Multi-sensor Satellite Image Analysis Using Niche Genetic Algorithm for Flood Assessment

This paper investigates a new approach for flood evaluation based on multi-sensor satellite images utilizing swarm intelligence techniques. The swarm intelligence techniques used are Genetic Algorithm (GA) for image registration and Niche Particle Swarm Optimization (NPSO) for image clustering. Analysis of satellite images are applied in two stages: Linear Imaging Self Scanning Sensor (LISS-III) image acquired before-flood and Synthetic Aperture Radar (SAR) image acquired during-flood. In the first step, SAR image is aligned with LISS-III image using GA. The aligned SAR image (during-flood) is used to extract flooded and non-flooded regions where as LISS-III image (before-flood) is used to classify various land cover regions. For this image clustering is carried out where cluster centers are generated using the cluster splitting technique such as NPSO. The data points are grouped into their respective classes using the merging method. Further, the resultant images are overlaid to analyze the extent of the flood in individual land classes. The performance comparisons of these swarm intelligence techniques with conventional methods are presented.

This paper presents the algorithms and analysis results for delineating snow zones using active and passive microwave satellite remote sensing data. With a high-resolution Radarsat synthetic aperture radar (SAR) image mosaic, dry snow zones, percolation zones, wet snow zones, and blue ice patches for the Antarctic continent have been successfully delineated. A competing region growing and merging algorithm is used to initially segment the SAR images into a series of homogeneous regions. Based on the backscatter characteristics and texture property, these image regions are classified into different snow zones. The higher level of knowledge about the areal size of and adjacency relationship between snow zones is incorporated into the algorithms to correct classification errors caused by the SAR image noise and relief-induced radiometric distortions. Mathematical morphology operations and a line-tracing algorithm are designed to extract a vector line representation of snow-zone boundaries. With the daily passive microwave Special Sensor Microwave/Imager (SSM/I) data, dry and melt snow zones were derived using a multiscale wavelet-transform-based method. The analysis results respectively derived from Radarsat SAR and SSM/I data were compared and correlated. The complementary nature and comparative advantages of frequently repeated passive microwave data and spatially detailed radar imagery for detecting and characterizing snow zones were demonstrated

Aircraft classification in synthetic aperture radar (SAR) images plays a considerable role in global region management and surveillance. Recently, deep learning has been applied to solve the classification problem and made significant progress. Due to the imaging variability at different angles and component scattering discreteness in SAR images, previous works have had difficulty in achieving desirable classification results. To address these issues, we study the positional and semantic relationship between the scattering points and propose an innovative scattering topology network (ST-Net) in this article. First, considering the diversity of imaging results caused by different target attitude angles, we extract and transform the scattering cluster centers to update the information of various categories. It can guide the model to strengthen the discriminative features and mitigate the impact of imaging variability on classification performance. Second, a novel scattering topology module (STM) is introduced to model the spatial relationships and semantic information interaction of discrete scattering points. In this process, the topology relations and scattering characteristics are enhanced for further accurate classification. Third, context attention excitation (CAE) is designed to capture significant global and semantic information, which is conducive to suppressing background interference and reducing category confusion. In conclusion, the ST-Net is presented with the SAR imaging mechanism and the topology geometric representation of aircraft. We construct the SAR aircraft category dataset (SAR-ACD) and conduct extensive experiments on it to show the effectiveness of ST-Net, which illustrates that our method achieves superior classification performance.

This paper presents an unsupervised texture-based segmentation algorithm which uses reduced contourlet transform sub-bands and mean shift clustering, to analysis the texture information of high resolution SAR images. One step and criteria is proposed to reduce the sub-bands and other's is presented to decrease the number of dimension of the feature space. The mean shift clustering method is used to obtain the number of texture regions and the centre of the label class. Group the pixels into corresponding texture region by their simple distance to the class centre pixel. Experiments on a mixture of Brodatz texture and SAR images show the proposed algorithm of using contourlet transform and mean shift clustering gives satisfactory results.

