Change detection (CD) in Satellite Image Time Series (SITS) is more complex than in bi-temporal images due to the higher dimensionality of the data. Utilizing the full dimensionality of the time series remains challenging, particularly with dense SITS. An approach that can minimize dimensions without compromising informational depth is essential. In this paper, we present an innovative framework for Change Vector Analysis (CVA) in time series analysis and initial demonstrations of its effectiveness in capturing the spectral-temporal characteristics of changes. Unlike current methods, the proposed approach incorporates a wide range of spectral-temporal information and constructs separate reference matrices for each change type, facilitating an in-depth analysis of change components for CD. Based on the Time Series Change Vector (TSCV), the proposed framework extends CVA into the time series perspective, offering novel interpretations for magnitude and direction across temporal and spectral dimensions. The framework effectiveness is validated using Sentinel-2 data, demonstrating significant improvements in tackling multiple CD challenges in dense SITS scenarios.

Detecting various types of changes in dense Satellite Image Time Series (SITS) presents a complex challenge. While Change Vector Analysis (CVA) is widely used for Change Detection (CD), it presents limitations due to a lack of prior information on changes, such as optimal spectral channels and change timing. To overcome these obstacles, the study focuses on the direction analysis of the Time Series Change Vectors (TSCV) [1], built upon CVA principles. Conducting unsupervised CD using time series magnitude information, the approach leverages multiple change dimensions in the direction analysis. A novel scheme formulates a representative change matrix within SITS temporal and spectral domains, guiding change representations and allowing segregation based on significance in both spectral and temporal dimensions. The proposed method efficacy is evaluated using Sentinel-2 time series data, with results affirming its robustness in effectively addressing multi-CD challenges within dense SITS.

Climate change finds one of its main causes in the happening transition between forest and arid lands of different types as a consequence of wildfires and/or massive deforestation practices. Remote sensing should provide effective and scalable solutions to monitor this dangerous trend. In this paper, a recently developed novel model for one-class classification based on abstract features constructed from normalized difference indices is presented and challenged on detecting deforestation patterns on multispectral images. Results are promising as the performance is nearly optimal, showing that the model comes with good generalization capabilities to deal with vegetation related changes in general.

Global scale assessment of burned area (BA) is essential for climate studies and open access satellite-borne multispectral (MS) imagery is vital for the mapping purpose. Global characterization of BAs via MS analysis is difficult as it usually requires ancillary data to model local factors such as vegetation types and local eco-climate systems. This paper proposes a novel classification model that exploits certain mathematical properties of normalized difference indexes (NDIs) to build an abstract space of features where the BA class can be learned globally and solely using MS images. The core idea is that, although NDIs are subject to strong intra-class variations, their mutual order (i.e., the sign of their difference) can be robust enough for characterization. By encoding every possible such ordering relation in a binary domain, the feature space turns out to be hyper-dimensional, with abstraction capabilities similar to that of Neural Network (NN) layers. The proposed classification model is one-class, therefore very convenient as it only requires training samples for the positive class to be collected. The model is experimentally validated in an extensive BA detection exercise with Sentinel-2 images that involves recently published global BA reference data. Results are promising as we report higher F1-score than those reported for state-of-the-art BA products currently available, which are obtained through hybrid techniques and multiple data sources. The model also outperforms the well-known and largely used one-class SVM (OC-SVM), which is tested in this work for the first time for BA detection at global scale.

The current remote sensing (RS) open data policy for multispectral (MS) missions such as Sentinel-2 and Landsat-8, together with the availability of free cloud distributed processing platforms such as Google Earth Engine, makes it possible the quick generation of burned area (BA) products even for nonexperts in the field. Indeed, fires and BAs can be detected using burn severity indices, which are usually obtained by simple band algebra operations. However, simple approaches can aid BA estimation only if typical error patterns are known and accounted for, especially when working at large (e.g., continental) scales. This article proposes an automatic BA detection system based on burn severity index thresholding, which integrates dedicated false and missed alarm mitigation strategies to improve the detection accuracy. The system is tested on Sentinel-2 and Landsat-8 data over ten different locations in Europe and spanning year 2018. Three known burn severity indices plus a custom one defined to improve the performance in the considered study area are under study. Results show that burned index thresholding is possible within accuracy bounds slightly larger than the state of the art, which is acceptable by considering the proposed simplified processing framework.

We propose a system for detecting clear-cuts in Sentinel-2 (S-2) images of the Indonesian forest by means of an adaptive and unsupervised multivariate Change Vector Analysis (CVA) method. By leveraging on the unique spatial and spectral characteristics of the S- 2 mission, the proposed method characterizes a relevant portion of the target change as lying in a Gaussian neighborhood of the spectral stacked bi-temporal domain of the change. The processing system analyzes all the available bi-temporal pairs in the time series, enabling us to: (1) partially recovering lost information due to cloud coverage, and (2) providing a representation of the change evolving in time. The system is fully automated and potentially operational ready, so it can be used to provide accurate information about clear-cuts at the country scale in Indonesia.

