Image Points Research Articles

Point of care ultrasound measurement of paralumbar caudal vena cava diameter and caudal vena cava to aortic ratio in hypovolemic dogs

BackgroundAccurate assessment of intravascular volume is critical for precise fluid prescription. In people, bedside or point of care ultrasound is used to measure the inferior vena cava, with or without paired aortic measurement, to estimate intravascular volume.ObjectiveTo determine if point of care ultrasound measurement of the caudal vena cava (CVC) diameter or the CVC diameter to the abdominal aorta (Ao) diameter (CVC:Ao) at the paralumbar view are associated with changes in intravascular volume, mean arterial pressure (MAP), or cardiac output in normovolemic and hypovolemic dogs.Animals8 purpose-bred dogs.MethodsPressure-targeted hemorrhagic shock was induced in purpose-bred dogs under general anesthesia. Dogs were exsanguinated to a mean arterial pressure of 40 mmHg, or a maximum 60% blood volume lost, then auto-transfused shed blood. At a left paralumbar view, longitudinal plane measurements of the abdominal CVC diameter and aortic diameter were obtained. Measurements were performed at 4 timepoints: baseline under anesthesia (TP1), after hemorrhagic shock was induced (TP2), after ½ of shed blood had been re-transfused (TP3), and post-resuscitation with completed re-transfusion (TP4). Additional variables collected included cardiac output using thermodilution and arterial blood pressure.ResultsCVC:Ao was not significantly different between timepoints and was not associated with changes in CO (p = 0.28) or MAP (p = 0.50). CVC diameter was significantly different between baseline (TP1) and hemorrhagic shock (TP2). CVC diameter was significantly different at TP2 compared to TP1 after controlling for the effect of CO (p = 0.03) and MAP (p = 0.001). Aortic diameter was also significantly different at TP2 (p = 0.002, p = 0.001) and TP3 (p = 0.023, p = 0.017) compared to TP1 after controlling for CO and MAP.Conclusions and clinical importanceObtaining point of care ultrasound images for CVC:Ao measurement was feasible. With a marked decrease in intravascular volume, both CVC and Ao diameter decreased, resulting in an unchanged CVC:Ao. Despite changes in CVC and Ao diameters, these changes were not associated with measured changes in CO, emphasizing that CO is not a direct estimate of intravascular volume and is affected by many compensatory mechanisms. Additional studies are needed to determine the most accurate method for bedside measurement of intravascular volume status.

Point cloud segmentation method based on an image mask and its application verification

Abstract Accurately perceiving three-dimensional (3D) environments or objects is crucial for the advancement of artificial intelligence (AI) interaction technologies. Currently, various types of sensors are employed to obtain point cloud data for 3D object detection or segmentation tasks. While this multi-sensor approach provides more precise 3D data than monocular or stereo cameras, it is also more expensive. The advent of RGB-D cameras, which provide both RGB images and depth information, addresses this issue.
In this study, we propose a point cloud segmentation method based on image masks. By using an RGB-D camera to capture color and depth images, we generate image masks through object recognition and segmentation. Given the mapping relationship between RGB image pixels and point clouds, these image masks can be further used to extract the point cloud data of the target objects. The experimental results revealed that the average accuracy of target segmentation was 84.78%, which was close to that of PointNet++. Compared with three traditional segmentation algorithms, the accuracy was improved by nearly 23.97%. The running time of our algorithm is reduced by 95.76% compared to the PointNet++ algorithm, which has the longest running time; and by 15.65% compared to the LCCP algorithm, which has the shortest running time among traditional methods. Compared with PointNet++, the segmentation accuracy was improved. This method addressed the issues of low robustness and excessive reliance on manual feature extraction in traditional point cloud segmentation methods, providing valuable support and reference for the accurate segmentation of 3D point clouds.