Digital image processing is an important field in pattern recognition and computer vision, where the process of separating an object with the background acts as one of the crucial roles in executing image processing. This research will talk about mean shift algorithm implementation in processing a set of undersea images to see its effectiveness in separating the background with the object automatically based on pixel distribution and color intensity. How the mean shift algorithm works is by doing a reading process to find the center of a pixel cluster in an image before this algorithm starts to cluster or group pixels with similar characteristics. In this research, a set of image input will be used as a test under mean shift algorithm to give output of an optimal pixel segmentation or grouping, leading to a proof that the mean shift algorithm has the capability to separate a main object from the background, especially in images with intense and high contrast. Even so, in images with less intense and lower contrast, the segmentation is not as accurate. The image input will have to undergo some more pre-processing before the mean shift segmentation is implemented. This research outcome is that the mean shift algorithm is effective for segmenting marine animal images based on colors without having to initialize how many clusters as the conclusion where this method is applicable in many computer vision programs such as object detection or image pattern recognition.

In the context of earth observation, different sensors
\nhave been used to acquire satellite images and it becomes a
\nresearch topic about how to analyse and use multi-sensor images. In this paper, we carry out a study of multi-sensor satellite image indexing. The goal is to study which kind of satellite image provides more information for classification. To this end, we prepared four datasets covering four typical cities. Each dataset consists of three kinds of images: multispectral and panchromatic images from WoldView-2, Synthetic Aperture Radar (SAR) images from TerraSAR-X satellite. Image indexing is performed
\nat patch level with the same feature extraction method. The
\nindexing is carried out using an active learning system we
\ndeveloped before. A series of independent and joint indexing by combining the features have been performed. Through this study, we found that the indexing accuracy on SAR images is the worst. By contrast, the joint indexing by concatenating the features computed from each kind of image could provide best accuracy. Thus, we conclude that combing information from multi-sensor images could achieve better results than using each kind of image independently.

Ship target segmentation plays an important role in synthetic aperture radar (SAR) image interpretation. However, existing segmentation methods for marine SAR images have the problem of inaccurate edge segmentation, a concern for real-world applications. In this letter, we propose a clustering center shifted adaptive target segmentation (CCSATS) method. Firstly, the proposed clustering center shift method is used to update the clustering centers of each iteration, which can quickly and accurately capture ship pixels. Then, based on regional homogeneity coefficients, we define a new similarity measurement criterion with two adaptive weight factors to ensure the homogeneity of segmentation results. Finally, neighborhood patches are used to represent pixel information, which can reduce the influence of speckle noise and enhance the target edge fitting ability. Our segmentation results of measured SAR images show that the proposed method effectively ensures segmentation accuracy. Compared with other existing methods, the proposed target segmentation method achieves better edge capture performance.

