Search

Environmental images that are captured by satellites can provide significant information for weather forecasting, climate warning, and so on. This article introduces a novel deep neural network that integrates a convolutional attention feature extractor (CAFE) in a recurrent neural network frame and a multivariate dynamic time warping (MDTW) loss. The CAFE module is designed to capture the complicated and hidden dependencies within image series between the source variable and the target variable. The proposed method can reconstruct the image series across environmental variables. The performance of the proposed method is validated by experiments using a real-world remote sensing dataset and compared with several representative methods. Experimental results demonstrate the emerging performance of the proposed method for cross-variable image series reconstruction. [ABSTRACT FROM AUTHOR]

In order to make ecotoxicological studies using bird embryos simpler and more cost effective, kinetic imaging, already proven in human medicine, was tested. In the study, a total of 8 still-living embryos were examined non-invasively with low-intensity (50 keV) X-rays. During the measurement, we tried to assess how the embryos react if they are not stored at the temperature of 38 °C required for hatching for 1 hour.

Modern monitoring and operational decision-making systems based on image series have become widely used for a wide variety of applications. At the stage of identification of graphic images, the affiliation of the found dynamic object to the class of objects of interest is established on the basis of a comparative analysis of its contours with a given template. The article continues the cycle of research in which the identification process is considered and the algorithm of machine graphics is given. A description of the interaction of the structural components of the video analytics system is presented. [ABSTRACT FROM AUTHOR]

Environmental images that are captured by satellites can provide significant information for weather forecasting, climate warning, and so on. This article introduces a novel deep neural network that integrates a convolutional attention feature extractor (CAFE) in a recurrent neural network frame and a multivariate dynamic time warping (MDTW) loss. The CAFE module is designed to capture the complicated and hidden dependencies within image series between the source variable and the target variable. The proposed method can reconstruct the image series across environmental variables. The performance of the proposed method is validated by experiments using a real-world remote sensing dataset and compared with several representative methods. Experimental results demonstrate the emerging performance of the proposed method for cross-variable image series reconstruction.

Modern monitoring and operational decision-making systems based on image series have become widely used for a wide variety of applications. At the stage of identification of graphic images, the affiliation of the found dynamic object to the class of objects of interest is established on the basis of a comparative analysis of its contours with a given template. The identification process is considered and the algorithm of machine graphics is given, including, firstly, image preprocessing using the Gauss smoothing operator, secondly, the search for object boundaries using the Kenny operator, thirdly, image post-processing for interpolation of the obtained discontinuous contours of the object using mathematical morphology operations and local processing of a set of contours. [ABSTRACT FROM AUTHOR]

This narrative review article was conducted to lay out a summarized but exhaustive review of current literature over mucocutaneous manifestations in 4 dimensions of SARS‐CoV‐2 pandemic: virus itself, treatment‐related, vaccine‐induced, and alteration of chronic dermatologic diseases following infection. Virus and vaccine‐related were mainly self‐limited and non‐severe. Treatment‐related reactions could be life‐threatening. [ABSTRACT FROM AUTHOR]

Modern monitoring and operational decision-making systems based on image series have become widely used for a wide variety of applications. Among such systems, we will single out real-time monitoring, the requirements for an image processing system in which are very strict. At the same time, the traditionally high complexity of images is in contradiction with the need for fast processing. One of the ways to resolve the contradiction is to represent a series of images as a sequence of additions and changes to the previous image in the next. An important component of such a representation is the search for motion vectors and the corresponding algorithms for searching for such vectors. A new algorithm based on an analytical solution is obtained and provides a multiple compression ratio by eliminating the temporary redundancy of data determined by a high correlation between adjacent frames of video sequences. [ABSTRACT FROM AUTHOR]