Robust and accurate visual geo-localization using prior map constructed by handheld LiDAR SLAM with camera image and terrestrial LiDAR point cloud

ABSTRACT Visual geo-localization using prior map of known environments has extensive applications in the fields such as self-driving, augmented reality and navigation. Currently, such prior maps are usually constructed by visual SLAM or SFM. However, the recent advances in LiDAR SLAM technology with RGB camera demonstrate great potential in efficient and accurate prior map construction and visual geo-localization. In this research, we developed a novel prior map construction approach which seamlessly integrates a handheld LiDAR SLAM system, a global LiDAR localization algorithm and a sparse set of terrestrial LiDAR scans as accurate control within a factor graph optimization framework. The developed LiDAR SLAM system augmented by terrestrial LiDAR scans achieves an improved mapping accuracy of 8 cm under GNSS-denied conditions in the areas over 50,000 m2 while the state-of-art FAST-LIO2 alone fails and produces a mapping error over 30 m. The results show that a competitive accuracy of visual geo-localization on a mobile phone using the constructed prior map is achieved (i.e. 60 and 76 cm in two tests respectively). Finally, this work also demonstrates a novel LiDAR point cloud fusion method that produces optimized and consistent coarse-to-fine 3D reconstruction in large and complex scenes.

A Novel Fuzzy Image-Based UAV Landing Using RGBD Data and Visual SLAM

In this work, an innovative perception-guided approach is proposed for landing zone detection and realization of Unmanned Aerial Vehicles (UAVs) operating in unstructured environments ridden with obstacles. To accommodate secure landing, two well-established tools, namely fuzzy systems and visual Simultaneous Localization and Mapping (vSLAM), are implemented into the landing pipeline. Firstly, colored images and point clouds acquired by a visual sensory device are processed to serve as characterizing maps that acquire information about flatness, steepness, inclination, and depth variation. By leveraging these images, a novel fuzzy map infers the areas for risk-free landing on which the UAV can safely land. Subsequently, the vSLAM system is employed to estimate the platform’s pose and an additional set of point clouds. The vSLAM point clouds presented in the corresponding keyframe are projected back onto the image plane on which a threshold fuzzy landing score map is applied. In other words, this binary image serves as a mask for the re-projected vSLAM world points to identify the best subset for landing. Once these image points are identified, their corresponding world points are located, and among them, the center of the cluster with the largest area is chosen as the point to land. Depending on the UAV’s size, four synthesis points are added to the vSLAM point cloud to execute the image-based visual servoing landing using image moment features. The effectiveness of the landing package is assessed through the ROS Gazebo simulation environment, where comparisons are made with a state-of-the-art landing site detection method.

Visible light infrared matching algorithm based on improved SuperPoint and linear converter

In order to solve the problems of high difficulty and mismatch rate in heterogeneous image matching of visible light and infrared images, a deep learning matching algorithm based on improved SuperPoint and linear transformer is proposed. The algorithm first introduces the idea of feature pyramid to construct a feature description branch based on the SuperPoint network structure, and trains it based on the hinge loss function, so as to better learn the multi-scale deep features of visible light and infrared images and increase the similarity of image point pair descriptors with the same name; in the feature matching module, the linear transformer is used to improve the SuperGlue matching algorithm and aggregate features to improve matching performance. The proposed algorithm is experimentally verified on multiple data sets. The results show that compared with the existing algorithms, the algorithm achieves better matching results and improves the matching accuracy.

Dense projection fusion for 3D object detection

Fusing information from LiDAR and cameras can effectively enhance the overall perceptivity of autonomous vehicles in various scenarios. Despite the relatively good results achieved by point-wise fusion and Bird’s-Eye-View (BEV) fusion, they still cannot fully leverage the image information and lack of effective depth information. For any fusion methods, the multi-modal features first need to be concatenated along the channel, and then the fused features are extracted using convolutional layers. However, this type of fusion methods is effective, but too coarse which causes that the fused features cannot pay more attention to the regions with important features and suffer from severe noise. To tackle these issues, we propose in this paper a Dense Projection Fusion (DPFusion) approach. It consists of two new modules: dense depth map guided BEV transform (DGBT) module and multi-modal feature adaptive fusion (MFAF) module. The DGBT module first quickly estimates the depth of each pixel and then projects all image features to the BEV space, making full use of the image information. The MFAF module computes the image weights and point cloud weights for each channel in each BEV grid and then adaptively weights and fuses the image BEV features with the point cloud BEV features. It is worth pointing out that the MFAF module makes the fused features pay more attention to background outline and object outline. Our proposed DPFusion demonstrates competitive results in 3D object detection, achieving a mean Average Precision (mAP) of 70.4 and a nuScenes detection score (NDS) of 72.3 on the nuScenes validation set.