A blind event-based learning algorithm for non-intrusive load disaggregation

Aims. We aim to investigate the relations between nuclear star clusters (NSCs) and their host galaxies and to offer a comparison between the structural properties of nucleated and non-nucleated galaxies. We also address the environmental influences on the nucleation of galaxies in the Fornax main cluster and the Fornax A group. Methods. We selected 557 galaxies (105.5 M⊙ < M*, galaxy < 1011.5 M⊙) for which structural decomposition models and non-parametric morphological measurements are available from our previous work. We determined the nucleation of galaxies based on a combination of visual inspection of galaxy images and residuals from multi-component decomposition models, as well as using a model selection statistic, the Bayesian information criterion (BIC), to avoid missing any faint nuclei. We also tested the BIC as an unsupervised method to determine the nucleation of galaxies. We characterised the NSCs using the nucleus components from the multi-component models conducted in the g′, r′, and i′ bands. Results. Overall, we find a dichotomy in the properties of nuclei that reside in galaxies more or less massive than M*, galaxy ≈ 108.5 M⊙. In particular, we find that the nuclei tend to be bluer than their host galaxies and follow a scaling relation of $ M_{\mathrm{*,nuc}} \propto {M_{\mathrm{*,galaxy}}}^{0.5} $ for M*, galaxy < 108.5 M⊙. In galaxies with M*, galaxy > 108.5 M⊙, we find redder nuclei compared to the host galaxy, which follows M*, nuc ∝ M*, galaxy. Comparing the properties of nucleated and non-nucleated early-type galaxies, we find that nucleated galaxies tend to be redder in global (g′−r′) colour, have redder outskirts relatively to their own inner regions (Δ(g′−r′)), are less asymmetric (A), and exhibit less scatter in the brightest second-order moment of light (M20) than their non-nucleated counterparts at a given stellar mass. However, with the exception of Δ(g′−r′) and the Gini coefficient (G), we do not find any significant correlations with cluster-centric distance. Yet, we find the nucleation fractions to be typically higher in the Fornax main cluster than in the Fornax A group, and that the nucleation fraction is highest towards the centre of their respective environments. Additionally, we find that the observed ultra-compact dwarf (UCD) fraction (i.e. the number of UCDs over the number of UCDs and nucleated galaxies) in Fornax and Virgo peaks at the cluster centre and is consistent with the predictions from simulations. Lastly, we find that the BIC can recover our labels of nucleation up to an accuracy of 97% without interventions. Conclusions. The different trends in NSC properties suggest that different processes are at play at different host stellar masses. A plausible explanation is that the combination of globular cluster in-spiral and in situ star formation play a key role in the build-up of NSCs. In addition, the environment is clearly another important factor in the nucleation of galaxies, particularly at the centre of the cluster where the nucleation and UCD fractions peak. Nevertheless, the lack of significant correlations with the structures of the host galaxies is intriguing. Finally, our exploration of the BIC as a potential method of determining nucleation have applications for large-scale future surveys, such as Euclid.

Abstract. Lagrangian cloud models (LCMs) are increasingly used in the cloud physics community. They not only enable a very detailed representation of cloud microphysics but also lack numerical errors typical for most other models. However, insufficient statistics, caused by an inadequate number of Lagrangian particles to represent cloud microphysical processes, can limit the applicability and validity of this approach. This study presents the first use of a splitting and merging algorithm designed to improve the warm cloud precipitation process by deliberately increasing or decreasing the number of Lagrangian particles under appropriate conditions. This new approach and the details of how splitting is executed are evaluated in box and single-cloud simulations, as well as a shallow cumulus test case. The results indicate that splitting is essential for a proper representation of the precipitation process. Moreover, the details of the splitting method (i.e., identifying the appropriate conditions) become insignificant for larger model domains as long as a sufficiently large number of Lagrangian particles is produced by the algorithm. The accompanying merging algorithm is essential to constrict the number of Lagrangian particles in order to maintain the computational performance of the model. Overall, splitting and merging do not affect the life cycle and domain-averaged macroscopic properties of the simulated clouds. This new approach is a useful addition to all LCMs since it is able to significantly increase the number of Lagrangian particles in appropriate regions of the clouds, while maintaining a computationally feasible total number of Lagrangian particles in the entire model domain.

In this work we present a mixed contextual algorithm for segmenting SAR-ERS 1 images (/spl copy/ ESA). The first step was to pre-process the original SAR image by means of a polynomial transform based filter in order to decrease the effect of speckle. Segmentation stage was performed as follows: cluster centers were obtained using a non-contextual algorithm; then, based on a Bayes classifier we achieved a first segmentation step, but defining a 'reject class'; finally, rejected pixels were e-classed via a Markovian model. Results obtained show segmented images exhibiting homogeneous regions and a minimal presence of isolated pixels. As well, they evidence that combined use of polynomial transform and Markov random field theory does not introduce a noticeable degradation of edges in segmented regions.

