Video Images Research Articles

Supercooled Water Droplets Impacting at High Speed on Superhydrophobic Surfaces: Open Questions Related to Icephobicity

It is posited that impact ice adhesion strength on superhydrophobic surfaces is related to droplet impalement. Several gaps still exist in the understanding of how different types of textured surfaces resist the impalement of high‐speed impacting droplets (<102 μm diameter at 102–103 m s−1). A previous study reveals that a pressure balance calculation can predict the wetting state of an impacting drop (≈103 μm diameter at ≈101 m s−1). However, the ability of this model to predict the wetting state of small droplets impacting at high speed or of droplets in a supercooled state has not been reported. To better understand supercooled microdroplet impalement, and to verify the hypothesis that droplet impalement is directly related to ice adhesion strength, herein, the impact behavior of microdroplets in a cold airflow onto surfaces of varying topography and wettability in an icing wind tunnel with support of high‐speed video images are investigated. Although the results do not allow for validating the above hypothesis about impalements and ice adhesion, they show that the difference between supercooled droplet spreading and retraction can be a predictor of ice adhesion strength. However, this relation must be validated with a greater body of data from samples with very diverse surface properties.

On the Nearshore Significant Wave Height Inversion from Video Images Based on Deep Learning

On the Nearshore Significant Wave Height Inversion from Video Images Based on Deep Learning

Integration Approaches in Forensic Portrait Examination

The article reviews some actual issues of the theory and practice of the production of forensic portrait examinations: the tight deadlines of the preliminary investigation, the increased time expenditures to produce forensic video examination, the need for an integrated approach to the training of forensic portrait experts. The author proposes to revise some approaches to the training of forensic experts in the field of forensic portrait examinations. Along with the possibility of a comprehensive forensic examination, taking into consideration current needs of practice, more attention needs to be paid to software application for processing photo and video images processing in order to improve visual perception of the information displayed and to study montage marks and their detectability. All this will contribute to the evolvement of a portrait examiner as a specialist of double competence.

A microwave discharge in high-velocity flows initiated by a half-wave antenna

A microwave discharge in high-velocity (150—250 m/s) air flows induced on a half-wave vibrator is studied. A cw magnetron microwave generator with a frequency of 2.45 GHz and an output power of up to 5 kW was used for initiation of the microwave discharge. The high-speed video imaging was used for studying the discharge structure, determining the diameter and length of the plasma channel as a function of flow velocity and pressure. Electron concentration and temperature, along with characteristic gas temperature, were determined based on the optical spectra. The possibility of using this microwave discharge for ignition of hydrocarbon–air mixtures in combustion chambers of ramjet engines is proved experimentally.

Модель та метод навчання детектора об’єктів на аерозображенні з оптимізацією робастності та кількості обчислень

The subject of research is Neural network-based object detectors, which are widely used for video image analysis. An increasing number of tasks now demand data processing directly at the source, which limits the available computational resources. However, the vulnerability of neural networks to noise, adversarial attacks, and weight error injections significantly diminishes their robustness and overall effectiveness. The relevant task is to develop models that provide both computational efficiency and robustness against perturbations. This paper investigates a model and method for enhancing the robustness of neural network detectors under limited resources. The objective is to design a model that allocates resources optimally while maintaining stability. To achieve this, the study employs techniques such as dynamic neural networks, robustness optimization, and resilience strategies. The following results were obtained. A detector with a feature extractor based on ViT-S/16, modified with gate modules for dynamic examination was developed. The model was trained on the RSOD dataset and meta-learned on the adaptation results to various perturbations. The model's resistance to random bit inversions in weights (10 % of weights) and to adversarial attacks with perturbation amplitudes up to 3/255 (L∞ norm) was tested. Conclusion. The proposed detector model incorporating dynamic examination and optimized robustness, reduced floating-point operations by over 20 % without loss of accuracy. A novel method for training the detector was developed, combining the RetinaNet loss function with the loss function of gate blocks and applying meta-learning on the adaptation results for various types of synthetic perturbations. Testing demonstrated an increase in accuracy by 11.9 % under the influence of error injection and by 13.2 % under the influence of adversarial attacks.

