Large Size Images Research Articles

Solar Power Prediction Based on Satellite Measurements – A Graphical Learning Method for Tracking Cloud Motion

The stochastic cloud cover on photovoltaic (PV) panels affects the solar power outputs, producing high instability in the integrated power systems. It is an effective approach to track the cloud motion during short-term PV power forecasting based on data sources of satellite images. However, since temporal variations of these images are noisy and non-stationary, pixel-sensitive prediction methods are critically needed in order to seek a balance between the forecast precision and the huge computation burden due to a large image size. Hence, a graphical learning framework is proposed in this study for intra-hour PV power prediction. By simulating the cloud motion using bi-directional extrapolation, a directed graph is generated representing the pixel values from multiple frames of historical images. The nodes and edges in the graph denote the shapes and motion directions of the regions of interest (ROIs) in satellite images. A spatial-temporal graph neural network (GNN) is then proposed to deal with the graph. Comparing with conventional deep-learning-based models, GNN is more flexible for varying sizes of input, in order to be able to handle dynamic ROIs. Referring to the comparative studies, the proposed method greatly reduces the redundancy of image inputs without sacrificing the visual scope, and slightly improves the prediction accuracy.

Robust 2D and 3D images zero - watermarking using dual Hahn moment invariants and Sine Cosine Algorithm.

In this paper, we initially provide significant improvements on the computational aspects of dual Hahn moment invariants (DHMIs) in both 2D and 3D domains. These improvements ensure the numerical stability of DHMIs for large-size images. Then, we propose an efficient method for optimizing the local parameters of dual Hahn polynomials (DHPs) when computing DHMIs using the Sine-Cosine Algorithm (SCA). DHMIs optimized via SCA are used to propose new and robust zero-watermarking scheme applied to both 2D and 3D images. On one hand, the simulation results confirm the efficiency of the proposed computation of 2D and 3D DHMIs regarding the numerical stability and invariability. Indeed, the proposed computation method of 2D DHMIs allows to reach a relative error (RE) of the order ≈10−10 for images of size 1024 × 1024 with an execution time improvement ratio exceeds 70% (ETIR ≥ 70%), which validates the efficiently of the proposed computation method. On the other hand, the simulation and comparison outcomes clearly demonstrate the robustness of the proposed zero-watermarking scheme against various geometric attacks (translation, rotation, scaling and combined transformations), as well as against other common 2D and 3D image processing attacks (compression, filtering, noise addition, etc.).Graphical abstract

A Larger Capacity Data Hiding Scheme Based on DNN

With the in-depth research in data hiding technology, the latest data hiding schemes using deep neural network (DNN) could hide the full-size color image into the same size color image. This paper proposed a larger capacity data hiding scheme based on DNN, which could hide large-size color image into small-size color image. This scheme used DNN in both the data hiding stage and data extraction stage. And the two networks were obtained through adversarial training and used in pairs. The information ratio between the carrier image and the secret image had reached 1 : 4. The image obtained after hiding the data did not change much compared with the carrier image, and the extracted image had the same size and no visual difference compared with the secret image. It could be seen from the simulation experiment that, compared with the existing DNN-based data hiding scheme, even if the capacity of the proposed scheme was 4 times larger than that of the existing scheme, the visual effect and PSNR were also better than some existing schemes.

Uncertainty-Guided Depth Fusion from Multi-View Satellite Images to Improve the Accuracy in Large-Scale DSM Generation

The generation of digital surface models (DSMs) from multi-view high-resolution (VHR) satellite imagery has recently received a great attention due to the increasing availability of such space-based datasets. Existing production-level pipelines primarily adopt a multi-view stereo (MVS) paradigm, which exploit the statistical depth fusion of multiple DSMs generated from individual stereo pairs. To make this process scalable, these depth fusion methods often adopt simple approaches such as the median filter or its variants, which are efficient in computation but lack the flexibility to adapt to heterogenous information of individual pixels. These simple fusion approaches generally discard ancillary information produced by MVS algorithms (such as measurement confidence/uncertainty) that is otherwise extremely useful to enable adaptive fusion. To make use of such information, this paper proposes an efficient and scalable approach that incorporates the matching uncertainty to adaptively guide the fusion process. This seemingly straightforward idea has a higher-level advantage: first, the uncertainty information is obtained from global/semiglobal matching methods, which inherently populate global information of the scene, making the fusion process nonlocal. Secondly, these globally determined uncertainties are operated locally to achieve efficiency for processing large-sized images, making the method extremely practical to implement. The proposed method can exploit results from stereo pairs with small intersection angles to recover details for areas where dense buildings and narrow streets exist, but also to benefit from highly accurate 3D points generated in flat regions under large intersection angles. The proposed method was applied to DSMs generated from Worldview, GeoEye, and Pleiades stereo pairs covering a large area (400 km2). Experiments showed that we achieved an RMSE (root-mean-squared error) improvement of approximately 0.1–0.2 m over a typical Median Filter approach for fusion (equivalent to 5–10% of relative accuracy improvement).