Analysis of the Grid Quantization for the Microwave Radar Coincidence Imaging Based on Basic Correlation Algorithm

In Microwave Radar Coincidence Imaging (MRCI), the imaging region is typically discretized into a fine grid. In other words, it assumes that the equivalent scatterers of the target are precisely located at the centers of these pre-discretized grids. However, this approach usually encounters the off-grid problem, which can significantly degrade the imaging performance. In this paper, to establish a criterion for grid quantization, the performance of the MRCI system related to the grid size and the distribution of imaging points is investigated. First, the discretization of the imaging scene is regarded as a random sampling problem, and the off-grid imaging model for MRCI is established. Then, the probability distribution function (PDF) of the imaging amplitude for a single point target is analyzed, and the mean first-order imaging error (MFE) for multiple point targets is derived based on the Basic Correlation Algorithm (BCA). Finally, the relationship between the grid quantization of the imaging area and the performance of the MRCI system is analyzed, providing a theoretical guidance for enhancing the performance of MRCI. The validity of the analyses is verified through simulation experiments.

UPT-Flow: Multi-scale transformer-guided normalizing flow for low-light image enhancement

Low-light images often suffer from information loss and RGB value degradation due to extremely low or nonuniform lighting conditions. Many existing methods primarily focus on optimizing the appearance distance between the enhanced image and the normal-light image, while neglecting the explicit modeling of information loss regions or incorrect information points in low-light images. To address this, this paper proposes an Unbalanced Points-guided multi-scale Transformer-based conditional normalizing Flow (UPT-Flow) for low-light image enhancement. We design an unbalanced point map prior based on the differences in the proportion of RGB values for each pixel in the image, which is used to modify traditional self-attention and mitigate the negative effects of areas with information distortion in the attention calculation. The Multi-Scale Transformer (MSFormer) is composed of several global-local transformer blocks, which encode rich global contextual information and local fine-grained details for conditional normalizing flow. In the invertible network of flow, we design cross-coupling conditional affine layers based on channel and spatial attention, enhancing the expressive power of a single flow step. Without bells and whistles, extensive experiments on low-light image enhancement, night traffic monitoring enhancement, low-light object detection, and nighttime image segmentation have demonstrated that our proposed method achieves state-of-the-art performance across a variety of real-world scenes. The code and pre-trained models will be available at https://github.com/NJUPT-IPR-XuLintao/UPT-Flow.

Surface insight: Leveraging high-density dataset fusion for enhanced roughness classification

The ability to assess the surface quality quickly and accurately is of immense importance in manufacturing system. Modern metrology system along with machine learning is great at classification but requires more time. Traditionally accessing surface roughness is a time-consuming process. The progress in manufacturing technology necessitates improved approaches for quality control, specifically in the categorization of surface roughness, which has a substantial impact on the performance of materials. This research study introduces a novel method for classifying surface roughness by combining image data and point cloud data to create a comprehensive model. It then compares the performance of this model with a model that just relies on image data. A comprehensive analysis is conducted in this study, where image and point cloud data is collected and analysed. Multilinear principal component analysis (MPCA) along with random forest classifier is employed to create a model that classifies the surface texture. The primary goal is to showcase the enhanced precision and comprehensive understanding offered by the fused data model compared to the model that solely relies on images.Furthermore, the work presents a pragmatic approach for developing this enhanced model offline and applying it online in real-time production environments, with a particular focus on using only image data. This strategy is in line with the objectives of Industry 4.0, which seeks to achieve more intelligent and data-driven manufacturing processes. Subsequent investigations will prioritize expanding the model’s suitability to various manufacturing settings, particularly highlighting its capacity to ensure quality in manufacturing lines through the utilization of images.

