Image Pixels Research Articles

Identification of the best method for detecting surface water in Sentinel-2 multispectral satellite imagery

Surface water maps are useful in a variety of disciplines from climate change analysis to water resource management. Multispectral satellite imagery can be used to derive such surface water maps using a variety of image processing methods. The medium resolution Sentinel-2 multispectral satellite imagery catalogue is currently used extensively for surface water mapping. The quality and accuracy of these maps produced from Sentinel-2 imagery can vary greatly depending on the method applied to classify the image pixels into land or water. Thus far, there has not been a consensus on which method produces the highest accuracy surface water maps, warranting a direct comparison to assess these methods in a wide range of geographic settings. Here we show that among some of the most commonly applied surface water mapping methods (NDWI, MNDWI, AWEI_SH, AWEI_NSH, AWEI_BOTH, SVM, RT, MLC, and KNN) that no single method produced the most accurate maps across the four locations studied, but AWEI_NSH performed the best overall across the four locations, and SVM was the best performing machine learning technique. Rather, each method's performance was shown to depend on the objects present in the image (e.g., built-up, shadows, vegetated shorelines, narrow waterbodies, etc.) and how successfully the method was able to classify those objects properly. This is in-line with current understanding of spectral index methods' performance, and we provide recommendations to aid remote sensing data users in choosing a suitable method based on their image's characteristics. Using these recommendations, we hope that the quality of surface water maps derived from multispectral satellite imagery will be improved for all disciplines that utilize such data by allowing users to choose the method that is best fit to the application.

Hyperspectral transmittance imaging detection of early decayed oranges caused by Penicillium digitatum using NFINDR-JMSAM algorithm with spectral feature separating

Decay caused by Penicillium spp. is the main cause of postharvest citrus quality loss, moreover, the fungus can quickly infect entire batches of citrus fruit resulting in significant economic losses. However, effective detection of early decay remains a challenge due to the lack of distinct visual features. In this study, a Vis-NIR hyperspectral imaging system was developed to acquire full-transmittance images and an NFINDR-JMSAM algorithm was proposed to segment different image pixels. By extracting pure pixels and separating spectral features, the overall classification accuracy of 99.3 % was obtained for all tested samples. The proposed method can also effectively identify scars on the flavedo, citrus stem-end and navel, thereby eliminating their interference with the detection of decayed orange fruit. This study provided a new idea for accurately detecting the early decayed citrus fruit and visualizing the detection results for different tissues by combining hyperspectral transmittance imaging and NFINDR-JMSAM algorithm.

Super-resolved analysis of colocalization between replication and transcription along the cell cycle in a model of oncogene activation

To understand how oncogenes affect genome organization, it is essential to visualize fundamental processes such as DNA replication and transcription at high resolution in intact cells. At the same time, it is important to determine the progression of the cell along the cell cycle, as cell cycle regulation is crucial for the control of cell proliferation and oncogenesis. Here, we present a super-resolution imaging-based method to analyze single cell nuclei sorted according to specific phases of the cell cycle. The sorting is based on the evaluation of the number and the intensity of pixels in the replication foci image and the colocalization analysis is based on image cross-correlation spectroscopy (ICCS). We evaluate the colocalization between replication and transcription, at different cell cycle phases, in a model of PML-RARα oncogene activation. We find that colocalization between replication and transcription is higher in cells in early S phase compared to cells in middle and late S phase. When we turn on the PML-RARα oncogene, this colocalization pattern is preserved but we detect an increase of colocalization between replication and transcription in the early S phase which points to an effect of the PML-RARα oncogene on the coordination between replication and transcription.