Bone anatomical landmark localization with cascaded spatial configuration network

Accurate localization of bone anatomical landmarks in medical images is of great significance for decision-making in surgical plans and orthopedic surgery visual navigation systems development. However, due to the high dimensionality and large size of medical images, current automatic anatomical landmarks detection methods still have issues in terms of accuracy, robustness, and efficiency. To improve the accuracy of bone anatomical landmark detection in medical images, a new network model with a two-step strategy (coarse localizing and fine localizing) was proposed in this study. By combining fully convolutional neural networks and the heatmap regression model, a cascaded spatial configuration network was designed to combine the global and local features of 3D image features and localize anatomical landmarks stepwise. The model was evaluated with a collected knee CT image dataset and a published spine CT image dataset. The results were compared to existing state-of-the-art models. The proposed method outperformed other models with an average error of 1.31 mm for knee landmarks and 5.31 mm for the localization of spine landmarks. The outlier rates at error radius 3 mm, 5 mm, and 7 mm are also smaller compared with other models, indicating good robustness of the model. Our proposed method provides a new neural network model with reasonably good accuracy and robustness with a limited computational cost for landmark localization tasks.

Attention recurrent residual U-Net for predicting pixel-level crack widths in concrete surfaces

Cracks in concrete structures are one of the most important indicators of structural damage, and it is a necessity to detect and measure cracks for ensuring safety and integrity of concrete structures. The widely practised approach in inspecting the structures is by performing visual inspections followed by manual estimation of crack widths. This approach is not only time-consuming, laborious, and time-intensive but also prone to subjective errors and inefficient. To address these issues, we propose a novel deep learning framework for detecting cracks and then estimating crack widths in concrete surface images. Our framework handles both small- and large-sized images and provides a prediction of crack width at locations specified by the user. The proposed framework uses Attention Recurrent Residual U-Net (Attention R2U-Net) with Random Forest regressor to predict crack width with the mean prediction error of ±0.31 mm for crack widths varying from 0 to 8.95 mm and produces the lowest absolute maximum error of 1.3 mm. Our model has a coefficient of determination (R2) of 0.91, showing a non-linear mapping function with low prediction errors. We compare our model with a combination of four other segmentation models and regression models. Our proposed model has superior performance compared to other models, and one can easily adopt our framework to a variety of Structural Health Monitoring applications using Internet of Things sensors.

A Transformer-Based Coarse-to-Fine Wide-Swath SAR Image Registration Method under Weak Texture Conditions

As an all-weather and all-day remote sensing image data source, SAR (Synthetic Aperture Radar) images have been widely applied, and their registration accuracy has a direct impact on the downstream task effectiveness. The existing registration algorithms mainly focus on small sub-images, and there is a lack of available accurate matching methods for large-size images. This paper proposes a high-precision, rapid, large-size SAR image dense-matching method. The method mainly includes four steps: down-sampling image pre-registration, sub-image acquisition, dense matching, and the transformation solution. First, the ORB (Oriented FAST and Rotated BRIEF) operator and the GMS (Grid-based Motion Statistics) method are combined to perform rough matching in the semantically rich down-sampled image. In addition, according to the feature point pairs, a group of clustering centers and corresponding images are obtained. Subsequently, a deep learning method based on Transformers is used to register images under weak texture conditions. Finally, the global transformation relationship can be obtained through RANSAC (Random Sample Consensus). Compared with the SOTA algorithm, our method’s correct matching point numbers are increased by more than 2.47 times, and the root mean squared error (RMSE) is reduced by more than 4.16%. The experimental results demonstrate that our proposed method is efficient and accurate, which provides a new idea for SAR image registration.

