Video Camera Research Articles

Topological Reinforcement Adaptive Algorithm (TOREADA) Application to the Alerting of Convulsive Seizures and Validation with Monte Carlo Numerical Simulations

The detection of adverse events—for example, convulsive epileptic seizures—can be critical for patients suffering from a variety of pathological syndromes. Algorithms using remote sensing modalities, such as a video camera input, can be effective for real-time alerting, but the broad variability of environments and numerous nonstationary factors may limit their precision. In this work, we address the issue of adaptive reinforcement that can provide flexible applications in alerting devices. The general concept of our approach is the topological reinforced adaptive algorithm (TOREADA). Three essential steps—embedding, assessment, and envelope—act iteratively during the operation of the system, thus providing continuous, on-the-fly, reinforced learning. We apply this concept in the case of detecting convulsive epileptic seizures, where three parameters define the decision manifold. Monte Carlo-type simulations validate the effectiveness and robustness of the approach. We show that the adaptive procedure finds the correct detection parameters, providing optimal accuracy from a large variety of initial states. With respect to the separation quality between simulated seizure and normal epochs, the detection reinforcement algorithm is robust within the broad margins of signal-generation scenarios. We conclude that our technique is applicable to a large variety of event detection systems.

Информационно-аналитическая система детектирования движения объектов на пешеходном переходе

To manage pedestrian and vehicle flows at intersections, systems are implemented that use adaptive traffic light models, adjusting time intervals based on the volume of pedestrians and vehicles. These systems include video cameras that monitor road user movements, enhancing real-time traffic control. This paper introduces an information and analytical system for managing transport and pedestrian flows using the YOLO neural model, which enables object recognition. The system performs several operations: converting the original image to gray scale, applying Gaussian blurring, detecting object boundaries through the Canny filter and fuzzy logic for edge detection, and contour processing, where each identified contour is assigned a unique number. The neural network then compares detected contours to the training sample data, determining whether the object is a person or a vehicle. The paper presents experimental results for these algorithms in object recognition. Modified software and images of intersections with pedestrian crossings captured from street video cameras in Kursk were used in the experiments. The recognition accuracy rate from the experiments was 72.4%.

YOLOv5DA: An Improved YOLOv5 Model for Posture Detection of Grouped Pigs

Accurate posture detection is the foundation for analyzing animal behavior, which can promote animal welfare. With the development of computer vision, such technology has been widely used in analyzing animal behavior without physical contact. However, computer vision technology for pig posture detection often suffers from problems of missed or false detection due to complex scenarios. To solve the problem, this study proposed a novel object detection model YOLOv5DA, which was based on YOLOv5s and designed for pig posture detection from 2D camera video. Firstly, we established the annotated dataset (7220 images) including the training set (5776 images), validation set (722 images), and test set (722 images). Secondly, an object detection model YOLOv5DA based on YOLOv5s was proposed to recognize pig postures (standing, prone lying, and side lying), which incorporated Mosaic9 data augmentation, deformable convolution, and adaptive spatial feature fusion. The comparative and ablation experiments were conducted to verify the model’s effectiveness and reliability. Finally, we used YOLOv5DA to detect the posture distribution of pigs. The results revealed that the standing posture was more frequent in the morning and afternoon and the side-lying posture was most common at noon. This observation demonstrated that the posture of pigs is influenced by temperature variations. The study demonstrated that YOLOv5DA could accurately identify three postures of standing, prone lying, and side lying with an average precision (AP) of 99.4%, 99.1%, and 99.1%, respectively. Compared with YOLOv5s, YOLOv5DA could effectively handle occlusion while increasing the mean precision (mAP) by 1.7%. Overall, our work provided a highly accurate, effective, low-cost, and non-contact strategy of posture detection in grouped pigs, which can be used to monitor pig behavior and assist in the early prevention of disease.