GB-SAR geocoding considering the radar attitude inclination angles for building facade deformation extraction

ABSTRACT The process of engineering construction typically impacts the nearby existing buildings, causing either localized or widespread deformation of these structures. The application of deformation monitoring technology enables the timely identification of damage or uneven deformation, thereby facilitating the implementation of appropriate maintenance and repair actions. This paper explores the application of ground-based synthetic aperture radar (GB-SAR) in building facade deformation monitoring. GB-SAR acquires two-dimensional (2D) images and measures deformation along the line of sight (LOS) direction through interference calculation. In order to accurately determine the location of deformation and retrieve the elevation information of image pixels, it is usually required to utilize external three-dimensional (3D) data to reconstruct the 3D coordinate of these pixels, which is known as geocoding, or georeferencing. In the case of the GB-SAR system, it is necessary for the observer to measure the angles between the antenna orientation, the radar movement direction and the reference plane of the local surveying coordinate system. Nevertheless, the measurement of these attitude angles may be overlooked in practice, and the impact of small attitude angles or their measurement errors on GB-SAR geocoding may be disregarded, which directly affects the slant range projection (SRP) calculation of the external 3D data, thereby leading to biased 3D coordinate reconstruction of GB-SAR pixels. This paper proposes a method to calculate the SRP coordinates of point cloud data considering the attitude inclination angles of radar sensor, and perform matching calculations on the high-quality pixels (HQPs) with the point cloud after SRP to extract building facade deformation. The results demonstrate that the method is capable of effectively mitigating the influence of the radar attitude inclination angles, resulting in a reduction of the average deviation of 3D coordinates to approximately one-third of the value without consideration of the sensor’s attitude in a real-world building monitoring experiment.

Automatic thresholding method using single information entropy under product transformation of order difference filter response

To automatically threshold images with unimodal, bimodal, multimodal or non-modal gray level distributions within a unified framework, an automatic thresholding method using single information entropy under the product transformation of order difference filter response is proposed. The proposed method first performs the product transformation of order difference filter response on an input image at different scales to obtain the product transformation image. Critical or non-critical pixels are labelled on each pixel of the binary images corresponding to different thresholds to construct a series of binary label images that are used for distinguishing critical or non-critical regions. A single information entropy is finally used for characterizing the information obtained from the product transformation image with the critical regions of different binary label images, and the threshold corresponding to maximum information entropy is selected as final threshold. The proposed method is compared with seven state-of-the-art segmentation methods. Experimental results on 12 synthetic images and 98 real-world images show that the average Matthews correlation coefficients of the proposed method reached 0.994 and 0.966 for the synthetic images and the real-world images, which outperform the second-best method by 52.4 % and 27.8 %, respectively. The proposed method has more robust segmentation adaptability to test images with different modalities, despite not offering an advantage in terms of computational efficiency.

Skin Lesion Segmentation Using Adaptive Color Segmentation and Decision Tree

A decision tree operates as a predictive model in machine learning, utilizing a structured hierarchy of rules for the decision-making process. This model is graphically depicted through a tree-like structure, where each node symbolizes a decision point, and the ensuing branches represent the resultant outcomes of these decisions. This method proves particularly efficacious in addressing both classification and regression challenges, offering clear interpretability through its graphical illustration of the connections between input features and predicted outcomes. In the domain of image processing, color image segmentation serves as a crucial preliminary step for various applications. Specifically, the segmentation of skin lesions holds significant importance in image analysis, notably in the classification of lesions within dermoscopy images. Image segmentation involves the categorization of image pixels into uniform regions based on attributes like color, texture, and luminosity. The primary objective here is to delineate the area of interest from the healthy surrounding tissue. In methods reliant on threshold-based segmentation, the effectiveness of the segmentation hinges on the accurate selection of an appropriate threshold.

Reproducibility of [18F]MK-6240 kinetics in brain studies with shortened dynamic PET protocol in healthy/cognitively normal subjects