Whole slide image registration via multi-stained feature matching

In the recent decade, medical image registration and fusion process has emerged as an effective application to follow up diseases and decide the necessary therapies based on the conditions of patient. For many of the considerable diagnostic analyses, it is common practice to assess two or more different histological slides or images from one tissue sample. A specific area analysis of two image modalities requires an overlay of the images to distinguish positions in the sample that are organized at a similar coordinate in both images. In particular cases, there are two common challenges in digital pathology: first, dissimilar appearances of images resulting due to staining variances and artifacts; second, large image size. In this paper, we develop algorithm to overcome the fact that scanners from different manufacturers have variations in the images. We propose whole slide image registration algorithm where adaptive smoothing is employed to smooth the stained image. A modified scale-invariant feature transform is applied to extract common information and a joint distance helps to match keypoints correctly by eliminating position transformation error. Finally, the registered image is obtained by utilizing correct correspondences and the interpolation of color intensities. We validate our proposal using different images acquired from surgical resection samples of lung cancer (adenocarcinoma). Extensive feature matching with apparently increasing correct correspondences and registration performance on several images demonstrate the superiority of our method over state-of-the-art methods. Our method potentially improves the matching accuracy that might be beneficial for computer-aided diagnosis in biobank applications.

Bone anatomical landmark localization with cascaded spatial configuration network

Abstract Accurate localization of bone anatomical landmarks in medical images is of great significance for decision-making in surgical plans and orthopedic surgery visual navigation systems development. However, due to the high dimensionality and large size of medical images, current automatic anatomical landmarks detection methods still have issues in terms of accuracy, robustness, and efficiency. To improve the accuracy of bone anatomical landmark detection in medical images, a new network model with a two-step strategy (coarse localizing and fine localizing) was proposed in this study. By combining fully convolutional neural networks and the heatmap regression model, a cascaded spatial configuration network was designed to combine the global and local features of 3D image features and localize anatomical landmarks stepwise. The model was evaluated with the collected knee CT image dataset and published spine CT image dataset. The results were compared to existing state-of-the-art models. The proposed method outperformed other models with an average error of 1.31 mm for knee landmarks and 5.31 mm for the localization of spine landmarks. The outlier rates at error radius 3mm, 5mm, and 7mm are also smaller compared with other models, indicating good robustness of the model. Our proposed method provides a new neural network model with reasonably good accuracy and robustness with a limited computational cost for landmark localization tasks.

A partial image encryption scheme based on DWT and texture segmentation

nowadays, image encryption is an interesting research area due to the rapid growth of communication technologies and the increasing demands for safeguarding the privacy of the transmitted images as unencrypted images are vulnerable to interception. Partial encryption is used to overcome the challenge of encryption the large size of digital images, due to the large computational overhead and long processing time needed. In this research, one level Discrete Wavelet Transform is applied to a colored image to divide the image to four sub-bands; then a texture segmentation using a Gabor filter and K-means clustering is applied to lowest frequency band. To achieve that, the texture segmentation is used as a new method for scrambling the image based on the features of another image. Finally, the scrambled segments of the image are encrypted using interchanged AES and RC4 Algorithms. Each one of the image pixels is then XORed using one of the two algorithms and the key of the other algorithm. The proposed work is evaluated using several security and performance analysis tests. The results show that the proposed work is resistant agents many kinds of attack and promising in real-time image transmission and encryption.

Spine Image Segmentation Based on U-Net and Atrous spatial pyramid pooling

In the past ten years, deep learning has achieved remarkable results in the area of natural image segmentation, and has gradually turned to the field of medical image segmentation. The precise segmentation of spine images can be used for early screening of spondylopathy, which is convenient for early detection and treatment of patients. Aiming at the segmentation of the spine image by the U-Net network, which structure will lead to large model calculation, network overfitting, image size, noise information and other issues. This paper introduces a new method based on spatial pyramid pooling module ASpp on U-Net network and applies the proposed network structure to the segmentation of the spine image. The model is first enhanced by the Spp module and Densenet data; secondly, the U-Net encoding and decoding structure is adopted, and the deep separable convolution is used. This method greatly reduces the complexity and computation of the model, and uses a rectangular convolution kernel to increase the computation of the model in a small amount. Based on the volume, the receptive field of the convolution operation is expanded; finally, in order to effectively enhance the segmentation area of the image, the SE-Net attention mechanism module is added to the lateral connection. The method proposed in this paper conducts ablation experiments on a public dataset of spine images and compares it with the U-Net network. The method proposed IOU in this paper can reach 72%, and the F1-score can reach 0.92. The comparison of the experimental results of spine medical image datasets shows that the method proposed in this paper can effectively improve the accuracy and accuracy of spine image segmentation.

