Video Camera Research Articles

An Optimal Feature Selection Method for Human Activity Recognition Using Multimodal Sensory Data

Recently, the research community has taken great interest in human activity recognition (HAR) due to its wide range of applications in different fields of life, including medicine, security, and gaming. The use of sensory data for HAR systems is most common because the sensory data are collected from a person’s wearable device sensors, thus overcoming the privacy issues being faced in data collection through video cameras. Numerous systems have been proposed to recognize some common activities of daily living (ADLs) using different machine learning, image processing, and deep learning techniques. However, the existing techniques are computationally expensive, limited to recognizing short-term activities, or require large datasets for training purposes. Since an ADL is made up of a sequence of smaller actions, recognizing them directly from raw sensory data is challenging. In this paper, we present a computationally efficient two-level hierarchical framework for recognizing long-term (composite) activities, which does not require a very large dataset for training purposes. First, the short-term (atomic) activities are recognized from raw sensory data, and the probabilistic atomic score of each atomic activity is calculated relative to the composite activities. In the second step, the optimal features are selected based on atomic scores for each composite activity and passed to the two classification algorithms: random forest (RF) and support vector machine (SVM) due to their well-documented effectiveness for human activity recognition. The proposed method was evaluated on the publicly available CogAge dataset that contains 890 instances of 7 composite and 9700 instances of 61 atomic activities. The data were collected from eight sensors of three wearable devices: a smartphone, a smartwatch, and smart glasses. The proposed method achieved the accuracy of 96.61% and 94.1% by random forest and SVM classifiers, respectively, which shows a remarkable increase in the classification accuracy of existing HAR systems for this dataset.

Dynamic fracture characterization of glass fiber composites reinforced with through-thickness nylon fibers

ABSTRACT A detailed experimental study is performed to investigate the mode-I dynamic fracture initiation toughness of through-thickness Nylon fibers reinforced glass/epoxy composites using a wet electrostatic flocking method. Composites of a double cantilever beam specimen configuration of two different deniers 1.5D and 3D of 0.75 mm long Nylon fibers with two different fiber densities 150 and 300 fiber/mm2 and composites without Nylon fibers (control) are fabricated. The dynamic fracture initiation toughness is investigated by using a modified split Hopkinson pressure bar setup with a novel fixture in conjunction with a high-speed video camera. In addition, rate sensitivity on dynamic fracture initiation toughness is also investigated for control and composites of 1.5D with fiber density of 300 fibers/mm2 as a function of three different rates of dynamic fracture toughness ( G ˙ = 1500, 2010, and 2,150 kJ/m2/s). Results show that for the composite of 3D–0.75 mm Nylon fiber, G IC values reach 0.78 kJ/m2 (110% increase) and 1.3 kJ/m2 (250% increase) at flock densities of 150 and 300 fibers/mm2 compared to the control sample with the lowest G IC value at 0.37 kJ/m2. The same pattern is observed for a 1.5D–0.75 mm configuration at the flock fiber density of 150 fiber/mm2 where G IC value demonstrates a 75% increase compared to control conditions. The dynamic fracture initiation toughness of flocked composites demonstrates significant rate sensitivity.

End-to-end training of acoustic scene classification using distributed sound-to-light conversion devices: verification through simulation experiments

We propose a framework for classifying acoustic scenes utilizing distributed sound sensor devices capable of sound-to-light conversion, which we term as Blinkies. These Blinkies can convert acoustic signals into varying intensities of light via an inbuilt light-emitting diode. By using Blinkies, we can aggregate the spatial acoustic information across a wide region by recording the fluctuating light intensities of numerous Blinkies distributed throughout the region. Nonetheless, the signal communicated is subject to the bandwidth limitation imposed by the frame rate of the video camera, typically capped at 30 frames per second. Our objective is to refine the process of transforming sound into light for the purpose of acoustic scene classification within these bandwidth confines. While traversing through the air, a light signal is affected by inherent physical limitations such as the attenuation of light and interference from noise. To account for these factors, we have integrated these physical constraints into differentiable physical layers. This approach enables us to jointly train a pair of deep neural networks for the conversion of sound to light and for the classification of acoustic scenes. Our simulation studies, which employed the SINS database for acoustic scene classification, demonstrated that our proposed framework outperforms the previous one that utilized Blinkies. These findings emphasize the effectiveness of Blinkies in the field of acoustic scene classification.