Background[18F]MK-6240 is a neurofibrillary tangles PET radiotracer that has been broadly used in aging and Alzheimer’s disease (AD) studies. Majority of [18F]MK-6240 PET studies use dynamic acquisitions longer than 60 min to assess the tracer kinetic parameters. As of today, no consensus has been established on the optimum dynamic PET scan time. In this study, we assess the reproducibility of [18F]MK-6240 quantitative metrics using shortest dynamic PET protocols in cognitively normal subjects. PET metrics were measured through two-tissue compartment model (2TCM) and Logan model to estimate VT and DVR, as well as SUVR from 90 to 120 min (SUVR90 − 120 min) post-tracer injection for brain regions. 2TCM was carried out using the 120 min dynamic coffee break dataset (first scan from 0 to 60 min p.i., second scan from 90 to 120 min p.i.) and then repeated after stepwise shortening it by 5 min. The dynamic scan length that reproduced the 120 min dynamic scans-based VT to within 10% error was defined as the shortest acquisition time (SAT). The SAT SUVR90 − 120 min was deduced from the SAT dataset by extrapolation of each image pixel time-activity curve to 120 min. The reproducibility of the 120 min dynamic scans-based VT2TCM, DVR2TCM, DVRLogan, and SUVR using the SAT was assessed using Passing-Bablock analysis. The limits of reproducibility of each PET metrics were determined using Bland-Altman analysis.ResultsA dynamic SAT of 40 min yielded < 10% error in [18F]MK-6240 VT2TCM’s for all brain regions, compared to those measured using the 120 min datasets. SAT-based analysis did not show statistically significant systemic or proportional biases in VT2TCM, DVR2TCM, DVRLogan, or SUVR compared to those deduced from the full dynamic dataset of 120 min. A mean difference between the 120 min- and SAT-based analysis of less than 4%, 10%, 15%, and 20% existed in the VT2TCM, DVR2TCM, DVRLogan, and SUVR respectively.ConclusionKinetic modeling of [18F]MK-6240 PET can be accurately performed using dynamic scan times as short as 40 min. This can facilitate studies with [18F]MK-6240 PET and improve patients accrual. Further work would be necessary to confirm the reproducibility of these results for patients in dementia spectra.

Assessing the Potential of UAV for Large-Scale Fractional Vegetation Cover Mapping with Satellite Data and Machine Learning

Fractional vegetation cover (FVC) is an essential metric for valuating ecosystem health and soil erosion. Traditional ground-measuring methods are inadequate for large-scale FVC monitoring, while remote sensing-based estimation approaches face issues such as spatial scale discrepancies between ground truth data and image pixels, as well as limited sample representativeness. This study proposes a method for FVC estimation integrating uncrewed aerial vehicle (UAV) and satellite imagery using machine learning (ML) models. First, we assess the vegetation extraction performance of three classification methods (OBIA-RF, threshold, and K-means) under UAV imagery. The optimal method is then selected for binary classification and aggregated to generate high-accuracy FVC reference data matching the spatial resolutions of different satellite images. Subsequently, we construct FVC estimation models using four ML algorithms (KNN, MLP, RF, and XGBoost) and utilize the SHapley Additive exPlanation (SHAP) method to assess the impact of spectral features and vegetation indices (VIs) on model predictions. Finally, the best model is used to map FVC in the study region. Our results indicate that the OBIA-RF method effectively extract vegetation information from UAV images, achieving an average precision and recall of 0.906 and 0.929, respectively. This method effectively generates high-accuracy FVC reference data. With the improvement in the spatial resolution of satellite images, the variability of FVC data decreases and spatial continuity increases. The RF model outperforms others in FVC estimation at 10 m and 20 m resolutions, with R2 values of 0.827 and 0.929, respectively. Conversely, the XGBoost model achieves the highest accuracy at a 30 m resolution, with an R2 of 0.847. This study also found that FVC was significantly related to a number of satellite image VIs (including red edge and near-infrared bands), and this correlation was enhanced in coarser resolution images. The method proposed in this study effectively addresses the shortcomings of conventional FVC estimation methods, improves the accuracy of FVC monitoring in soil erosion areas, and serves as a reference for large-scale ecological environment monitoring using UAV technology.

A Multi-Fruit Recognition Method for a Fruit-Harvesting Robot Using MSA-Net and Hough Transform Elliptical Detection Compensation