High-resolution satellite imaging represents a potentially effective technique to monitor cyclone-caused environmental damage and recovery over large areas at a high spatial scale. This study utilized a 10-m resolution Sentinel satellite image series to document vegetation changes in a portion of the Florida Keys, USA, over which the core of Category 4 Hurricane Irma passed on 10 September 2017. A previously assembled field survey was used to establish land-cover patterns in the satellite data, and concurrent field measurements verified post-hurricane changes. Normalized difference vegetation index (NDVI) was utilized as a tracer for pre-storm baseline patterns and through 19 post-storm months. NDVI patterns show that the severity of vegetation damage varied appreciably across the area, with the least damage on islands in the western sector of the hurricane's eye and around its center, and greatest damage on islands just east of the eye. The data reveal that for 2.5 months after the storm, multiple inland vegetation classes showed substantial early regrowth. However, mangrove forests were more negatively affected. The storm caused extensive mortality of black mangrove (Avicennia germinans) and red mangrove (Rhizophora mangle), corresponding to more than 40% of the total mangrove area on some islands. The full extent of mangrove die-off was not immediately evident, and increased progressively through the first few months after the storm. In addition to demonstrating the utility of high-resolution satellite image series for post-hurricane environmental assessment, this study reveals high-resolution links between vegetation types, their location within the cyclone, and the extent of post-storm recovery. [ABSTRACT FROM AUTHOR]

Although modern reconstruction methods have advanced considerably, their ability to retrieve fine details, small features of a surface is limited. Applying texture can be used to conceal lack of geometry to some extent, but it becomes apparent when lighting varies. A more sophisticated solution is to map normal vectors to the surface of the model in order to alter the way it is rendered under different illuminations in accordance with the properties of the real object. The principle of photometric stereo is to reconstruct normals from a series of images. By illuminating the object with different directional light sources local surface orientation can be inferred. The contribution of this study is that the authors successfully applied the widely used bundle adjustment algorithm to photometric stereo problems when non‐parallel light rays illuminate the objects.

In this paper, we propose a new color image encryption method using color scrambling based on the chaotic permutation multiple circular shrinking and expanding (CPMCS/ CPMCE). The plain color image with a size of m x n x 3 is arranged in two-dimensional array, where each row consists of the Red, Green, and Blue (RGB) component, forming two-dimensional array with a size of m x 3n. The arranged 2D array then permuted by CPMCS for the each row and column. To reconstruct the original image, the ciphered image is arranged in 2D array then is permuted by CPMCE for each column and row. The proposed method is characterized by very high key space that reaches 2 for an image size of 256x256, so that resistance to brute force attack and can anticipate the emergence of quantum computers. It also resistant to a differential attack due to change a single bit in the plain image causes a significant change in the ciphered image. The proposed encryption also yield completely difference ciphered image series from the same plain image just using arbitrary increment sequence key. It is also robust to JPEG compression so the ciphered image can be stored in smaller size, such as for the ciphered Lena image only needs 1/5.2 of the original one when compressed using JPEG 70 %. It also resistant to noise scheme (Gaussian, Poisson, Salt&Pepper, and spekle), data loss, and brightness-contrast adjustment, so the ciphered image can be transmitted in a non error free communication system. [ABSTRACT FROM AUTHOR]

This paper is devoted to the problem of reflecting visual image (iconic) presentations in intelligent systems. The problems of the role played by visual images in medical diagnostics are considered. Different aspects of the formation of image series (fuzzy, associative, and dynamic) are analyzed. The variants of building the frames that include linguistic and image visual components are suggested. The possibility that images can be involved at different steps of decision making is considered. [ABSTRACT FROM AUTHOR]

Abstract: Image series are increasingly being used to output ecological indicators because they provide the ability to reanalyze data that has already been collected and they improve temporal as well as spatial resolution. We address both the increased utilization and the need to diversify the way they are produced by introducing an open source Python (www.python.org) library called EcoIS that creates image series from unaligned pictures of specially equipped plots. We use EcoIS to sample flowering phenology plots in a high arctic environment and create image series that later generate phenophase counts and automatically estimate phenological dates of interest. Our results exhibit one day difference between EcoIS estimations of local indicators and the ones calculated with the established field-based process. We show that EcoIS' error is similar to the one of image series generated with fixed camera setups. We see that EcoIS processes an image in 3.8s and show how it is equipped to handle data intensive scenarios. We additionally identify in-camera automatic image formatting and image acquiring oversight as contributing factors for increasing the overall error. Our main conclusion is that EcoIS creates usable image series that maintain the spatiotemporal qualities of the original images and can successfully be utilized to generate ecological indicators. EcoIS is relevant as a replacement for traditional image series infrastructure where the cost of deploying EcoIS is smaller or less intrusive to the ecosystem. [Copyright &y& Elsevier]