Computing laminate composite voxel properties using Mirtich formulas

AbstractComputational homogenization methods offer deeper insights into the mechanical behavior of heterogeneous materials, often exhibiting complex anisotropic properties due to intricate manufacturing processes. Micromechanical techniques exploit the knowledge of the material's microstructure to predict effective behavior. Digital material data, represented as voxels, require processing numerous image points. Despite the computational power of modern fast Fourier transform‐based numerical solvers, performance improvements are still valuable. The composite voxel technique, in its original form, furnishes voxels containing more than one material with a surrogate material law, resulting in higher accuracy. This work contributes to the understanding and application of composite voxels in computational micromechanics by integrating them into a level‐set‐based framework, providing a detailed methodology for deriving laminate composite properties using the formulas of Mirtich, and demonstrating their potential to enhance computational performance through a numerical example.

Overview of Structure from Motion

In this paper is given an overview of tools and techniques for obtain information about the geometry of 3D scenes from 2D images. The generating three-dimensional structure from a series of 2D images or video of scenes is known as Structure from Motion (SfM). A central tenet of structure from motion is that, given the position of a feature in one image, it is possible to find the corresponding position of the same feature in successive images. We described methods for the simultaneous recovery of 3D points and camera projection matrices using corresponding image points in multiple views. Structure from Motion (SfM) is a fascinating field within computer vision that seeks to reconstruct a three-dimensional structure of the environment from a sequence of two-dimensional images. At the heart of SfM lies a set of sophisticated algorithms that enable the extraction of spatial information from a series of images. Two public repositories that may be of use are Open SfM and Colmap.

Enhanced Estimation of Crown-Level Leaf Dry Biomass of Ginkgo Saplings Based on Multi-Height UAV Imagery and Digital Aerial Photogrammetry Point Cloud Data

Ginkgo is a multi-purpose economic tree species that plays a significant role in human production and daily life. The dry biomass of leaves serves as an accurate key indicator of the growth status of Ginkgo saplings and represents a direct source of economic yield. Given the characteristics of flexibility and high operational efficiency, affordable unmanned aerial vehicles (UAVs) have been utilized for estimating aboveground biomass in plantations, but not specifically for estimating leaf biomass at the individual sapling level. Furthermore, previous studies have primarily focused on image metrics while neglecting the potential of digital aerial photogrammetry (DAP) point cloud metrics. This study aims to investigate the estimation of crown-level leaf biomass in 3-year-old Ginkgo saplings subjected to different nitrogen treatments, using a synergistic approach that combines both image metrics and DAP metrics derived from UAV RGB images captured at varying flight heights (30 m, 60 m, and 90 m). In this study, image metrics (including the color and texture feature parameters) and DAP point cloud metrics (encompassing crown-level structural parameters, height-related and density-related metrics) were extracted and evaluated for modeling leaf biomass. The results indicated that models that utilized both image metrics and point cloud metrics generally outperformed those relying solely on image metrics. Notably, the combination of image metrics obtained from the 60 m flight height with DAP metrics derived from the 30 m height significantly enhanced the overall modeling performance, especially when optimal metrics were selected through a backward elimination approach. Among the regression methods employed, Gaussian process regression (GPR) models exhibited superior performance (CV-R2 = 0.79, rRMSE = 25.22% for the best model), compared to Partial Least Squares Regression (PLSR) models. The common critical image metrics for both GPR and PLSR models were found to be related to chlorophyll (including G, B, and their normalized indices such as NGI and NBI), while key common structural parameters from the DAP metrics included height-related and crown-related features (specifically, tree height and crown width). This approach of integrating optimal image metrics with DAP metrics derived from multi-height UAV imagery shows great promise for estimating crown-level leaf biomass in Ginkgo saplings and potentially other tree crops.