In the context of agricultural modernization and intelligentization, automated fruit recognition is of significance for improving harvest efficiency and reducing labor costs. The variety of fruits commonly planted in orchards and the fluctuations in market prices require farmers to adjust the types of crops they plant flexibly. However, the differences in size, shape, and color among different types of fruits make fruit recognition quite challenging. If each type of fruit requires a separate visual model, it becomes time-consuming and labor intensive to train and deploy these models, as well as increasing system complexity and maintenance costs. Therefore, developing a general visual model capable of recognizing multiple types of fruits has great application potential. Existing multi-fruit recognition methods mainly include traditional image processing techniques and deep learning models. Traditional methods perform poorly in dealing with complex backgrounds and diverse fruit morphologies, while current deep learning models may struggle to effectively capture and recognize targets of different scales. To address these challenges, this paper proposes a general fruit recognition model based on the Multi-Scale Attention Network (MSA-Net) and a Hough Transform localization compensation mechanism. By generating multi-scale feature maps through a multi-scale attention mechanism, the model enhances feature learning for fruits of different sizes. In addition, the Hough Transform ellipse detection compensation mechanism uses the shape features of fruits and combines them with MSA-Net recognition results to correct the initial positioning of spherical fruits and improve positioning accuracy. Experimental results show that the MSA-Net model achieves a precision of 97.56, a recall of 92.21, and an mAP@0.5 of 94.81 on a comprehensive dataset containing blueberries, lychees, strawberries, and tomatoes, demonstrating the ability to accurately recognize multiple types of fruits. Moreover, the introduction of the Hough Transform mechanism reduces the average localization error by 8.8 pixels and 3.5 pixels for fruit images at different distances, effectively improving the accuracy of fruit localization.

Damage Scene Change Detection Based on Infrared Polarization Imaging and Fast-PCANet

Change detection based on optical image processing plays a crucial role in the field of damage assessment. Although existing damage scene change detection methods have achieved some good results, they are faced with challenges, such as low accuracy and slow speed in optical image change detection. To solve these problems, an image change detection approach that combines infrared polarization imaging with a fast principal component analysis network (Fast-PCANet) is proposed. Firstly, the acquired infrared polarization images are analyzed, and pixel image blocks are extracted and filtered to obtain the candidate change points. Then, the Fast-PCANet network framework is established, and the candidate pixel image blocks are sent to the network to detect the change pixel points. Finally, the false-detection points predicted by the Fast-PCANet are further corrected by region filling and filtering to obtain the final binary change map of the damage scene. Comparisons with typical PCANet-based change detection algorithms are made on a dataset of infrared-polarized images. The experimental results show that the proposed Fast-PCANet method improves the PCC and the Kappa coefficient of infrared polarization images over infrared intensity images by 6.77% and 13.67%, respectively. Meanwhile, the inference speed can be more than seven times faster. The results verify that the proposed approach is effective and efficient for the change detection task with infrared polarization imaging. The study can be applied to the damage assessment field and has great potential for object recognition, material classification, and polarization remote sensing.

EstuarySAT Database Development of Harmonized Remote Sensing and Water Quality Data for Tidal and Estuarine Systems.

Researchers and environmental managers need big datasets spanning long time periods to accurately assess current and historical water quality conditions in fresh and estuarine waters. Using remote sensing data, we can survey many water bodies simultaneously and evaluate water quality conditions with greater frequency. The combination of existing and historical water quality data with remote sensing imagery into a unified database allows researchers to improve remote sensing algorithms and improves understanding of mechanisms causing blooms. We report on the development of a water quality database "EstuarySAT" which combines data from the Sentinel-2 multi-spectral instrument (MSI) remote sensing platform and water quality data throughout the coastal USA. EstuarySAT builds upon an existing database and set of methods developed by the creators of AquaSat, whose region of interest is primarily larger freshwater lakes in the USA. Following the same basic methods, EstuarySAT utilizes open-source tools: R v. 3.24+ (statistical software), Python (dynamic programming environment), and Google Earth Engine (GEE) to develop a combined water quality data and remote sensing imagery database (EstuarySAT) for smaller coastal estuarine and freshwater tidal riverine systems. EstuarySAT fills a data gap that exists between freshwater and estuarine water bodies. We are able to evaluate smaller systems due to the higher spatial resolution of Sentinel-2 (10 m pixel image resolution) vs. the Landsat platform used by AquaSat (30 m pixel resolution). Sentinel-2 also has a more frequent revisit (overpass) schedule of every 5 to 10 days vs. Landsat 7 which is every 17 days. EstuarySAT incorporates publicly available water quality data from 23 individual water quality data sources spanning 1984-2021 and spatially matches them with Sentinel-2 imagery from 2015-2021. EstuarySAT currently contains 299,851 matched observations distributed across the coastal USA. EstuarySAT's primary focus is on collecting chlorophyll data; however, it also contains other ancillary water quality data, including temperature, salinity, pH, dissolved oxygen, dissolved organic carbon, and turbidity (where available). As compared to other ocean color databases used for developing predictive chlorophyll algorithms, this coastal database contains spectral profiles more typical of CDOM-dominated systems. This database can assist researchers and managers in evaluating algal bloom causes and predicting the occurrence of future blooms.