A geometric model with stochastic error for abnormal motion detection of portal crane bucket grab

Abnormal swing angle detection of bucket grabs is crucial for efficient harbor operations. In this study, we develop a practically convenient swing angle detection method for crane operation, requiring only a single standard surveillance camera at the fly-jib head, without the need for sophisticated sensors or markers on the payload. Specifically, our algorithm takes the video images from the camera as input. Next, a fine-tuned ‘the fifth version of the You Only Look Once algorithm’ (YOLOv5) model is used to automatically detect the position of the bucket grab on the image plane. Subsequently, a novel geometric model is constructed, which takes the pixel position of the bucket grab, the steel rope length provided by the Programmable Logic Controller (PLC) system, and the optical lens information of the camera into consideration. The key parameters of this geometric model are statistically estimated by a novel iterative algorithm. Once the key parameters are estimated, the algorithm can automatically detect swing angles from video streams. Being analytically simple, the computation of our algorithm is fast, as it takes about 0.01 s to process one single image generated by the surveillance camera. Therefore, we are able to obtain an accurate and fast estimation of the swing angle of an operating crane in real-time applications. Simulation studies are conducted to validate the model and algorithm. Real video examples from Qingdao Seaport under various weather conditions are analyzed to demonstrate its practical performance.

Hydromechanical properties of metachronal swimming in polychaetes

Free-swimming polychaetes are common in marine habitats and exhibit a unique form of swimming whereby a metachronal wave occurs simultaneously with a bending body wave. This body wave is unusual among swimming animals because it travels in the same direction as the animal’s swimming direction. However, we currently lack a mechanistic understanding of this unusual form of locomotion. In this study we use a combination of high-speed, high-resolution video and particle image velocimetry (PIV) to quantify kinematics and fluid dynamics for three species of swimming polychaetes, spanning two orders of magnitude in size. We find that in all species, flows generated by metachronal waves of parapodia dominate while typical flows associated with body bending is absent. However, the parapodia are less flexible than propulsive structures in other metachronal swimmers. This creates a localized, but substantial upstream flow during the recovery stroke. Using body bending, the recovery stroke can occur mostly beneath the bulk flow from the power strokes, resulting in minimal inference while the subsequent power stroke can benefit from the pressure field generated during recovery. These results may have implications for future vehicle designs that incorporate metachronal locomotion.

Living histopathology - interrogation of ocular tissues by light: a celebration of the slit-lamp and a repertoire of clinical techniques.

The evolution of the slit-lamp microscope has enabled ophthalmologists to examine the transparent tissues of the eye with histological detail. This paper considers the history and optics of the slit-lamp. Optical sectioning and retro-illumination are discussed; particularly, effective placement of the reflected light beam. A variety of less conventional slit-lamp examination techniques is described. These include remote dark-field retro-illumination, examination through refractive surfaces (particularly, meniscus retro-illumination to demonstrate tear cells and non-contact corneal endothelial specular microscopy), location of vitreous abnormalities by parallax, expanding radial cords of vitreous cells in lymphoma, mirror examination of the superior fornix and corneal epithelial folds in ocular hypotension. It concludes with brief discussions about haemoglobin video imaging, semi-quantification of aqueous outflow volume by aqueous column cross-section area, and autofocus for video-microscopy.