High-frequency study of megafaunal communities on whale bone, wood and carbonate in hypoxic Barkley Canyon

Organic-rich whale bones and wood falls occur widely in the deep sea and support diverse faunal communities, contributing to seafloor habitat diversity. Changes in community structure through succession on deep-sea bone/wood substrates are modulated by ecosystem engineers, i.e., bone-eating Osedax annelids, and wood-boring Xylophaga bivalves. Here, we use a comparative experimental approach and Ocean Networks Canada’s (ONC) cabled observatory in hypoxic Barkley Canyon to study, at high temporal resolution, colonization and succession on whale-bone, Douglas fir wood, and control carbonate rock over 8.3 mo. Experimental substrates were similar in size and mounted on PVC plates near the seafloor at 890 m depth and monitored by high-definition video camera for 5-min intervals every 6-12 h over a period of 8.3 mo. A broad range of seafloor and sea-surface environmental variables were also monitored at this site over the 8.3 mo to account for environmental variability and food input. Following loss of the high-definition camera, substrates were surveyed approximately annually with lower resolution ROV video for an additional 8.5 y. We find that megafaunal abundances, species diversity, and community structure varied substantially over 8.3 mo on each substrate, with markedly different patterns on whale bones due to the development of extensive white bacterial mats. A combination of seafloor and sea surface variables explained < 35% of bone/wood community variation. Bone-eating Osedax annelids failed to colonize whale bones even after 9.2 years, and boring Xylophaga bivalves colonized the wood at much lower rates than in better oxygenated deep-sea locations. Species diversity on whale-bone and wood substrates appeared to be substantially reduced due to the absence of ecosystem engineers and the low oxygen concentrations. We hypothesize that Osedax/Xylophaga colonization, bone/wood degradation, and bone/wood community development may be limited by oxygen concentrations of 0.22 - 0.33 ml.l on the NE Pacific margin, and that OMZ expansion due to climate change will reduce whale-bone and wood degradation, and the contribution of whale falls and wood falls to beta diversity, on the NE Pacific margin.

Control model of community elderly recreational exercise assistive robot based on improved dense trajectory algorithm

As the number of elderly population in the community grows, more efficient and precise recreation and exercise aids are needed to safeguard their quality of life. The study proposes a control model based on an improved dense trajectory algorithm to enhance the recognition and response capabilities of recreation and exercise assistance robots. The main method of the model is to improve the dense trajectory algorithm to enhance its recognition speed and accuracy for complex and small movements. Specifically, the study deeply refined the control process of a health and exercise assisted robot, and combined action capture to construct a health and exercise assisted robot model. The control model of the health and exercise assisted robot was optimized using an improved dense algorithm. The improved dense trajectory algorithm has feature embedding and attention mechanism, which can supplement the input data of the model, thus enabling more accurate action recognition. The results show that among the five samples, the recreation effectiveness score of the experimental group averaged 8.9, which was significantly higher than that of the control group, which was 7.3. The recognition accuracy has been improved by 2.7 % and 3.9 %, respectively, effectively suppressing the influence of camera motion. After using the improved dense trajectory algorithm, the fitness of the health training assistant robot reached 96.25 % under the same processing time, which is 8.93 % higher than the traditional model's fitness of 87.32 %. In summary, the control model of a community elderly health exercise assistance robot based on improved dense trajectory algorithm has achieved more accurate and faster recognition and response to the actions of the elderly, providing a more efficient technical means for health exercise and improving the health effect of the elderly.