Making a difference with matter in researchers’ positionality dynamics in qualitative inquiry

Scholars have increasingly highlighted the usefulness of new materialist theories and methodologies in attempts to address the perceived shortcomings of conventional theories inspired by social constructionism and post-structuralism. Contributing to these discussions, we utilize a new materialist theory which rests on a monistic ontology drawn from Spinozian and Deleuzian assemblage theory to examine the constitutive role of material elements (e.g. audio recorders, video cameras, and dress/shirts worn during interviews), spatial, and discursive forces in co-creating fluid nonstatic researcher positionalities in qualitative research process. This article is part of a larger ethnographic study conducted by the first author among fisherfolk in Ghana's coastal fishing communities. Our results show that the researcher's fluid positionalities during interview encounters were brought to bear and sustained in space and time through the joint effort of material, discursive, and spatial forces. As qualitative researchers seek ways to ensure better understanding of their study communities through intimate interactions, an attention to the assemblage of material-discursive forces in interview encounters may highlight some of the opportunities and obstacles in qualitative inquiry beyond human agency and negotiations.

The connection of mise-en-scene camera movement in the visual image to cinematic decoration as elements of scenography Applying to the movie “Kira and the Jinn”

The connection of mise-en-scene camera movement in the visual image to cinematic decoration as elements of scenography Applying to the movie “Kira and the Jinn”

Methodology for Automatically Detecting Pan–Tilt–Zoom CCTV Camera Drift in Advanced Traffic Management System Networks

Many transportation agencies have deployed pan–tilt–zoom (PTZ) closed-circuit television (CCTV) cameras to monitor roadway conditions and coordinate traffic incident management (TIM), particularly in urbanized areas. Pre-programmed “presets” provide the ability to rapidly position a camera on regions of highways. However, camera views occasionally develop systematic deviations from their original presets due to a variety of factors, such as camera change-outs, routine maintenance, drive belt slippage, bracket movements, and even minor vehicle crashes into the camera support structures. Scheduled manual calibration is one way to systematically eliminate these positioning problems, but it is more desirable to develop automated techniques to detect and alert agencies of potential drift. This is particularly useful for agencies with large camera networks, often numbering in the 1000’s. This paper proposes a methodology using the mean Structured Similarity Index Measure (SSIM) to compare images for a current observation to a stored original image with identical PTZ coordinates. Analyzing images using the mean SSIM generates a single value, which is then aggregated every week to generate potential drift alerts. This methodology was applied to 2200 images from 49 cameras over a 12-month period, which generated less than 30 alerts that required manual validation to determine the confirmed drift detection rate. Approximately 57% of those alerts were confirmed to be camera drift. This paper concludes with the limitations of the methodology and future research opportunities to possibly increase alert accuracy in an active deployment.

Translational Tomography with the Wide-field Imager for Parker Solar Probe (WISPR). II. Refinements to the Method

We present progress on the translational tomography technique for measuring the three-dimensional structure of the corona from near-perihelion Wide-field Imager for Parker Solar Probe (WISPR) image sequences. Translational tomography makes use of noncircular motion of a camera to extract three-dimensional information from an optically thin subject. Parker Solar Probe (PSP) presents a special case both because of the particular structure of the corona and because of the nonlinear motion of the vantage point. We show improvements to a previous direct analytic method (described in Paper I of this series) and an alternative inversion pathway using a synthetic sequence of WISPR images. The newer method successfully reconstructs the correct locations of modeled coronal rays in a synthetic WISPR image sequence, with curvilinear camera motion modeled on the PSP orbit. We present the refined methodology and validation study, and show that the technique is ready for application to actual WISPR data.

Conceptualizing Mathematics Student Teachers' Approaches towards Responding to Availability of Tools and Resources in the Context of Knowledge Quartet

The purpose of this study is to conceptualize the approaches of secondary mathematics student teachers towards contingencies encountered during the teaching process within the context of responding to availability of tools and resources. In order to achieve the goal of the study based on the grounded theory, the nine secondary mathematics student teachers’ lessons were observed, and recorded using a video camera, and semi-structured interviews were performed. The data collection process ended after 54 lesson hours of observation, that is, when code saturation was reached. As a result, four sub-codes in the context of responding to availability of tools and resources were identified within the approaches of participants in relation to contingent moments. It is thought that conceptualizing the approaches of participants towards unplanned situations encountered during lessons in real class environment would prove to be beneficial in teacher training.