Genesis of Music Video Clip as a Popular Form of Modern Audiovisual Culture: Experiments with Music Visualisation

The purpose of the article is to reveal the peculiarities of the development of the music video clip in the context of the historical interaction of musical and audiovisual culture. Research methodology. General scientific methods of cognition were applied, in particular analysis and synthesis, systematisation of theoretical data, the method of structural-functional analysis, which made it possible to reveal specific aspects of the interaction of music and various forms of artistic practices in the space of audiovisual culture; a typological method, with the help of which various features of the music video clip in the structure of modern audiovisual culture are revealed. Scientific novelty. The genesis of the music video clip as a popular form of modern audiovisual culture is studied; the problem of integration of visual images and music as part of artistic practices in historical retrospect is considered. Little-known works of foreign scientists, the problems of which are correlated with the subject area of research were introduced into scientific circulation. Conclusions. The genesis of the music video clip testifies to the significant role of artistic practices in the process of image and music interaction at the early stages, which contributed to the invention of new creative ways of representing the imaginary – animation and montage proposed by avant-garde artists; videos and video installations created by mastering the television image; music videos that opened a new dimension for experimentation, becoming an influential form of modern culture. Artistic history of analogue interactions between cinema and music during the 20th century demonstrates the antecedent conditions of production, perception, and socio-political context that were necessary for the mass popularization of the music video as an established form. Thanks to the early experiments in the formation of visualised music, the music video as a new form of audiovisual art gained cultural value, which allowed it to play a significant role at the modern stage. The music video played and continues to play a key role in the socio-cultural space. The technological evolution from analogue to digital means of production and display has accelerated the development of both the form and the aesthetics of the music video, which emphasises one of the most important roles of art in society – to provoke thought and encourage a rethinking of social, political and cultural conditions and surroundings, using this is the main means of communication, including popular music.

Flocculation of fiber suspensions studied by Rheo-OCT

When dealing with papermaking fiber suspensions, particle flocculation takes place even before the paper web is formed. The particle flocculation depends on several aspects, including particle mass concentration (consistency), particle collisions, electrochemical interactions promoted by chemical additives, etc. Due to its impor-tance, fiber suspension flocculation has been studied for a long time in papermaking, and several methods have been developed for this purpose. The traditional techniques include, for example, focused beam reflectance micros-copy (FBRM) and high-speed video imaging (HSVI). Recently, a new optical method, optical coherence tomography (OCT), has emerged for flocculation analysis. The advantages of OCT are the possibility to study opaque suspensions, its micron-level resolution, and its high data acquisition speed. The OCT measurements can be combined with rheological (Rheo) measurements, allowing simul-taneous measurement of both the time evolution of the floc size and the suspension viscosity. In this work, we used this approach, Rheo-OCT, to study the flocculation of suspensions of various papermaking furnishes. We analyzed the time evolution of the floc size and the fiber suspension viscosity when the studied paper-making suspensions were treated with highly refined furnish (HRF) — a furnish that contained a significant amount of micofibrillated cellulose (MFC)-type fibrils — and/or chemical additives. Such studies can lead to a better under-standing of the impact of flocculation on the produced paper web in terms of qualities like formation, drainage potential, and strength behavior.

Evaluating Methods for Violence Classification and Firearm Detection in Indoor CCTV Environment

The adoption of security systems based on computer vision for violence detection has the potential to significantly improve safety in various public and private properties. However, developing these systems can be extremely challenging.We can choose to use classification models to identify violence in images or also use object detection models to identify firearms, which may indicate robbery. Additionally, when developing such systems focused on private environments, we encounter specific challenges, such as obtaining appropriate datasets to train the algorithms. Many publicly available datasets for violence detection consist of outdoor images, with elements such as streets and cars, which do not adequately reflect the nuances and unique characteristics of private properties. In this work, we evaluate both learned and handcrafted features to classify videos as 'violence' or 'non-violence' across a variety of datasets, including a new dataset composed exclusively of closed-circuit television (CCTV) images. Additionally, we propose a new dataset for firearm detection in CCTV images and conduct some experiments using YoloV8. In this way, we hope to provide a clearer insight into the possible decisions when developing a security system for indoor environments.

