This work presents a comprehensive comparison between two different approaches for feature extraction for non-destructive biomass estimation using aerial multispectral imagery. The first method is called GFKuts, an approach that optimally labels the plot canopy based on a Gaussian mixture model, a Montecarlo-based K-means, and a guided image filtering for the extraction of canopy vegetation indices associated with biomass yield. The second method is based on a Graph-Based Data Fusion (GBF) approach that does not depend on calculating vegetation-index image reflectances. Both methods are experimentally tested and compared through rice growth stages: vegetative, reproductive, and ripening. Biomass estimation correlations are calculated and compared against an assembled ground-truth biomass measurements taken by destructive sampling. The proposed GBF-Sm-Bs approach outperformed competing methods by obtaining biomass estimation correlation of $0.995$ with $R^2=0.991$ and $RMSE=45.358$ g. This result increases the precision in the biomass estimation by around $62.43\%$ compared to previous works.

This paper introduces a unified framework for developing graph-based change detection algorithms in remote sensing, which is based on signal feasibility problems and variational inequalities. We argue that signal feasibility problems provide a natural way to frame the change detection problem, while variational inequalities, core elements of modern data science and signal processing methods, enable us to find efficient, stable, and reliable solutions to the proposed feasibility problems. We demonstrate the design of both semi-supervised and unsupervised change detection schemes from our perspective, establishing connections with graph Laplacian filtering and graph convolutional networks. In contrast to specialized methods that rely on composite objective functions with multiple penalty parameters, our approach greatly simplifies hyperparameter selection, as the hyperparameters are both bounded and can form convex combinations (i.e., they are non-negative and sum up to one). We evaluate our approach on various real heterogeneous and homogeneous datasets, demonstrating its capabilities compared to traditional and modern change detection methods. Additionally, our ablation studies confirm the consistency of our solutions under variations in the number of nodes and graph structure learning methods. We conclude by discussing the advantages, limitations, and promising future research directions, with connections to graph filtering, sampling set selection, and self-supervised learning. The source code to replicate the experiments and explore the approach further is available on GitHub at https://github.com/jfflorez/Exploiting-variational-inequalities-for-generalized-change-detection-on-graphs.git.

In this paper, we address the problem of sampling on graphs for change detection in large multi-spectral (MS) and synthetic aperture radar (SAR) images by proposing a graph-based data-driven framework. The main steps of the proposed approach are: (i) the segmentation of regions that enclose the change; (ii) the use of smoothness prior for learning a graph of the regions; (iii) the integration of blue-noise sampling (BN) in the change detection scheme. We validate our approach in 14 real cases of remote sensing according to quantitative analyses. The results confirm that using a structured sampling such as BN outperforms recent state-of-the-art methods in change detection for multimodal data.