THE MOTIVATION OF PRACTICING SPORTS DANCE DURING PHYSICAL EDUCATION LESSONS IN ORDER TO IMPROVE THE SELF-IMAGE

Background. Motivational dynamics is always manifested at the level of global behavior, which means that understanding the motivational orientation of behavior requires a systemic view of it. Objectives. Sports dance - whose specific means we used in the experimental study, are effective ways to develop the self-image, the motivational system and the motivation to achieve the self-image. 70 subjects participated in the research, students from different faculties within the University of Bucharest, based on registration in the sports dance class. Among them, 50 female students and 20 male students, aged between 19 and 25, first-year students at the University of Bucharest. All of them opted for the sports dance class at the beginning of the 2022-2023 academic year. Sports dance lessons were held throughout the academic year according to the curriculum. Methods. The observation method: were monitored the indicators related to the efficiency of the execution, the improvement of the posture, of the body attitude, the efficiency of the communication, the relationship with the others, as relevant elements for the studied phenomenon. In addition to direct observation, the video camera and the computer were used. Speaking: using dialogue to obtain useful information. For the present research, the preferred subjects are: knowledge of the particularities of the motivational system; hierarchical organization of motives; knowledge of the conditional determinative and inhibiting factors for practicing of sports dance; evaluation and knowledge of the relationship between achievement motivation and self-image. Questionnaire-based survey: the questionnaire was developed to study self-image and self-esteem. It was developed and applied in order to study the importance that the subjects give to the sports dance practiced in the physical education class for the development of the motivation to realize the self-image. Statistical-mathematical method – statistical-mathematical processing of the data resulting from the questionnaire. Graphical representation method: Microsoft Excel was used. Results. The obtained results were ranked according to the score, tabulated, interpreted and presented graphically. Conclusion. The processing of the subjects results from the initial and final testing, highlights the awareness that has occurred on the benefits that the practice of physical exercises, in general and sports dance, in particular, brings to personal development. From the results of the study, it emerged that Sports Dance develops social intelligence, interpersonal relationships, communication ability, emotional intelligence, the ability to make voluntary effort, perceptive qualities.

KINEMATIC CHARACTERISTICS OF THE APPROACH RUN ON HANDSPRING VAULT BY HIGH LEVEL MALE GYMNASTS HIGH LEVEL MALE GYMNASTS

The approach run is a fundamental precondition for successful vault performance, as it enables the gymnast to develop maximum controlled horizontal velocity. The purpose of this study was to investigate the length, frequency, and velocity of steps during the run-up phase (approach run) in the execution of the handspring vault on the vaulting table. Nine high-level male artistic gymnasts, who performed the handspring vault under training conditions, volunteered to participate in the study. Five video cameras—four stationary and one scanning—were used to record the run-up phase, the hurdle step, and the take-off from the springboard. The gymnasts performed six trials of the handspring vault with a three-minute rest between each trial. Results showed that the final step was shorter than the penultimate step, and the penultimate step was longer than the preceding step. Additionally, the gymnasts demonstrated a gradual increase in their run-up velocity, a key requirement for a successful jump, up to the penultimate step. The average step frequency among gymnasts ranged from 3.20 to 4.88 steps per second, while the average step velocity across the six attempts was between 4.03 and 7.37 m/sec. Finally, a gradual increase in the gymnast’s velocity was observed up until the last step, with the final step being shorter than the penultimate step and the penultimate step being longer than the one before it.