Ultra-compact 3D-printed wide-angle cameras realized by multi-aperture freeform optical design.

Simultaneous realization of ultra-large field of view (FOV), large lateral image size, and a small form factor is one of the challenges in imaging lens design and fabrication. All combined this yields an extensive flow of information while conserving ease of integration where space is limited. Here, we present concepts, correction methods and realizations towards freeform multi-aperture wide-angle cameras fabricated by femtosecond direct laser writing (fsDLW). The 3D printing process gives us the design freedom to create 180° × 360° cameras with a flat form factor in the micrometer range by splitting the FOV into several apertures. Highly tilted and decentered non-rotational lens shapes as well as catadioptric elements are used in the optical design to map the FOV onto a flat surface in a Scheimpflug manner. We present methods to measure and correct freeform surfaces with up to 180° surface normals by confocal measurements, and iterative fabrication via fsDLW. Finally, approaches for digital distortion correction and image stitching are demonstrated and two realizations of freeform multi-aperture wide-angle cameras are presented.

Study on the Cytotoxic Microstructure of Titanium Dioxide Nanoparticles by X-Ray Phase-Contrast CT Imaging.

To address the problem of microstructural analysis of titania nanoparticles with high cytotoxicity, the authors propose X-ray phase-comparative CT imaging studies. In this method, the HE-stained section samples were compared with the X-ray phase-contrast CT imaging microscopic images, and 3D texture analysis was used to observe the changes in the preparation of hepatocyte microstructures in the two groups. The results show that X-ray phase-contrast CT imaging microscopic images and their larger image size are closely related to HE staining images, and X-ray phase-contrast CT microscopic images can observe important data of hepatocytes from multiple angles. The ship skeleton extraction method based on the endpoint limit also has advantages over traditional algorithms in extraction accuracy and can provide more 3D feature files, confirming the growth and transformation of normal hepatocytes into hepatocyte cytotoxic microstructures. The distribution effect of using the ensemble process is better than the simple 2D feature set and 3D feature set, and the overall accuracy is improved; the result distribution of the tree determination and random forest methods is also better than that of the support vector machine method. The experimental results show that the X-ray phase-contrast CT images can highlight the 2D and 3D imaging features of the hepatotoxic microstructure of TiO2 nanoparticles and provide data for quantitative analysis.

Align Deep Features for Oriented Object Detection

The past decade has witnessed significant progress on detecting objects in aerial images that are often distributed with large-scale variations and arbitrary orientations. However, most of existing methods rely on heuristically defined anchors with different scales, angles, and aspect ratios, and usually suffer from severe misalignment between anchor boxes (ABs) and axis-aligned convolutional features, which lead to the common inconsistency between the classification score and localization accuracy. To address this issue, we propose a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">single-shot alignment network</i> (S <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> A-Net) consisting of two modules: a feature alignment module (FAM) and an oriented detection module (ODM). The FAM can generate high-quality anchors with an anchor refinement network and adaptively align the convolutional features according to the ABs with a novel alignment convolution. The ODM first adopts active rotating filters to encode the orientation information and then produces orientation-sensitive and orientation-invariant features to alleviate the inconsistency between classification score and localization accuracy. Besides, we further explore the approach to detect objects in large-size images, which leads to a better trade-off between speed and accuracy. Extensive experiments demonstrate that our method can achieve the state-of-the-art performance on two commonly used aerial objects’ data sets (i.e., DOTA and HRSC2016) while keeping high efficiency.