A clustering tool for generating biological geometries for computational modeling in radiobiology.

Objective.To develop a computational tool that converts biological images into geometries compatible with computational software dedicated to the Monte Carlo simulation of radiation transport (TOPAS), and subsequent biological tissue responses (CompuCell3D). The depiction of individual biological entities from segmentation images is essential in computational radiobiological modeling for two reasons: image pixels or voxels representing a biological structure, like a cell, should behave as a single entity when simulating biological processes, and the action of radiation in tissues is described by the association of biological endpoints to physical quantities, as radiation dose, scored the entire group of voxels assembling a cell.Approach.The tool is capable of cropping and resizing the images and performing clustering of image voxels to create independent entities (clusters) by assigning a unique identifier to these voxels conforming to the same cluster. The clustering algorithm is based on the adjacency of voxels with image values above an intensity threshold to others already assigned to a cluster. The performance of the tool to generate geometries that reproduced original images was evaluated by the dice similarity coefficient (DSC), and by the number of individual entities in both geometries. A set of tests consisting of segmentation images of cultured neuroblastoma cells, two cell nucleus populations, and the vasculature of a mouse brain were used.Main results.The DSC was 1.0 in all images, indicating that original and generated geometries were identical, and the number of individual entities in both geometries agreed, proving the ability of the tool to cluster voxels effectively following user-defined specifications. The potential of this tool in computational radiobiological modeling, was shown by evaluating the spatial distribution of DNA double-strand-breaks after microbeam irradiation in a segmentation image of a cell culture.Significance.This tool enables the use of realistic biological geometries in computational radiobiological studies.

Lossy Image Compression with Stochastic Quantization

Introduction. Lossy image compression algorithms play a crucial role in various domains, including graphics, and image processing. As image information density increases, so do the resources required for processing and transmission. One of the most prominent approaches to address this challenge is color quantization, proposed by Orchard et al. (1991). This technique optimally maps each pixel of an image to a color from a limited palette, maintaining image resolution while significantly reducing information content. Color quantization can be interpreted as a clustering problem (Krishna et al. (1997), Wan (2019)), where image pixels are represented in a three-dimensional space, with each axis corresponding to the intensity of an RGB channel. The purpose of the paper. Scaling of traditional algorithms like K-Means can be challenging for large data, such as modern images with millions of colors. This paper reframes color quantization as a three-dimensional stochastic transportation problem between the set of image pixels and an optimal color palette, where the number of colors is a predefined hyperparameter. We employ Stochastic Quantization (SQ) with a seeding technique proposed by Arthur et al. (2007) to enhance the scalability of color quantization. This method introduces a probabilistic element to the quantization process, potentially improving efficiency and adaptability to diverse image characteristics. Results. To demonstrate the efficiency of our approach, we present experimental results using images from the ImageNet dataset. These experiments illustrate the performance of our Stochastic Quantization method in terms of compression quality, computational efficiency, and scalability compared to traditional color quantization techniques. Conclusions. This study introduces a scalable algorithm for solving the color quantization problem without memory constraints, demonstrating its efficiency on a subset of images from the ImageNet dataset. The convergence speed of the algorithm can be further enhanced by modifying the update rule with alternative methods to Stochastic Gradient Descent (SGD) that incorporate adaptive learning rates. Moreover, the stochastic nature of the proposed solution enables the utilization of parallelization techniques to simultaneously update the positions of multiple quants, potentially leading to significant performance improvements. This aspect of parallelization and its impact on algorithm efficiency presents a topic for future research. The proposed method not only addresses the limitations of existing color quantization techniques but also opens up new possibilities for optimizing image compression algorithms in resource-constrained environments. Keywords: non-convex optimization, stochastic optimization, stochastic quantization, color quantization, lossy compression.

