A sequential framework for image change detection.

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.

Game Theory based Framework for Synthetic Aperture Radar Image De-noising and Change Detection

Change-Point (CP) detection has attracted considerable attention in the fields of data mining and statistics; it is very meaningful to discuss how to quickly and efficiently detect abrupt change from large-scale bioelectric signals. Currently, most of the existing methods, like Kolmogorov-Smirnov (KS) statistic and so forth, are time-consuming, especially for large-scale datasets. In this paper, we propose a fast framework for abrupt change detection based on binary search trees (BSTs) and a modified KS statistic, named BSTKS (binary search trees and Kolmogorov statistic). In this method, first, two binary search trees, termed as BSTcA and BSTcD, are constructed by multilevel Haar Wavelet Transform (HWT); second, three search criteria are introduced in terms of the statistic and variance fluctuations in the diagnosed time series; last, an optimal search path is detected from the root to leaf nodes of two BSTs. The studies on both the synthetic time series samples and the real electroencephalograph (EEG) recordings indicate that the proposed BSTKS can detect abrupt change more quickly and efficiently than KS, t-statistic (t), and Singular-Spectrum Analyses (SSA) methods, with the shortest computation time, the highest hit rate, the smallest error, and the highest accuracy out of four methods. This study suggests that the proposed BSTKS is very helpful for useful information inspection on all kinds of bioelectric time series signals.

Urban change detection (CD) using remote sensing images is of great significance for monitoring and analyzing the spatial and temporal distribution of changes within cities, which can be used to guide urban management. In order to reduce false detections and improve the CD automation, a novel CD framework for high resolution images is proposed in this article. First, a novel multilevel matching feature is presented, combining structural invariant features with multiscale dense matching features to comprehensively describe the invariant properties of ground objects at different levels. Second, a newly automatic training sample extraction strategy is proposed, in which sufficient and accurate no-change samples can be obtained by Gaussian-weighted Dempster–Shafer evidence theory and L1-norm, meanwhile, typical change samples can be extracted by sequential spectral change vector analysis. Utilizing the automatic extracted samples, the final CD results are obtained using four supervised classifiers, respectively ( k -nearest neighbor, support vector machine, rotation forest, and extra-trees). To validate the proposed CD framework, experiments are conducted in four datasets with spectral variability, spectral confusion between the changed objects and unchanged backgrounds, and misregistration. The results demonstrate that the proposed multilevel matching feature and automatic sample extraction strategy can obtain better results with different types of supervised classifiers, and can effectively improve automation of CD, which is applicable to the large spatial extent scene.

Interoperable cross-domain semantic and geospatial framework for automatic change detection

Spectral mapping with adversarial learning for unsupervised hyperspectral change detection

This article proposes a Bayesian learning framework for online change detection of high-dimensional data streams where only a subset of variables can be observed at each time point due to limited sensing capacities. On the one hand, we need to build a change detection scheme based on partial observations. On the other, the scheme should be able to adaptively and actively select the most critical sensing variables to observe to maximize the detection power. To address these two points, in this article, first, a novel Bayesian Spike-Slab Composite Decomposition (BSSCD) is proposed to decompose the high-dimensional signals onto normal and abnormal bases, where the projection coefficients are efficiently estimated via variational Bayesian inference. Built upon it, the posterior Bayes factor is constructed as the detection statistic. Second, by further formulating the detection statistic as the reward function of combinatorial multi-armed bandit (CMAB), a Thompson sampling strategy is proposed for selecting the potential changed variables with the balance of exploration and exploitation. The efficacy and applicability of our method are demonstrated in practice with numerical studies and a real case study.

In recent years, Foundation Vision Models (FVMs) have provided new technical approaches for change detection and understanding of remote sensing images due to their strong generalization and multi-scale representation capabilities. However, in complex spatiotemporal scenarios, existing methods still face two major challenges: insufficient feature interaction and an imbalance between global and detail representation. To address these challenges, this paper proposes RoCD, which introduces the Refine-and-Align Framework (RAF) and FusionR-Decoder on top of the frozen basic visual model, FastSAM encoder. First, RAF introduces a pairwise difference refinement (PDR) mechanism to enhance feature interactions and effectively suppress spurious changes caused by inter-domain differences. Second, FusionR-Decoder embeds a three-branch RBlock based on state space models (SSMs) in the multi-scale decoding stage to achieve long dependency modeling and global consistency constraints. Experimental results on the three public datasets LEVIR-CD, LEVIR-CD+, and WHU-CD show that RoCD achieves F1/IoU scores of 92.11/85.38, 87.68/76.90, and 95.95/91.04, respectively.