Prototype for Multi-UAV Monitoring–Control System Using WebRTC

Most unmanned aerial vehicle (UAV) ground control station (GCS) solutions today are either web-based or native applications, primarily designed to support a single UAV. In this paper, our research aims to provide an open, universal framework intended for rapid prototyping, addressing these objectives by developing a Web Real-Time Communication (WebRTC)-based multi-UAV monitoring and control system for applications such as automated power line inspection (APOLI). The APOLI project focuses on identifying damage and faults in power line insulators through real-time image processing, video streaming, and flight data monitoring. The implementation is divided into three main parts. First, we configure UAVs for hardware-accelerated streaming using the GStreamer framework on the NVIDIA Jetson Nano companion board. Second, we develop the server-side application to receive hardware-encoded video feeds from the UAVs by utilizing a WebRTC media server. Lastly, we develop a web application that facilitates communication between clients and the server, allowing users with different authorization levels to access video feeds and control the UAVs. The system supports three user types: pilot/admin, inspector, and customer. Our research aims to leverage the WebRTC media server framework to develop a web-based GCS solution capable of managing multiple UAVs with low latency. The proposed solution enables real-time video streaming and flight data collection from multiple UAVs to a server, which is displayed in a web application interface hosted on the GCS. This approach ensures efficient inspection for applications like APOLI while prioritizing UAV safety during critical scenarios. Another advantage of the solution is its integration compatibility with platforms such as cloud services and native applications, as well as the modularity of the plugin-based architecture offered by the Janus WebRTC server for future development.

Automated system for classifying images of video streams for timely detection of fires

ABSTRACT Early detection of a fire during its development stage is highly desired to minimize human and material losses. The improvement of the efficiency of these monitoring systems through the analysis of fire video data drawn from unmanned aerial vehicles is considered . Classification of video images when monitoring a fire event on the territory is used based on their segmentation into identical rectangular segments of a given size and then assigning them to one of three classes: Smoke, Flame, and Indifferent classes. The Walsh-Hadamard transform was used to form descriptors for the Weak classifiers. Descriptors were calculated for three Weak classifiers; first, the Walsh-Hadamard transform was calculated for the window of the entire segment, and its spectral coefficients were used for the first Weak classifier. Next, the descriptors were calculated in windows whose sizes were half and a quarter of the original window size. The classifier consisted of three independently-trained neural networks. A simple ensemble averaging block was used to combine the outputs of those networks. A special software code has been developed to classify video images. The code allows us to create a database of segments of the ‘Smoke’ and ‘Flame’ classes, determine the two-dimensional Walsh-Hadamard spectrum of video image segments, train fully connected neural networks, conduct exploratory analysis and evaluate the relevance of the calculated two-dimensional spectral coefficients. For validation we used real data from Сlosed Circuit Television cameras presented in open databases. The experimental studies on the classification of video data containing flames and smoke showed that the proposed method has an average smoke detection accuracy of 86% and an average flame detection accuracy of 89.5%. Errors II in smoke detection and flame detection had the averages of 13% and 4.5%, respectively.

Real-Time Decoding of Snapshot Compressive Imaging Using Tensor FISTA-Net.

Snapshot compressive imaging (SCI) cameras compress high-speed videos or hyperspectral images into measurement frames. However, decoding the data frames from measurement frames is compute-intensive. Existing state-of-the-art decoding algorithms suffer from low decoding quality or heavy running time or both, which are not practical for real-time applications. In this article, we exploit the powerful learning ability of deep neural networks (DNN) and propose a novel tensor fast iterative shrinkage-thresholding algorithm net (Tensor FISTA-Net) as a real-time decoder for SCI cameras. Since SCI cameras have an accurate physical model, we can trade training time for the decoding time by generating abundant synthetic data and training a decoder on the cloud. Tensor FISTA-Net not only learns a sparse representation of the frames through convolution layers but also reduces the decoding time and memory consumption significantly through tensor operations, which makes Tensor FISTA-Net an appropriate approach for a real-time decoder. Our proposed Tensor FISTA-Net obtains an average PSNR improvement of 0.79-2.84 dB (video images) and 2.61-4.43 dB (hyperspectral images) over the state-of-the-art algorithms, along with more clear and detailed visual results on real SCI datasets, Hammer and Wheel, respectively. Our Tensor FISTA-Net reaches 45 frames per second in video datasets and 70 frames per second in hyperspectral datasets, meeting the real-time requirement. Besides, the trained model occupies only a 12 -MB memory footprint, making it applicable to real-time Internet of Things (IoT) applications.