Real-World Video Denoising for Visual Inspection in High-Dose Radiological Environments

In high-dose radiological environments, where precision and safety are of utmost importance, the ability to acquire accurate and clear visual information is of paramount importance for ensuring safety and reliability in critical industrial processes. However, these environments inherently introduce significant challenges due to the adverse effects of radiation on imaging equipment. As a consequence, inspection videos captured within such high-radiation environments often contain a significant amount of noise. This noise substantially complicates the task of identifying and assessing potential defects in vital components. It also diverts attention and resources toward investigating false positives created by noise, leading to inefficiencies, and for industrial processes on the critical path, this can further prolong the outage. Addressing this noise is essential not only for precision, but also for ensuring safety, reliability, and efficiency in critical industrial processes. In this paper, we present a custom-designed filter utilizing a priori information about camera position and trajectory to remove the noise from the inspection videos, making the defects easier to manually identify. As the camera movement is in one direction at a constant speed, the proposed approach uses this temporal and spatial information to accurately remove the noise. This approach applies to a subset of visual inspection problems throughout the nuclear industry, as well as many other industries where there is knowledge available about the camera speed and direction of travel. The proposed approach is compared with three accepted/well-known approaches, median filtering, bilateral filtering, and fast nonlocal means denoising, and an additional state-of-the-art deep learning model is also used for comparison. It was found that the proposed approach produces the most accurate video denoising in terms of visual quality and the retainment of the defect features throughout the videos tested.

AUTOMATED TECHNOLOGY OF MEASUREMENT OF PHYSIOLOGICAL PARAMETERS OF FARM ANIMALS

Abstract. The development and application of automated technologies in the agricultural sector have significantly transformed the management and monitoring of farm animals. This paper presents a comprehensive analysis of existing technical systems for measuring the physiological parameters of farm animals, particularly focusing on cows. The primary goal of these technologies is to enhance the accuracy and efficiency of health monitoring and to optimize livestock management through continuous data collection and analysis. Key technological solutions include the use of wireless data transmission systems, radio monitoring devices, and unmanned aerial vehicles (UAVs). These technologies enable real-time tracking of animal health parameters such as body temperature, heart rate, movement patterns, and other critical indicators. The use of various sensors, including ear, neck, and intra-body sensors, plays a crucial role in collecting primary physiological data. These sensors are integrated into a broader system that includes radio modules with built-in controllers for converting raw data into digital formats, enabling wireless transmission to central systems for processing and storage. The radio monitoring of animals allows for the continuous tracking of physiological and behavioral parameters across large areas, providing crucial insights into their well-being. It is particularly beneficial in detecting early signs of disease or health issues, ensuring timely intervention, and preventing potential economic losses for farmers. The integration of unmanned aerial vehicles (UAVs) further expands the capabilities of monitoring systems, enabling the visual assessment of animals' behavior and movement across vast pastures. Equipped with video cameras and data relays, UAVs collect video footage that is transmitted to a central processing unit for real-time analysis and storage. The combined use of radio monitoring and UAV technology forms a comprehensive framework for livestock management, allowing farmers to make data-driven decisions, optimize resource allocation, and improve overall herd health and productivity. By leveraging these automated systems, it becomes possible to reduce the dependency on manual labor, minimize human error, and ensure that animals are closely monitored without the need for constant physical presence. This represents a significant advancement in modern animal farming, aligning with global trends toward smart farming and precision agriculture. In conclusion, the integration of automated physiological monitoring technologies in farm animal management presents an innovative solution for enhancing animal welfare, improving farm efficiency, and reducing operational costs. These systems hold considerable potential for further advancements in the field of animal health monitoring, ultimately contributing to more sustainable and productive farming practices.

Optimization Study of Coal Gangue Detection in Intelligent Coal Selection Systems Based on the Improved Yolov8n Model

To address the low recognition accuracy of models for coal gangue images in intelligent coal preparation systems—especially in identifying small target coal gangue due to factors such as camera angle changes, low illumination, and motion blur—we propose an improved coal gangue separation model, Yolov8n-improvedGD(GD—Gangue Detection), based on Yolov8n. The optimization strategy includes integrating the GCBlock(Global Context Block) from GCNet(Global Context Network) into the backbone network to enhance the model’s ability to capture long-range dependencies in images and improve recognition performance. The CGFPN (Contextual Guidance Feature Pyramid Network) module is designed to optimize the feature fusion strategy and enhance the model’s feature expression capabilities. The GSConv-SlimNeck architecture is employed to optimize computational efficiency and enhance feature map fusion capabilities, thereby improving the model’s robustness. A 160 × 160 scale detection head is incorporated to enhance the sensitivity and accuracy of small coal and gangue detection, mitigate the effects of low-quality data, and improve target localization accuracy.