Assessing grapevine water status through fusion of hyperspectral imaging and 3D point clouds

Mild to moderate and timely water deficit is desirable in grape production to optimize fruit quality for winemaking. It is crucial to develop robust and rapid approaches to assess grapevine water stress for scheduling deficit irrigation. Hyperspectral imaging (HSI) has the potential to detect changes in leaf water status, but the robustness and accuracy are restricted in field applications. The varied leaf orientations can significantly affect how light interacts with the plant, ultimately influencing the reflectance properties. This study focused on developing an approach for detecting grapevine water status using HSI and 3D data. Leaf orientation parameters derived from 3D point clouds were integrated with spectral signatures to address the spectral variance caused by variations in leaf orientation. A water status assessment model was developed based on multiblock partial least squares (MBPLS) to estimate midday leaf water potential (ΨL) using spectral signatures and leaf orientation parameters. HSI and 3D point clouds of selected leaves were captured simultaneously in a vineyard during the 2021 growing season, and ΨL was measured as the ground truth to assess the model performance. Mean spectral reflectance was derived from the hyperspectral images, while leaf orientation parameters were extracted from 3D point cloud data. The dataset was split randomly into 70% training/calibration and 30% test datasets. The test result shows that the model estimated the ΨL with R2 = 0.89, RMSE=0.12 MPa and MAE=0.09 MPa. The leaf orientation parameters derived from 3D point clouds had a contribution of 6.25% in estimating ΨL. Moreover, it acted as an enhancing component that explained the spectral variance caused by variations in leaf orientation and improved the interpretation of the underlying relationship between spectral reflectance and vine water status.

Local slope tolerance model for optical surfaces with distortion as the evaluation criterion

Ultra-precision imaging systems support cutting-edge scientific exploration and technological innovation. The continuous development of optical freeform and aspheric surface technology offers new possibilities for high-performance optical systems but also presents significant manufacturing challenges. In this paper, we derive and discuss in detail the impact of surface manufacturing errors on the image point positions of optical systems. The analysis reveals that among the manufacturing errors, the surface slope error is the primary factor driving positional changes in image points. Based on these insights, a local slope tolerance model using distortion as the evaluation criterion is proposed. This model specifies the slope error requirements at each point on the surface, ensuring the optical system's distortion meets the acceptable threshold during manufacturing. The model’s effectiveness is validated through an off-axis three-mirror freeform optical system and a Cassegrain aspheric optical system.

Global calibration method for multi-view-based vibration measurement of large structures

A multi-view global calibration method is proposed to overcome the limitations of overlapping regions in multi-view structural vibration measurement. This method establishes a mapping relationship from image points to experimental model points at the outset of vibration measurement, enabling a one-time global calibration of multi-view vibration response data. Furthermore, an image point detection method based on shape-function matching is designed to improve global calibration accuracy. Experimental results demonstrate that the proposed method excels in point detection and global calibration. Finally, the feasibility of this method is validated through vibration experiments on large aircraft fuselage structures.

Monocular visual detection of coal flow rate in scraper conveyor based on template matching background differencing

Abstract The monitoring of coal flow is a crucial aspect of the intelligent regulation and control of comprehensive mining equipment. In recent years, machine vision technology has become a mainstream method for quickly and efficiently extracting coal flow information. However, the majority of research in this field has focused on belt conveyors, with relatively limited investigation into the use of this technology with scraper conveyors. In order to address the need for monitoring coal flow in scraper conveyors, a monocular visual detection method of coal flow rates based on template matching-background differencing is proposed. First, the region of interet in the images captured using a monocular camera mounted at a specific location is quickly identified using an enhanced template matching method. Second, the image motion region is segmented using interframe and background differencing. Finally, the coal flow rate is calculated on the basis of the number of pixel points in the segmented image. Experimental verification is performed using scraper conveyor test bench and real underground data. The results demonstrate that the proposed coal flow detection method is capable of achieving real-time detection of coal flow in scraper conveyor and provides a theoretical basis for the monitoring of coal flow of the scraper conveyor.

Pengaruh Kualitas Pelayanan, Athmosphere Store, Bundling Product dan Point Of Purchase terhadap Impulsive Buying Melalui Corporate Image Sebagai Variabel Intervening

This research aims to examine the influence of service quality, Atmosphere Store, bundling product and point of purchase to Impulsive buying through Corporate image as an intervening variable. The study was conducted on Alfamart Members in the North Ciamis Region. Sampling is carried out using techniques propotioned stratified random sampling, with a total sample size of 210 samples, spread across 16 Alfamart stores in the North Ciamis Region. The research instrument used was a questionnaire with a Likert scale. The analysis technique used is structural equation modeling with the smartPLS application. The results of this research show that, 1) Service quality is in good condition, whereas Atmosphere Store, Bundling product, Point of purchase, Corporate image and Impulsive buying in very good condition; 2) Quality of service, Atmosphere Store, Bundling product and Point of purchase positive and significant effect on Corporate image; 3) Quality of service, Atmosphere Store, Bundling product and Point of purchase positive and significant effect on Impulsive buying; 4) Corporate image positive and significant effect on Impulsive buying; 5) Quality of service, Atmosphere Store, Bundling product and Point of purchase influence on Impulsive buying through Corporate image as an intervening variable.