Cohesion Intensive Hash Code Book Coconstruction for Efficiently Localizing Sketch Depicted Scenes

We investigate the problem of efficiently localizing sketch depicted scenes in a remote sensing image dataset. We pose the problem as that of remote sensing image retrieval with sketch queries and explore the use of hashing techniques to achieve efficient retrieval. Given two training datasets of sketches and remote sensing images that have a common set of class labels, we develop a hashing strategy that coconstructs two hash code books for the sketches and the remote sensing images separately. The hash code book coconstruction strategy encourages hash codes for the sketches and remote sensing images from different classes to be far away from one another and those from the same class to be close. This property is maintained by two cohesion intensive cues: 1) an interclass pairwise disperse cue (InterPDC) and 2) an intraclass pairwise balance cue (IntraPBC). We use the two coconstructed hash code books for training two linear mapping models that generate hash codes for sketches and remote sensing images separately. Sorting the Hamming distance between the sketch hash codes and the remote sensing image hash codes renders efficient remote sensing image retrieval with sketch queries. This enables localizing the sketch depicted scenes in the remote sensing image dataset. In addition, our method can also be used for fast localizing sketch depicted scenes in a remote sensing image of large size. Extensive experiments on public datasets validate the effectiveness and efficiency of our method.

Peaberry and normal coffee bean classification using CNN, SVM, and KNN: Their implementation in and the limitations of Raspberry Pi 3

&lt;abstract&gt; &lt;p&gt;Peaberries are a special type of coffee bean with an oval shape. Peaberries are not considered defective, but separating peaberries is important to make the shapes of the remaining beans uniform for roasting evenly. The separation of peaberries and normal coffee beans increases the value of both peaberries and normal coffee beans in the market. However, it is difficult to sort peaberries from normal beans using existing commercial sorting machines because of their similarities. In previous studies, we have shown the availability of image processing and machine learning techniques, such as convolutional neural networks (CNNs), support vector machines (SVMs), and k-nearest-neighbors (KNNs), for the classification of peaberries and normal beans using a powerful desktop PC. As the next step, assuming the use of our system in the least developed countries, this study was performed to examine their implementation in and the limitations of Raspberry Pi 3. To improve the performance, we modified the CNN architecture from our previous studies. As a result, we found that the CNN model outperformed both linear SVM and KNN on the use of Raspberry Pi 3. For instance, the trained CNN could classify approximately 13.77 coffee bean images per second with 98.19% accuracy of the classification with 64×64 pixel color images on Raspberry Pi 3. There were limitations of Raspberry Pi 3 for linear SVM and KNN on the use of large image sizes because of the system's small RAM size. Generally, the linear SVM and KNN were faster than the CNN with small image sizes, but we could not obtain better results with both the linear SVM and KNN than the CNN in terms of the classification accuracy. Our results suggest that the combination of the CNN and Raspberry Pi 3 holds the promise of inexpensive peaberries and a normal bean sorting system for the least developed countries.&lt;/p&gt; &lt;/abstract&gt;

Concept Bottleneck Model With Additional Unsupervised Concepts

With the increasing demands for accountability, interpretability is becoming an essential capability for real-world AI applications. However, most methods utilize post-hoc approaches rather than training the interpretable model. In this article, we propose a novel interpretable model based on the concept bottleneck model (CBM). CBM uses concept labels to train an intermediate layer as the additional visible layer. However, because the number of concept labels restricts the dimension of this layer, it is difficult to obtain high accuracy with a small number of labels. To address this issue, we integrate supervised concepts with unsupervised ones trained with self-explaining neural networks (SENNs). By seamlessly training these two types of concepts while reducing the amount of computation, we can obtain both supervised and unsupervised concepts simultaneously, even for large-sized images. We refer to the proposed model as the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">concept bottleneck model with additional unsupervised concepts</i> ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CBM-AUC</i> ). We experimentally confirmed that the proposed model outperformed CBM and SENN. We also visualized the saliency map of each concept and confirmed that it was consistent with the semantic meanings.