The state of built-up features after their destruction, as well as the process of their rehabilitation, are assessed through the analysis of conflict and postconflict very high spatial resolution Ikonos images using a pixel-level support vector machine (SVM) learning classification approach. Different input vectors of the supervised SVM classifier are tested in order to assess the discrimination power of structural and spectral image descriptors: the use of spectral information only with (a) the panchromatic images at time t0 and t1, (b) the pan-sharpened images with the multispectral bands at time t0 and t1, (c) the iteratively re-weighted multivariate alteration detection (IR-MAD) variates derived from dataset (b); the use of structural information only with image series resulting from the decomposition by the derivative of the morphological profile (DMP) of the panchromatic (d) and pan-sharpened (e) data; finally, the use of spectral and structural information simultaneously (f) and (g) by stacking up (a) and (d), and (b) and (e), respectively. The results show that the SVM performs better with feature vectors based on the simultaneous use of spectral and structural information rather than with those formed by the grey-level information or the DMPs only. Moreover, approach (f) requiring only two panchromatic data as input compete well with approaches (b), (e), and (g), which instead necessitate ten spectral channels as input. [ABSTRACT FROM PUBLISHER]

A semiautomatic segmentation method based on active contour is proposed for computed tomography (CT) image series. First, to get initial contour, one image slice was segmented exactly by C-V method based on Mumford-Shah model. Next, the computer will segment the nearby slice automatically using the snake model one by one. During segmenting of image slices, former slice boundary, as next slice initial contour, may cross over next slice real boundary and never return to right position. To avoid contour skipping over, the distance variance between two slices is evaluated by an threshold. which decides whether to initiate again. Moreover, a new improved marching cubes (MC) algorithm based on 2D images series segmentation boundary is given for 3D image reconstruction. Compared with the standard method, the proposed algorithm reduces detecting time and needs less storing memory. The effectiveness and capabilities of the algorithm were illustrated by experimental results. [ABSTRACT FROM AUTHOR]

Abstract: To ensure the delineated boundaries of a series of 2-D images closely following the visually perceivable edges with high boundary coherence between consecutive slices, a cell-based two-region competition algorithm based on a maximum a posteriori (MAP) framework is proposed. It deforms the region boundary in a cell-by-cell fashion through a cell-based two-region competition process. The cell-based deformation is guided by a cell-based MAP framework with a posterior function characterizing the distribution of the cell means in each region, the salience and shape complexity of the region boundary and the boundary coherence of the consecutive slices. The proposed algorithm has been validated using 10 series of breast sonograms, including seven compression series and three freehand series. The compression series contains two carcinoma and five fibroadenoma cases and the freehand series contains two carcinoma and one fibroadenoma cases. The results show that >70% of the derived boundaries fall within the span of the manually delineated boundaries. The robustness of the proposed algorithm to the variation of regions-of-interest is confirmed by the Friedman tests and the p-values of which are 0.517 and 0.352 for the compression and freehand series groups, respectively. The Pearson’s correlations between the lesion sizes derived by the proposed algorithm and those defined by the average manually delineated boundaries are all higher than 0.990. The overlapping and difference ratios between the derived boundaries and the average manually delineated boundaries are mostly higher than 0.90 and lower than 0.13, respectively. For both series groups, all assessments conclude that the boundaries derived by the proposed algorithm be comparable to those delineated manually. Moreover, it is shown that the proposed algorithm is superior to the Chan and Vese level set method based on the paired-sample t-tests on the performance indices at a 5% significance level. (E-mail: chung@ntu.edu.tw) [Copyright &y& Elsevier]