The change detection (CD) problem is very important in the remote sensing domain. The advent of a new generation of multispectral (MS) sensors has given rise to new challenges in the development of automatic CD techniques. In particular, typical approaches to CD are not able to well model and properly exploit the increased radiometric resolution characterizing new data as this results in a higher sensitivity to the number of natural classes that can be statistically modeled in the images. In this paper, we introduce a theoretical framework for the description of the statistical distribution of the difference image as a compound model where each class is determined by temporally correlated class transitions in the bitemporal images. The potential of the proposed framework is demonstrated on the very common problem of binary CD based on setting a threshold on the magnitude of the difference image. Here, under some simplifying assumptions, a multiclass distribution of the magnitude feature is derived and an unsupervised method based on the expectation-maximization algorithm and Bayes decision is proposed. Its effectiveness is demonstrated on a large variety of data sets from different MS sensors. In particular, experimental tests confirm that: 1) the fitting of the magnitude distribution significantly improves if compared with already existing models and 2) the overall CD error is close to the optimal value.

The increased radiometric resolution of last generation multispectral sensors results in large statistical variability of classes represented in the image. However, classes present high spatial homogeneity. To preserve classes identity while simplifying their representation, in this paper we propose a class-wise spatial-contextual method based on a variational model with free discontinuities that reduces the statistical variability of classes by emphasizing their spatial contours. To prove its effectiveness, the proposed method is applied in the context of change detection in multispectral images. Here, it is able to augment the discrimination between the unchange and the change classes and to improve the detection performance.

Variational models are known to work well for addressing image restoration/regularization problems. However, most of the methods proposed in the literature are defined for scalar inputs and are used on multiband images (such as RGB or multispectral imagery) by the composition of a simple band-wise processing. This involves suboptimal results and may introduce artifacts. Only in a few cases, variational models are extended to the case of vector-valued inputs. However, the known implementations are restricted to the first-order models, while the second-order models are never considered. Thus, typical problems of the first-order models, such as the staircasing effect cannot be overtaken. This paper considers a second-order functional model to function approximation with free discontinuities given by Blake-Zisserman (BZ) and proposes an efficient minimization algorithm in the case of vector-valued inputs. In the BZ model, the Hessian of the solution is penalized outside a set of finite length, therefore the solution is forced to be piecewise linear. Moreover, the model allows the formation of free discontinuities and free gradient discontinuities. The proposed algorithm is applied to difficult color image restoration/regularization problems and to piecewise linear approximation of curves in space.

Recently, a thresholding method based on the Rayleigh-Rice mixture has been proposed for solving binary change detection problems in multispectral image pairs. However, when images acquired by the last generation of multispectral scanners having high radiometric resolution are considered, the distribution fitting is still not satisfactory and computed thresholds remain quite distant from the optimal values. The main reason for this seems to be that in all previous approaches the unchange class is modeled as a single class. Instead, both practice and recent studies showed that this is not the case for new generation data. In this work, we propose a generalized statistical model for the difference image that allows the unchange class to be complex. The resulting model has more degrees of freedom, therefore it better fits real distributions and returns almost optimal thresholds for binary decision also with high radiometric resolution images.

Typical tiling approaches to segmentation of large images perform separated runs of a specific segmentation algorithm on tiles and then merge the results. However, specific post-processing is often required to remove possible artifacts on tiles junctions. In this paper, we aim at showing that a simple tiling strategy with partially overlapping tiles can be applied to a 2-nd order variational segmentation method based on the minimization of the Blake-Zisserman functional, in such a way that tile boundaries are coherent without any need of specific post-processing. Moreover, the energy minimization is performed on each tile with Dirichlet initial boundary conditions; thus, tiles are independent and the whole procedure is parallelizable with independent tiles.

This paper presents an effective semiautomatic method for discovering and detecting multiple changes (i.e., different kinds of changes) in multitemporal hyperspectral (HS) images. Differently from the state-of-the-art techniques, the proposed method is designed to be sensitive to the small spectral variations that can be identified in HS images but usually are not detectable in multispectral images. The method is based on the proposed sequential spectral change vector analysis, which exploits an iterative hierarchical scheme that at each iteration discovers and identifies a subset of changes. The approach is interactive and semiautomatic and allows one to study in detail the structure of changes hidden in the variations of the spectral signatures according to a top-down procedure. A novel 2-D adaptive spectral change vector representation (ASCVR) is proposed to visualize the changes. At each level this representation is optimized by an automatic definition of a reference vector that emphasizes the discrimination of changes. Finally, an interactive manual change identification is applied for extracting changes in the ASCVR domain. The proposed approach has been tested on three hyperspectral data sets, including both simulated and real multitemporal images showing multiple-change detection problems. Experimental results confirmed the effectiveness of the proposed method.

The problem of estimating the parameters of a Rayleigh-Rice mixture density is often encountered in image analysis (e.g., remote sensing and medical image processing). In this paper, we address this general problem in the framework of change detection (CD) in multitemporal and multispectral images. One widely used approach to CD in multispectral images is based on the change vector analysis. Here, the distribution of the magnitude of the difference image can be theoretically modeled by a Rayleigh-Rice mixture density. However, given the complexity of this model, in applications, a Gaussian-mixture approximation is often considered, which may affect the CD results. In this paper, we present a novel technique for parameter estimation of the Rayleigh-Rice density that is based on a specific definition of the expectation-maximization algorithm. The proposed technique, which is characterized by good theoretical properties, iteratively updates the parameters and does not depend on specific optimization routines. Several numerical experiments on synthetic data demonstrate the effectiveness of the method, which is general and can be applied to any image processing problem involving the Rayleigh-Rice mixture density. In the CD context, the Rayleigh-Rice model (which is theoretically derived) outperforms other empirical models. Experiments on real multitemporal and multispectral remote sensing images confirm the validity of the model by returning significantly higher CD accuracies than those obtained by using the state-of-the-art approaches.