In the era of big data, text as an information reserve database is very important, in all walks of life. From humanities research to government decision-making, from precision medicine to quantitative finance, from customer management to marketing, massive text, as one of the most important information carriers, plays an important role everywhere. The text data generated in these practical problems of humanities research, financial industry, marketing, and other fields often has obvious domain characteristics, often containing the professional vocabulary and unique language patterns in these fields and often accompanied by a variety of “noise.” Dealing with such texts is a great challenge for the current technical conditions, especially for Chinese texts. A clustering algorithm provides a better solution for text big data information processing. Clustering algorithm is the main body of cluster analysis, K-means algorithm with its implementation principle is simple, low time complexity is widely used in the field of cluster analysis, but its K value needs to be preset, initial clustering center random selection into local optimal solution, other clustering algorithm, such as mean drift clustering, K-means clustering in mining text big data. In view of the problems of the above algorithm, this paper first extracts and analyzes the text big data and then does experiments with the clustering algorithm. Experimental conclusion: by analyzing large-scale text data limited to large-scale and simple data set, the traditional K-means algorithm has low efficiency and reduced accuracy, and the K-means algorithm is susceptible to the influence of initial center and abnormal data. According to the above problems, the K-means cluster analysis algorithm for data sets with large data volumes is analyzed and improved to improve its execution efficiency and accuracy on data sets with large data volume set. Mean shift clustering can be regarded as making many random centers move towards the direction of maximum density gradually, that is, moving their mean centroid continuously according to the probability density of data and finally obtaining multiple maximum density centers. It can also be said that mean shift clustering is a kernel density estimation algorithm.

With the advancements in Space technology and the development of light-weight Synthetic Aperture Radar (SAR) satellites by commercial companies such as ICEYE, Capella Space and Umbra, SAR images have become available on a wide scale. Ship detection is a classic problem in the interpretation and analysis of satellite images and has its significance both in maritime as well as defense applications. In the case of SAR images, ship detection becomes even more challenging due to the presence of large-scale distortions as well as inter-class similarity signature problem. Moreover, the State-of-the-Art (SOTA) object detection models have weak generalization capability over SAR datasets. To overcome these challenges, we propose a You Only Look Once (YOLO) based, optimized ship detection model called YOLO-OSD. Our optimized ship detector is based on a hybrid data-model centric approach which utilizes the statistical characteristics of the datasets under observation and has an efficient model architecture. We also carry out a detailed comparative analysis of our proposed model with other SOTA deep learning models on three well-known publicly available datasets. Our results show that the proposed YOLO-OSD outperforms YOLO5, YOLO7 and RetinaNet on all datasets under observation in terms of F1 score and mean Average Precision (mAP). YOLO-OSD also has approximately 16% fewer network parameters as compared to the original YOLO5. Moreover, our proposed model is at least 37.7% faster than YOLO7 and 41.02% faster than the YOLO8 model in terms of training time and thus suitable for real-time satellite based SAR ship detection.

Considering the clustering algorithms could explore the label information automatically, this paper proposes a new method in terms of polarimetric synthetic aperture radar (POLSAR) image classification, which named a clustering-wishart-auto-encoder (WAE) classification model. With considering the statistical distribution characteristic of the POLSAR image, the WAE classification model, which proposed by ourselves, could improve the classification performance of the POLSAR image to some extent. The clustering-WAE classification model, that embedded the K-means clustering algorithm into the objective function of the WAE model, has the ability to improve the network performance. Our proposed method could minimize the difference of intra-class data and maximize the difference of inter-class data, from which the obtained POLSAR image features will be more compact to their corresponding cluster centers. Via simultaneously considering the compactness and statistical distribution of data, our method is capable of improving the POLSAR image classification results. The effectiveness of our proposed classification model has been demonstrated on four real POLSAR data sets.

In order to solve the challenge that are caused by the traditional k-means algorithm such as local optimal solution, initial value selection with randomness, sensitivity to outlier. An improved K-means clustering algorithm based on density radius was proposed. First, remove the outliers in the dataset according to the Local outlier factor (lof). Then calculate the sample point density within the sample point density radius, and the initial cluster center and k value are selected and determined according to the density. After that according to the traditional K-means thoughts to cluster and get new clusters center. Finally, a k-value optimization strategy based on Bayesian Information Criterion (BIC) score is proposed to optimize the k-value and effectively improve the clustering quality. The theoretical analysis and simulation results show that the improved algorithm improves accuracy.