Abstract: The classical means to measure traffic density and velocity depend on local measurements from induction loops and other on site instruments. This information does not give the whole picture of the two-dimensional traffic situation. In order to obtain precise knowledge about the traffic flow of a large area, only airborne cameras or cameras positioned at very high locations (towers, etc.) can provide an up-to-date image of all roads covered. The paper aims at showing the potential of using image time series from these cameras to derive traffic parameters on the basis of single car measurements. To be able to determine precise velocities and other parameters from an image time series, exact geocoding is one of the first requirements for the acquired image data. The methods presented here for determining several traffic parameters for single vehicles and vehicle groups involve recording and evaluating a number of digital or analog aerial images from high altitude and with a large total field of view. Visual and automatic methods for the interpretation of images are compared. It turns out that the recording frequency of the individual images should be at least 1/3 Hz (visual interpretation), but is preferably 3 Hz or more, especially for automatic vehicle tracking. The accuracy and potentials of the methods are analyzed and presented, as well as the usage of a digital road database for improving the tracking algorithm and for integrating the results for further traffic applications. Shortcomings of the methods are given as well as possible improvements regarding methodology and sensor platform. [Copyright &y& Elsevier]

This paper describes image processing methods for automatic spotted microarray image analysis. Automatic gridding is important to achieve constant data quality and is, therefore, especially interesting for large-scale experiments as well as for integration of microarray expression data from different sources. We propose a Markov random field (MRF) based approach to high-level grid segmentation, which is robust to common problems encountered with array images and does not require calibration. We also propose an active contour method for single-spot segmentation. Active contour models describe objects in images by properties of their boundaries. Both MRFs and active contour models have been used in various other computer vision applications. The traditional active contour model must be generalized for successful application to microarray spot segmentation. Our active contour model is employed for spot detection in the MRF score functions as well as for spot signal segmentation in quantitative array image analysis. An evaluation using several image series from different sources shows the robustness of our methods. [ABSTRACT FROM PUBLISHER]

The present work develops an analytical model that allows one to estimate the current distribution within the whole muscle and the resulting isometric recruitment curve (IRC). The quasistatic current distribution, expressed as an image series, i.e., a collection of properly weighted and shifted point-source responses, outlines an extension for more than three layers of the classical image theory in conductive plane-stratified media. Evaluation of the current distribution via the image series expansions requires substantially less computational time than the standard integral representation. The expansions use a unique recursive representation for Green's function, that is a generic characteristic of the stratification. This approach permits one to verify which of the tissue electrical properties are responsible for the current density distribution within the muscle, and how significant their combinations are. In addition, the model permits one to study the effect of different electrode placement on the shape and the magnitude of the potential distribution. A simple IRC model was used for parameter estimation and model verification by comparison with experimentally obtained isometric recruitment curves. Sensitivity of the model to different parameters such as conductivity of the tissues and activation threshold was verified. The resulting model demonstrated characteristic features that were similar to those of experimentally obtained data. The model also quantitatively confirmed the differences existing between surface (transcutaneous) and implanted (percutaneous) electrode stimulation. © 2000 Biomedical Engineering Society. PAC00: 8719Ff, 8754Dt, 8719Nn, 8717Nn [ABSTRACT FROM AUTHOR]

This paper presents a new method for unsupervised subpixel change detection using image series. The method is based on the definition of a probabilistic criterion capable of assessing the level of coherence of an image series relative to a reference classification with a finer resolution. In opposition to approaches based on an a priori model of the data, the model developed here is based on the rejection of a nonstructured model—called a-contrario model—by the observation of structured data. This coherence measure is the core of a stochastic algorithm which automatically selects the image subdomain representing the most likely changes. A theoretical analysis of this model is led to predict its performances, in particular regarding the contrast level of the image as well as the number of change pixels in the image. Numerical simulations are also presented that confirm the high robustness of the method and its capacity to detect changes impacting more than 25 percent of a considered pixel under average conditions. An application to land-cover change detection is then provided using time series of satellite images. [ABSTRACT FROM PUBLISHER]