Abstract. Building change detection from remote sensing images is vital for many applications such as urban planning and dynamic monitoring, smart city construction, and geographical information census. In recent years, with the improvement of artificial intelligence and computer vision techniques, deep learning algorithms, especially convolutional neural networks (CNN), provide automatic detection and extraction methods. Unlike traditional approaches relying on shallow manual features, CNN can generate the deep semantic features by fusing spatial and spectral information, which is conducive to identifying building change regions. However, most deep CNN models directly fuse different level features and recover spatial details, which probably introduce redundant background information and noise from shallow layers. Considering the building’s multiscale, convolution operation with fixed receptive fields cannot obtain a strong global feature response to changed regions. To address the above problems, we develop a CNN framework for automatic building region change detection using dual-temporal high-resolution remote sensing images. To refine the shallow features, self-attention knowledge distillation strategies are introduced to FCN. Furthermore, we propose the multiscale feature change-aware module to integrate the globally changed information in different decoders. Finally, the model aggregates the multi-scale regional change information and outputs the prediction map. The results of comparative visual analysis and quantitative evaluation in two public datasets demonstrate that the proposed network model can improve the accuracy and efficiency of the automatic building change detection (85.69 IoU, 97.56 OA on the WHU dataset, and 83.72 IoU, 97.64 OA on the LEVIR-CD dataset).

Change detection on multimodal remote sensing images has become an increasingly interesting and challenging topic in the remote sensing community, which can play an essential role in time-sensitive applications, such as disaster response. However, the modal heterogeneity problem makes it difficult to compare the multimodal images directly. This paper proposes a Fourier domain structural relationship analysis framework for unsupervised multimodal change detection (FD-MCD), which exploits both modality-independent local and nonlocal structural relationships. Unlike most existing methods analyzing the structural relationship in the original domain of multimodal images, the three critical parts in the proposed framework are implemented on the (graph) Fourier domain. Firstly, a local frequency consistency metric calculated in the Fourier domain is proposed to determine the local structural difference. Then, the nonlocal structural relationship graphs are constructed for pre-change and post-change images. The two graphs are then transformed to the graph Fourier domain, and high-order vertex information is modeled for each vertex by graph spectral convolution, where the Chebyshev polynomial is applied as the transfer function to pass K-hop local neighborhood vertex information. The nonlocal structural difference map is obtained by comparing the filtered graph representations. Finally, an adaptive fusion method based on frequency-decoupling is designed to effectively fuse the local and nonlocal structural difference maps. Experiments conducted on five real datasets with different modality combinations and change events show the effectiveness of the proposed framework.

Automatic change detection is an important and difficult task in the field of remote sensing. In this study, a deep Siamese convolutional network based on the fusion of high- and low-level features is proposed for change detection in remote sensing images. Given that low-level features correspond to low-order ones (e.g., texture) that are sensitive to change and that high-level features can accurately reflect image category information (e.g., semantic information), we fuse these features to enhance the abstractness and robustness of the extracted features in the change detection framework. The whole system is end-to-end and does not require any pre- or post-processing. Experimental results on three datasets show that our method is superior to other advanced methods by adding a high- and low-level fusion framework.

Magnetic resonance imaging (MRI) provides noninvasive evaluation of patient's anatomy without using ionizing radiation. Due to this and the high soft-tissue contrast, MRI use has increased and has potential for use in longitudinal studies where changes in patients' anatomy or tumors at different time points are compared. Deformable image registration can be useful for these studies. Here, we describe two datasets that can be used to evaluate the registration accuracy of systems for MR images, as it cannot be assumed to be the same as that measured on CT images. Two sets of images were created to test registration accuracy. (a) A porcine phantom was created by placing ten 0.35-mm gold markers into porcine meat. The porcine phantom was immobilized in a plastic container with movable dividers. T1-weighted, T2-weighted, and CT images were acquired with the porcine phantom compressed in four different ways. The markers were not visible on the MR images, due to the selected voxel size, so they did not interfere with the measured registration accuracy, while the markers were visible on the CT images and were used to identify the known deformation between positions. (b) Synthetic images were created using 28 head and neck squamous cell carcinoma patients who had MR scans pre-, mid-, and postradiotherapy treatment. An inter- and intrapatient variation model was created using these patient scans. Four synthetic pretreatment images were created using the interpatient model, and four synthetic post-treatment images were created for each of the pretreatment images using the intrapatient model. The T1-weighted, T2-weighted, and CT scans of the porcine phantom in the four positions are provided. Four T1-weighted synthetic pretreatment images each with four synthetic post-treatment images, and four T2-weighted synthetic pretreatment images each with four synthetic post-treatment images are provided. Additionally, the applied deformation vector fields to generate the synthetic post-treatment images are provided. The data are available on TCIA under the collection MRI-DIR. The proposed database provides two sets of images (one acquired and one computer generated) for use in evaluating deformable image registration accuracy. T1- and T2-weighted images are available for each technique as the different image contrast in the two types of images may impact the registration accuracy.