Monitoring and Analysis of Human Activities Using Heterogeneous Sensors in the Gas Room of a Hospital

Every hospital relies on the gas pipeline system. There are common three types of gases are used: oxygen, nitrogen, and nitrous oxide. Each type of gas is critical in many departments, including the operating room and intensive care unit. Gas room administrators, such as engineers or hospital personnel, are just as important as gas rooms. If something happens to engineers or personnel, an unattended gas room may malfunction and cause trouble in the hospital. Therefore, we proposed a monitoring system with a human activity surveillance project using accelerometer sensors, video images, and gas sensors. This system can collect all the signals used for the analysis of the posture or activities of the personnel who examine the gas in the gas room. We also developed surveillance in the event of an unexpected event in the gas room.

Development and Implementation of a Multicenter Registry for Resuscitation-Focused Transesophageal Echocardiography

To evaluate the clinical effect, safety, and clinical outcomes of focused transesophageal echocardiography (TEE) in the evaluation of critically ill patients in the emergency department (ED) and ICUs. We established a prospective, multicenter, observational registry involving adult critically ill patients in whom focused TEE was performed for evaluation of out-of-hospital cardiac arrest (OHCA), inhospital cardiac arrest, evaluation of undifferentiated shock, hemodynamic monitoring, and/or procedural guidance in the ED, ICU, or operating room setting. The primary objective of the current investigation was to evaluate the clinical influence and safety of focused, point-of-care TEE in critically ill patients. Data elements included patient and procedure characteristics, laboratory values, timing of interventions, clinical outcomes, and TEE video images. A total of 1,045 focused TEE studies were collected among 916 patients from 28 hospitals, including 585 (64%) intraarrest and postarrest OHCA and inhospital cardiac arrest, 267 (29%) initial evaluation of undifferentiated shock, 101 (11%) procedural guidance, and 92 (10%) hemodynamic monitoring. TEE changed management in 85% of patients with undifferentiated shock, 71% of patients with inhospital cardiac arrest, and 62% of patients with OHCA. There were no reported esophageal perforations or oropharyngeal injuries, and other procedural complications were rare. A prospective, multicenter, and multidisciplinary TEE registry was successfully implemented, and demonstrated that focused TEE is safe and clinically impactful across multiple critical care applications. Further studies from this research network will accelerate the development of outcome-oriented research and knowledge translation on the use of TEE in emergency and critical care settings.

Decreased diaphragm moving distance measured by ultrasound speckle tracking reflects poor prognosis in amyotrophic lateral sclerosis

ObjectiveDecreased cephalocaudal diaphragm movement may indicate respiratory dysfunction in amyotrophic lateral sclerosis (ALS). We aimed to evaluate diaphragm function in ALS using ultrasound speckle tracking, an image-analysis technology that follows similar pixel patterns. MethodsWe developed an offline application that tracks pixel patterns of recorded ultrasound video images using speckle-tracking methods. Ultrasonography of the diaphragm movement during spontaneous quiet respiration was performed on 19 ALS patients and 21 controls to measure the diaphragm moving distance (DMD) in the cephalocaudal direction during a single respiration. We compared respiratory function measures and analyzed the relationship between the clinical profiles and DMD. ResultsDMD was significantly lower in ALS patients than in the control group (0.6 ± 1.4 mm vs 2.2 ± 2.2 mm, p < 0.01) and positively correlated with phrenic nerve compound motor action potential amplitude (R = 0.63, p = 0.01). DMD was negatively correlated with the change in the ALS Functional Rating Scale-Revised scores per month after the exam (R = −0.61, p = 0.02), and those with a larger rate of decline had a significantly lower DMD (p = 0.03). ConclusionsDiaphragm ultrasound speckle tracking enabled the detection of diaphragm dysfunction in ALS. SignificanceDiaphragm ultrasound speckle tracking may be useful for predicting prognosis.