Distortion correction for wide angle holographic projector

This letter presents distortion correction method enabling distortion minimized, large size image in wide angle holographic projector. The technique applies numerical predistortion of an input image used for hologram generation. It is based on estimation of distortion coefficients by comparing optically reconstructed point test chart with the original one. Obtained experimental results prove that the technique allows reconstruction of high-quality image. Full Text: PDF ReferencesM. Makowski, Experimental Aspects of Holographic Projection with a Liquid-Crystal-on-Silicon Spatial Light Modulator, in Holographic Materials and Optical Systems, M. Kumar, ed. (IntechOpen, 2019). CrossRef H. Pang, A. Cao, W. Liu, L. Shi, and Q. Deng, "Effective method for further magnifying the image in holographic projection under divergent light illumination", Appl. Opt. 58, 8713 (2019). CrossRef Y. Qi, C. Chang, and J. Xia, "Speckleless holographic display by complex modulation based on double-phase method", Opt. Express 24, 30368 (2016). CrossRef E. Buckley, "Holographic Laser Projection", J. Display Technol. 99, 1 (2010). DirectLink M. Chlipała, T. Kozacki, H. Yeom, J. Martinez-Carranza, R. Kukołowicz, J. Kim, J. Yang, J. Choi, J. Pi, and C. Hwang, "Wide angle holographic video projection display", Opt. Lett. 46, 4956 (2021). CrossRef Z. He, X. Sui, L. Cao and G. Jin, "Image-Distortion Correction Algorithm for Computer-Generated Holographic Display," 2018 IEEE 27th International Symposium on Industrial Electronics (ISIE), 1331 (2018). CrossRef A. Kaczorowski, G.S. Gordon, A. Palani, S. Czerniawski and T.D. Wilkinson, "Optimization-Based Adaptive Optical Correction for Holographic Projectors", J. Display Technol. 11(7), 596 (2015). CrossRef Z. He, X. Sui, G. Jin, L. Cao, "Distortion-Correction Method Based on Angular Spectrum Algorithm for Holographic Display", IEEE Trans. Industr. Inform. 15, 6162 (2019). CrossRef O. Mendoza-Yero, G. Mínguez-Vega, and J. Lancis, "Encoding complex fields by using a phase-only optical element", Opt. Lett. 39, 1740 (2014). CrossRef T. Kozacki, K. Falaggis, "Angular spectrum method with compact space–bandwidth: generalization and full-field accuracy", Appl. Opt. 55, 5014 (2016). CrossRef

Novel Video Surveillance-Based Fire and Smoke Classification Using Attentional Feature Map in Capsule Networks.

A fire is an extraordinary event that can damage property and have a notable effect on people’s lives. However, the early detection of smoke and fire has been identified as a challenge in many recent studies. Therefore, different solutions have been proposed to approach the timely detection of fire events and avoid human casualties. As a solution, we used an affordable visual detection system. This method is possibly effective because early fire detection is recognized. In most developed countries, CCTV surveillance systems are installed in almost every public location to take periodic images of a specific area. Notwithstanding, cameras are used under different types of ambient light, and they experience occlusions, distortions of view, and changes in the resulting images from different camera angles and the different seasons of the year, all of which affect the accuracy of currently established models. To address these problems, we developed an approach based on an attention feature map used in a capsule network designed to classify fire and smoke locations at different distances outdoors, given only an image of a single fire and smoke as input. The proposed model was designed to solve two main limitations of the base capsule network input and the analysis of large-sized images, as well as to compensate the absence of a deep network using an attention-based approach to improve the classification of the fire and smoke results. In term of practicality, our method is comparable with prior strategies based on machine learning and deep learning methods. We trained and tested the proposed model using our datasets collected from different sources. As the results indicate, a high classification accuracy in comparison with other modern architectures was achieved. Further, the results indicate that the proposed approach is robust and stable for the classification of images from outdoor CCTV cameras with different viewpoints given the presence of smoke and fire.

Multiscale framework for rapid change analysis from SAR image time series: Case study of flood monitoring in the central coast regions of Vietnam

Recently, the frequency of natural and environmental disasters has increased significantly, causing constant changes on the Earth's surface. Synthetic Aperture Radar (SAR) data have been proved to be useful for operational change monitoring tasks. The multiscale framework presented in this paper aims at detecting and analyzing changes using SAR image time series composed of large-size images. Spatio-temporal changes are initially detected at the subimage scale analysis stage to determine regions and image acquisition dates related to the change occurrence. Detailed changes are then identified at the pixel scale analysis stage between selected acquisitions at each recognized region. This framework was used for flood monitoring over a large area along the central coast of Vietnam (from Thua Thien Hue province to Quang Nam province). We exploited a Sentinel-1 image time series acquired during two rainy seasons and typhoon seasons in the Western Pacific (from September to December of the two years 2017 and 2018). The proposed framework detected flooded areas with a high overall accuracy of 90.4% and could analyze different types of changes that occurred in this time series, i.e. dirac, periodic, chaotic changes, and temporal stability.