Given a sample from an unknown probability distribution over strings, there exist algorithms for inferring the structure and parameters of stochastic grammatical representations of the unknown distribution, i.e. string grammars. Despite the fact that research on grammatical representations of sets of graphs has been conducted since the late 1960’s, almost no work has considered the possibility of stochastic graph grammars and no algorithms exist for inferring stochastic graph grammars from data. This paper presents PEGG, an algorithm for estimating the parameters of stochastic context-free graph grammars given a sample from an unknown probability distribution over graphs. It is established formally that for a certain class of graph grammars PEGG finds parameter estimates in polynomial time that maximize the likelihood of the data, and preliminary empirical results demonstrate that the algorithm performs well in practice.KeywordsGraph TransformationGraph GrammarMaximum Likelihood ParameterStart SymbolEstimate Maximum Likelihood ParameterThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Synthetic aperture radar (SAR) imaging can penetrate rain, snow, fog, and mist, providing an effective precipitation detector under a wide range of atmospheric conditions. This powerful technique operates under any weather conditions and can detect environmental changes or help in the evaluation of natural disasters. Multi-temporal change detection is important for monitoring disasters, but commonly applied wavelet transforms are not ideal for capturing change information. This paper presents a new multi-directional change detection (MDCD) method designed to improve the change detection accuracy using multiple SAR images. This method employs double-density dual-tree complex wavelet transforms (DDDT-CWT) theory, which allows the capture of multi-directional information. The MDCD method can provide information for 16 directions at any decomposed scale, which allows for change detection in multiple SAR images collected over time. We used the MDCD algorithm method to analyse SAR images from actual natural disasters and successfully identified environmental changes over time using SAR images.

Rotated object detection in aerial images is still challenging due to arbitrary orientations, large scale and aspect ratio variations, and extreme density of objects. Existing state-of-the-art rotated object detection methods mainly rely on angle-based detectors. However, angle-based detectors can easily suffer from a long-standing boundary problem. To tackle this problem, we propose a purely angle-free framework for rotated object detection, called Point RCNN. Point RCNN is a two-stage detector including both PointRPN and PointReg which are angle-free. Given an input aerial image, first, the backbone-FPN extracts hierarchical features, then, the PointRPN module generates an accurate rotated region of interests (RRoIs) by converting the learned representative points of each rotated object using the MinAreaRect function of OpenCV. Motivated by RepPoints, we designed a coarse-to-fine process to regress and refine the representative points for more accurate RRoIs. Next, based on the learned RRoIs of PointRPN, the PointReg module learns to regress and refine the corner points of each RRoI to perform more accurate rotated object detection. Finally, the final rotated bounding box of each rotated object can be attained based on the learned four corner points. In addition, aerial images are often severely unbalanced in categories, and existing rotated object detection methods almost ignore this problem. To tackle the severely unbalanced dataset problem, we propose a balanced dataset strategy. We experimentally verified that re-sampling the images of the rare categories can stabilize the training procedure and further improve the detection performance. Specifically, the performance was improved from 80.37 mAP to 80.71 mAP in DOTA-v1.0. Without unnecessary elaboration, our Point RCNN method achieved new state-of-the-art detection performance on multiple large-scale aerial image datasets, including DOTA-v1.0, DOTA-v1.5, HRSC2016, and UCAS-AOD. Specifically, in DOTA-v1.0, our Point RCNN achieved better detection performance of 80.71 mAP. In DOTA-v1.5, Point RCNN achieved 79.31 mAP, which significantly improved the performance by 2.86 mAP (from ReDet’s 76.45 to our 79.31). In HRSC2016 and UCAS-AOD, our Point RCNN achieved higher performance of 90.53 mAP and 90.04 mAP, respectively.