Deep learning neural network-assisted badminton movement recognition and physical fitness training optimization

This work aims to solve the problem of low accuracy in recognizing the trajectory of badminton movement. This work focuses on the visual system in badminton robots and conducts side detection and tracking of flying badminton in two-dimensional image plane video streams. Then, the cropped video images are input into a convolutional neural network frame by frame. By adding an attention mechanism, it helps identify the badminton movement trajectory. Finally, to address the detection challenge of flying badminton as a small target in video streams, the deep learning one-stage detection network, Tiny YOLOv2, is improved from both the loss function and network structure perspectives. Moreover, it is combined with the Unscented Kalman Filter algorithm to predict the trajectory of badminton movement. Simulation results show that the improved algorithm performs excellently in tracking and predicting badminton trajectories compared with the existing algorithms. The average accuracy of the proposed method for tracking badminton trajectories is 91.40 %, and the recall rate is 84.60 %. The average precision, recall, and frame rate of the measured trajectories in four simple and complex scenarios of badminton flight video streams are 96.7 %, 95.7 %, and 29.2 frames/second, respectively. They are all superior to other classic algorithms. It is evident that the proposed method can provide powerful support for badminton trajectory recognition and help improve the accuracy of badminton movement recognition.

Decomposition-Estimation-Reconstruction: An Automatic and Accurate Neuron Extraction Paradigm.

The extraction of spatiotemporal neuron activity from calcium imaging videos plays a crucial role in unraveling the coding properties of neurons. While existing neuron extraction approaches have shown promising results, disturbing and scattering background and unused depth still impede their performance. To address these limitations, we develop an automatic and accurate neuron extraction paradigm, dubbed as decomposition-estimation-reconstruction (DER), consisting of D-procedure, E-procedure, and R-procedure. Specifically, the D-procedure first decomposes the raw data into a low-rank background and a sparse neuron signal, and regularizes L0 -norm priors of intensity and gradient of the neuron signal to suppress blurring and artifact effects. Then, the E-procedure estimates the depth-dependent transmission of the neuron signal based on its bright and dark channel priors. The R-procedure finally integrates the depth estimation of the neuron signal as a content-importance weight into a constrained non-negative matrix decomposition framework, which facilitates accurate neuron locations to boost the quality of extracted neurons. These three procedures are coupled in a cascade manner, where the former copes with calcium imaging data to facilitate the subsequent one. Comprehensive experiments on neuron extraction from calcium imaging videos demonstrate the superiority of our DER paradigm in both qualitative results and quantitative assessments over state-of-the-art methods.

Multinational and Multimodal Character Framing of Political Candidates in Online News: Do Political and Media System Classifications Matter?

An evolving body of research generally referred to as visual politics has brought the heavy research focus on linguistic modalities of political communication closer to parity with visual emphasis. The study reported here transcends this schism by joining momentum toward multimodality as an ontological departure point for research. We expanded an existing visual instrument into a multimodal one and provided evidence that it reliably captures character framing of political candidates (stateliness, compassion, mass appeal, ordinariness, and sure loser) in German, Polish, and United States commercial online news. We focused on election coverage in these countries because they represent three distinct political and media systems (democratic-corporatist, polarized-pluralist, and hybrid) of the Global North. The quantitative content analysis sample we used spans 2,688 online news stories with seven political candidates identified in 6,560 cases across six modalities (still images, moving images, frozen video images, text, audio, and superimposed text). We found support for the hypothesis that political and media system latencies affect how news media frame the character traits of political candidates in both visual and linguistic modalities. Specifically, the competitive tendencies of majoritarian democracies manifested more clearly as candidate-centered, simplistic, and polarizing character framing in US media content than in journalistic output of multiparty consensus democracies. For example, US news media were more consistent in their portrayal of election winners and losers than German and Polish news media, emphasizing stateliness, compassion, and ordinariness in the winner while unambiguously assigning the negative sure loser frame to the election loser.