People Counting from Moving Camera Videos through PeopleNet Framework

People Counting from Moving Camera Videos through PeopleNet Framework

Model test study on the dynamic failure process of tunnel surrounding rocks in jointed rock mass under explosive load

The presence of joints can significantly reduce the integrity and stability of an engineering rock mass. Under dynamic loads, such as from blasting excavation, the key blocks divided by joints may be destabilized and prone to sliding, potentially leading to engineering geological disasters like rockbursts. To study the dynamic instability process, similar materials for the rock mass and joints were developed based on the similarity theory, and a tunnel model in the jointed rock mass was constructed. Subsequently, a detonating fuse was used to generate a dynamic load, and the dynamic instability process of the tunnel surrounding rock in the jointed rock mass under explosive load was studied using the geotechnical multifunctional testing device. The deformation characteristics and dynamic instability process of the tunnel surrounding rock were analyzed using acceleration sensors, resistance strain gages, linear variable displacement transducers and motion camera. The study shows that the acceleration at the tunnel vault is significantly greater than at the straight wall and floor under blast loads, with differences reaching an order of magnitude. Acceleration waveforms were classified into three categories based on peak characteristics, explained through the propagation of explosive stress waves. Additionally, strain and displacement at the tunnel arch were also significantly greater than in other areas, indicating more severe stress concentration and dynamic damage at the arch, necessitating reinforced support in tunnel excavation. The entire dynamic instability process of the tunnel surrounding rock was successfully recorded using a motion camera. The dynamic failure process was divided into several phases, the appearance of cracks on the joint surface, particle ejection accompanied by the dropping of jointed blocks, a significant drop of the jointed blocks, and return to calm. The dynamic failure modes include the dropping and rotation of jointed blocks, local particle ejection, and shear cracks on jointed block.

IMU Airtime Detection in Snowboard Halfpipe: U-Net Deep Learning Approach Outperforms Traditional Threshold Algorithms

Airtime is crucial for high-rotation tricks in snowboard halfpipe performance, significantly impacting trick difficulty, the primary judging criterion. This study aims to enhance the detection of take-off and landing events using inertial measurement unit (IMU) data in conjunction with machine learning algorithms since manual video-based methods are too time-consuming. Eight elite German National Team snowboarders performed 626 halfpipe tricks, recorded by two IMUs at the lateral lower legs and a video camera. The IMU data, synchronized with video, were labeled manually and segmented for analysis. Utilizing a 1D U-Net convolutional neural network (CNN), we achieved superior performance in all of our experiments, establishing new benchmarks for this binary segmentation task. In our extensive experiments, we achieved an 80.34% lower mean Hausdorff distance for unseen runs compared with the threshold approach when placed solely on the left lower leg. Using both left and right IMUs further improved performance (83.37% lower mean Hausdorff). For data from an algorithm-unknown athlete (Zero-Shot segmentation), the U-Net outperformed the threshold algorithm by 67.58%, and fine-tuning on athlete-specific (Few-Shot segmentation) runs improved the lower mean Hausdorff to 78.68%. The fine-tuned model detected takeoffs with median deviations of 0.008 s (IQR 0.030 s), landing deviations of 0.005 s (IQR 0.020 s), and airtime deviations of 0.000 s (IQR 0.027 s). These advancements facilitate real-time feedback and detailed biomechanical analysis, enhancing performance and trick execution, particularly during critical events, such as take-off and landing, where precise time-domain localization is crucial for providing accurate feedback to coaches and athletes.