A calibration method for telecentric line-scan cameras with an enhanced dynamic imaging model and initial estimates derived from direct linear transformation

This study presents a calibration method for telecentric line-scan cameras, incorporating a dynamic imaging model and initial estimates derived from direct linear transformation. The enhanced dynamic imaging model includes an inclination parameter instead of velocities in three orthogonal spatial directions. It is applicable to any direction of motion, considers lens distortion, and accommodates the line sensor at an arbitrary position relative to the optical axis. Employing the enhanced camera model, the initial values of telecentric line-scan camera parameters are determined derived from direct linear transformation. Sensitivity of our method with respect to the noise level of image points and the number of pattern planes are assessed through numerical simulations, while effectiveness and robustness are validated through experiments using real-world data, achieving a reprojection error of 0.6386 pixels and a standard deviation of 0.0160 pixels. The versatility of the proposed method can be extended to measurement applications utilizing flatbed scanners.

Adenomyosis: An Update Concerning Diagnosis, Treatment, and Fertility.

This review article aims to summarize current tools used in the diagnosis of adenomyosis with relative pharmacological and surgical treatment and to clarify the relative association between adenomyosis and infertility, considering the importance of an accurate diagnosis of this heterogeneous disease. Among different reported concepts, direction invagination of gland cells from the basalis endometrium deep into the myometrium is the most widely accepted opinion on the development of adenomyosis. Adenomyosis has been increasingly identified in young women with pain, AUB, infertility, or no symptoms by using imaging techniques such as transvaginal ultrasound and magnetic resonance. Furthermore, adenomyosis often coexists with other gynecological conditions, such as endometriosis and uterine fibroids, increasing the heterogeneity of available data. However, there is no agreement on the definition and classification of adenomyotic lesions from both the histopathology and the imaging points of view, and diagnosis remains difficult and unclear. A standard, universally accepted classification system needs to be implemented to improve our understanding and inform precise diagnosis of the type of adenomyosis. This could be the key to designing RCT studies and evaluating the impact of adenomyosis on quality of life in terms of menstrual symptoms, fertility, and pregnancy outcome, given the high risk of miscarriage and obstetric complications.

Research progress of optic nerve imaging during 1991-2023: a bibliometric analysis.

Optic nerve imaging is crucial for diagnosing and understanding optic neuropathies because it provides detailed visualization of the nerve's structure and pathologies through advanced modalities. This study conducted a bibliometric analysis within the field of optic nerve imaging, aiming to pinpoint the latest research trends and focal points in optic nerve imaging. The core literature on optic nerve imaging published between January 1991 and August 2023 was retrieved from the Web of Science Core Collection. The analysis and visualization of scientific productivity and emerging trends were facilitated through the utilization of Bibliometrix software, CiteSpace, Gephi, VOSviewer, R software, and Python. In total, 15,247 publications on optic nerve imaging were included in the analysis. Notably, the top 3 journals contributing to this field were Investigative Ophthalmology & Visual Science, Ophthalmology, and the British Journal of Ophthalmology. This research on optic nerve imaging extended across 97 countries, with the USA leading in research endeavors. Noteworthy burst term analysis revealed that "Segmentation" and "Machine learning" are gaining attention. Additionally, the Latent Dirichlet Allocation model indicated that image processing has been a hotspot in recent years. This study revealed the research trends, hotspots, and emerging topics in optic nerve imaging through bibliometric analysis and network visualization. At present, the research focus is directed towards employing artificial intelligence for image post-processing. The findings of this study offer valuable insights into future research direction and clinical applications.