Sterilization of image steganography using self-supervised convolutional neural network

Background With the development of steganography technology, lawbreakers can implement covert communication in social networks more easily, exacerbating network security risks. Sterilization of image steganography methods can eliminate secret messages to block the transmission of illegal covert communication. However, existing methods overly rely on cover-stego image pairs and are unable to sanitize unknown image, which reduces stego image blocking rate in social networks. Methods To address the above problems, this paper proposes an effective sterilization of image steganography method using self-supervised convolutional neural network (SS-Net), which does not require any prior knowledge of image steganography schemes. SS-Net includes a purification module and a refinement module. Firstly, the pixel-shuffle down-sampling in purification module is adopted to reduce the spatial correlation of pixels in the stgeo image, and improve the learning mode from supervised learning to self-supervised learning. Secondly, centrally masked convolutions and dilated convolution residual blocks are merged to eliminate secret messages and avoid image quality degradation. Finally, a refinement module is employed to improve image texture details and boundaries. Results A series of experiments show that SS-Net from BOSSbase test sets is able to balance the destruction of secret messages with image quality, achieving 100% blocking rate of stego image. Meanwhile, our method outperforms the state-of-the-art methods in secret messages elimination ability and image quality preserving ability.

Effect of experimental parameters on X-ray Micro-CT imaging for Spectral CT applications

Computed tomography (CT) is recognized as a reliable method for structural characterization of different materials. Recently, Spectral CT methods have emerged as a tool to describe the sample composition through assessment of mass density (ρ) and effective atomic number (Zeff) assessment from CT results. These techniques depend on measuring the linear attenuation of a set of standards samples. However, besides ρ and Zeff, these results are influenced by factors such as X-ray energy and may be affected by experimental factors not accounted for in the foundational equation. Thus, in this study, we propose to quantify the effects of two factors: uniaxial compression and image pixel size on measurements of linear attenuation assessed through the registered mean gray value and its standard deviation. Initially, a group of metallic oxides pellets were compressed under different pressures and scanned at various magnification factors. Subsequently, based on factorial design theory, Yates’ method was applied to evaluate the significant effects of the factors. In a second phase, using a group of known samples, a Dual-Energy CT (DECT) measurement of a validation sample was conducted to verify the quantified effects. As expected initially, we observed that uniaxial compression positively influences attenuation, as it directly affects mass density. However, we found that an increase in image pixel size leads to a decrease in registered attenuation as it reduces the relationship between radiation attenuation and detected photons. Indeed, for the leveraged variation, the linear effect of pixel size variation proved to be the most influential on the registered mean gray value. When considering these effects in DECT application, no statistical difference was observed between loose powder and pellet measurements. Furthermore, no trend was observed in the results regarding image pixel size. However, it is possible that more significant changes in these factors may yield different results, and therefore, operators applying Spectral CT methods must ensure that the same experimental conditions are applied to both the standard sample set and the sample under investigation.

Referring Image Segmentation with Multi-Modal Feature Interaction and Alignment Based on Convolutional Nonlinear Spiking Neural Membrane Systems.

Referring image segmentation aims to accurately align image pixels and text features for object segmentation based on natural language descriptions. This paper proposes NSNPRIS (convolutional nonlinear spiking neural P systems for referring image segmentation), a novel model based on convolutional nonlinear spiking neural P systems. NSNPRIS features NSNPFusion and Language Gate modules to enhance feature interaction during encoding, along with an NSNPDecoder for feature alignment and decoding. Experimental results on RefCOCO, RefCOCO[Formula: see text], and G-Ref datasets demonstrate that NSNPRIS performs better than mainstream methods. Our contributions include advances in the alignment of pixel and textual features and the improvement of segmentation accuracy.

Weighted Contrastive Prototype Network for Few-Shot Hyperspectral Image Classification with Noisy Labels

Few-shot hyperspectral image classification aims to develop the ability of classifying image pixels by using relatively few labeled pixels per class. However, due to the inaccuracy of the localization system and the bias of the ground survey, the potential noisy labels in the training data pose a very significant challenge to few-shot hyperspectral image classification. To solve this problem, this paper proposes a weighted contrastive prototype network (WCPN) for few-shot hyperspectral image classification with noisy labels. WCPN first utilizes a similarity metric to generate the weights of the samples from the same classes, and applies them to calibrate the class prototypes of support and query sets. Then the weighted prototype network will minimize the distance between features and prototypes to train the network. WCPN also incorporates a weighted contrastive regularization function that uses the sample weights as gates to filter the fake positive samples whose labels are incorrect to further improve the discriminative power of the prototypes. We conduct experiments on multiple hyperspectral image datasets with artificially generated noisy labels, and the results show that the WCPN has excellent performance that can sufficiently mitigate the impact of noisy labels.