AI-Driven Particulate Matter Estimation Using Urban CCTV: A Comparative Analysis Under Various Experimental Conditions

Despite the high public interest in particulate matter (PM), a key determinant for indoor and outdoor activities, the current PM information provided by monitoring stations (e.g., data per administrative district) is insufficient. This study employed the closed-circuit television (CCTV) cameras densely installed within a city to explore the spatial expansion of PM information. It conducted a comparative analysis of PM estimation effects under diverse experimental conditions based on AI image recognition. It also fills a gap by providing an optimal analysis framework that comprehensively considers the combination of variables, including the sun’s position, day and night settings, and the PM distribution per class. In the deep learning model structure and process comparison experiment, the hybrid DL-ML model using ResNet152 and XGBoost showed the highest predictive power. The classification model was better than the ResNet regression model, and the hybrid DL-ML model with the post-processed XGBoost was better than the single ResNet152 model regarding AI prediction of PM. All four experiments that excluded the nighttime, added the solar incidence angle variable, applied the distribution of PM per class, and removed the outlier removal algorithm showed high predictive power. In particular, the final experiment that satisfied all conditions, including the exclusion of nighttime, addition of solar incidence angle variable, and application of outlier removal algorithm, derived predictive values that are expected to be commercialized.

How Many Events are Needed for One Reconstructed Image Using an Event Camera?

Abstract. Event cameras offer significant advantages over traditional cameras, including high temporal resolution, high dynamic range, and low power consumption. However, reconstructing images from the asynchronous events generated by these cameras presents unique challenges. This paper investigates the optimal number of events needed for high-quality image reconstruction using event cameras. We evaluate two primary reconstruction strategies—fixed time window and fixed number of events—across various dynamic and static scenes. Our study includes scenarios with different lighting conditions and camera movements. Using the state-of-the-art E2VID algorithm, we perform both qualitative and quantitative analyses of the reconstructed images, comparing them with reference frames from a traditional RGB camera. Our results demonstrate the trade-offs between temporal resolution and image quality for each reconstruction strategy, providing insights into the optimal settings for different applications. This research offers practical guidelines for selecting appropriate reconstruction parameters to achieve the better image quality from event cameras.

In the arm-in-cage test, topical repellents activate mosquitoes to disengage upon contact instead of repelling them at distance

Topical repellents provide protection against mosquito bites and their efficacy is often assessed using the arm-in-cage test. The arm-in-cage test estimates the repellent’s protection time by exposing a repellent-treated forearm to host-seeking mosquitoes inside a cage at regular intervals until the first confirmed mosquito bite. However, the test does not reveal the repellents’ behavioural mode of action. To understand how mosquitoes interact with topical repellents in the arm-in-cage test, we used a 3D infrared video camera system to track individual Aedes aegypti and Anopheles stephensi females during exposure to either a repellent-treated or an untreated forearm. The repellents tested were 20% (m/m) ethanolic solutions of N, N-diethyl-meta-toluamide, p-menthane-3,8-diol, icaridin and ethyl butylacetylaminopropionate. All four repellents substantially reduced the number of bites compared to an untreated forearm, while the flight trajectories indicate that the repellents do not prevent skin contact as the mosquitoes made multiple brief contacts with the treated forearm. We conclude that, in the context of the arm-in-cage test, topical repellents activate mosquitoes to disengage from the forearm with undirected displacements upon contact rather than being repelled at distance by volatile odorants.

The effect of non-uniform skelp temperature on X70 steel coil cooling

This study explored the effect of varying steel skelp temperature (500 °C–600 °C) on the subsequent temperature-time ( T- t) profile during and after coiling of low C (0.05 wt. %) X70 microalloyed steels. Three industrially produced steel coils with similar rough rolling temperatures (∼1050 °C) and finish rolling temperatures (∼850 °C) but different coiling temperatures (500 °C–600 °C) and different skelp thicknesses (19 mm and 25 mm) were studied. The surface temperature of each coil was measured using an infrared video camera. A three-dimensional heat transfer model was developed to predict the T- t profiles. A lower (∼60 °C) initial skelp temperature near the head and tail of the skelp led to a reduced coil temperature. A higher (∼50 °C) temperature near the head and tail region of the skelp resulted in a more uniform coil temperature (a difference of ∼10 °C instead of ∼50 °C).