A New 3D reconstruction method for pressure-sensitive paint measurements under limited optical access

Reconstruction of 3D pressure field is crucial for pressure-sensitive paint measurements in turbomachinery experiments. Existing methods impose high requirements on feature points in terms of quantity, spatial distribution, and positional accuracy, and is difficult to apply under limited optical access, such as in planar cascade wind tunnels. We propose a novel direct linear transformation method based on contour matching (CM-DLT). This method leverages model contours captured from a tilted camera perspective, which provides the basis for identifying the projection matrix linking image pixels to 3D spatial points. The subsequent optimization of the projection matrix significantly enhances the accuracy and robustness of 3D pressure field reconstruction. In a benchmark experiment, the efficiency and reprojection accuracy of 3D reconstruction are investigated. Subsequently, the CM-DLT method is successfully applied in the cascade wind tunnel experiment. The obtained 3D pressure fields of two surfaces of adjacent blades are analyzed.

Pressure distribution based 2D in-bed keypoint prediction under interfered scenes

In-bed pose estimation holds significant potential in various domains, including healthcare, sleep studies, and smart homes. Pressure-sensitive bed sheets have emerged as a promising solution for addressing this task considering the advantages of convenience, comfort, and privacy protection. However, existing studies primarily rely on ideal datasets that do not consider the presence of common daily objects such as pillows and quilts referred to as interference, which can significantly impact the pressure distribution. As a result, there is still a gap between the models trained with ideal data and the real-life application. Besides the end-to-end training approach, one potential solution is to recognize the interference and fuse the interference information to the model during training. In this study, we created a well-annotated dataset, consisting of eight in-bed scenes and four common types of interference: pillows, quilts, a laptop, and a package. To facilitate the analysis, the pixels in the pressure image were categorized into five classes based on the relative position between the interference and the human. We then evaluated the performance of five neural network models for pixel-level interference recognition. The best-performing model achieved an accuracy of 80.0% in recognizing the five categories. Subsequently, we validated the utility of interference recognition in improving pose estimation accuracy. The ideal model initially shows an average joint position error of up to 30.59 cm and a Percentage of Correct Keypoints (PCK) of 0.332 on data from scenes with interferences. After retraining on data including interference, the error is reduced to 13.54 cm and the PCK increases to 0.747. By integrating interference recognition information, either by excluding the parts of the interference or using the recognition results as input, the error can be further minimized to 12.44 cm and the PCK can be maximized up to 0.777. Our findings represent an initial step towards the practical deployment of pressure-sensitive bed sheets in everyday life.

A novel image encryption method based on the cycle replacement

For the bit-level image encryption algorithms, pixel values and positions can be changed simultaneously. The operation can enhance the security of image encryption but will require the complicated calculations. Therefore, high security and suitable computation for a new algorithm are needed to be considered. In this paper, a novel image encryption algorithm, which combines the bit-level encryption and the pixel-level encryption methods, is proposed based on the cycle replacement. Firstly, a new 2-dimensional (2D) map with a hyperbolic cosine function (2D-Cosh map) is introduced, which has rich and complex dynamics. Based on the chaotic characteristic of the map, an image encryption algorithm is introduced via the substitution of bit of pixels which can scramble the pixels, and change the image pixel positions effectively. Numerical simulation and security analysis are used to demonstrate the effectiveness and feasibility of the algorithm. From which we can see that the correlation coefficients are almost 0, average entropy = 7.9973, average NPCR = 99.6104%, and average UACI = 33.4664%. It is clear that the algorithm is resistant to differential attacks, interference attacks, and can reduce the correlation of adjacent pixels of the encrypted image greatly. Meanwhile, the algorithm has no limit for the size of a color image in the process of the encryption.