Private Cctv Liability Under Biometric Data Protection Rules

The penetration of technology that is increasingly developing has a lot of impact on human life. Increasing technology also results in the rapid development of home security equipment, especially Closed-Circuit Television cameras (hereinafter mentioned as CCTV). The right to privacy, to which everyone is entitled to personal self- protection Doctrinal legal research is a crucial aspect in recognizing various societal problems. Doctrinal research combines a systematic analysis of the provisions of legislation and the legal principles contained in it or derived from it, but also the logical and rational order of legal propositions and principles. Doctrinal legal research methods involve the analysis of legal propositions or legal concepts on which the main study is based. Case base approach demands the researcher to understand the reasons that used by the judges or another adjudicator until it reaches the final decision. Most personal data protection laws around the world distinguish between regular personal data and biometric data. At the beginning, Article 4 paragraph (1) of EU GDPR regular personal data commonly define on the laws as a set of data that able to identify a natural person either from electronic or non-electronic devices. Under the data protection laws regime especially GDPR, UK Data Protection Law and Indonesia Data Protection Law, mitigation during a data protection failure involving household CCTV systems typically involves taking immediate steps to minimize the impact of the breach Furthermore, stated in the Fairhurst v Woodard case homeowner could be held liable for failure to protect the personal data if they use camera on the outside boundary of their house and they could face hefty fine and/or tools removal. Finally, this writing contributes to undergoing discourse on cyber law field especially in data protection law and provide insights for academician, practitioner, and society.

From lab to field with machine learning – Bridging the gap for movement analysis in real-world environments: A commentary

Biomechanical data collection was largely confined to controlled laboratory setups, relying on marker-based systems or force platforms. However, the emergence of wearable sensors and markerless motion capture has revolutionized this field, enabling data collection in real-world scenarios. This shift has also sparked interest in integrating machine learning (ML) into biomechanical workflows, promising to revolutionize data acquisition in field settings and refine data analysis (Halilaj et al., 2018). Figure 1 provides an overview of corresponding ML applications for key tasks in the biomechanical workflow. This commentary explores the transformative potential of ML in biomechanics, focusing on enhancing data collection and analysis in real-world environments. Pose estimation (a) is the process of automatically tracking and determining the body’s anatomical landmarks, body segments, or joint centre locations in video images using ML, enabling the quantification of human movement without marker and sensor attachments to the human body. Feature estimation (b) employs ML to predict complex biomechanical data, e.g. joint moments from more accessible data sources, including IMUs, pressure insoles, and RGB video cameras. Event detection (c) in time series data is the annotation of certain events that are used to extract useful and vital information or to remove unwanted and unnecessary data for further analysis. Clustering (d) involves grouping instances or individuals with similar biomechanical characteristics using unsupervised ML, thereby revealing underlying structures and subgroups within complex biomechanical data. Finally, automated classification (e) refers to the process of developing a predictive model that assigns input features of data samples to predefined categories or classes using supervised ML. Despite the advancements of ML in biomechanics, central challenges are faced. Estimation errors remain critically high depending on the task and application field, necessitating a careful reflection on data acquisition potentials. Furthermore, especially complex Deep Learning models, while showing promising performances, exhibit a lack of transparency in understanding their decision-making processes and the underlying patterns and rules learned from the data. This phenomenon, often termed as the black-box nature of these models, poses a considerable obstacle. In response, Explainable Artificial Intelligence (XAI), a field that encompasses different explainability approaches to shed light on the inner workings of complex, non-linear ML models, has gained increasing attention in recent years (Slijepcevic et al., 2023). A further central challenge is the availability of data and annotations, which describes the limited availability or insufficiency of relevant and comprehensive datasets, as well as task-specific annotations, for conducting thorough analyses and research in biomechanics. The lack of large-scale benchmark datasets available restricts the widespread adoption of ML-based approaches in biomechanics. Privacy concerns present significant ethical and legal issues, e.g. with identifiable video data. Additionally, model validation remains a critical problem, as many studies fail to validate their models on diverse datasets, often relying on limited data from a single laboratory. Furthermore, there is a risk that the fundamental mechanical understanding of biomechanical processes might be overshadowed by an over-reliance on ML techniques. In conclusion, the integration of ML into biomechanics presents a transformative opportunity for understanding human movement by enabling and improving data collection and analysis in real-world settings. Challenges in data accessibility and methodological transparency necessitate collaborative efforts for future advancements.

Capillary interaction of copper melt with dense and porous MAX phase (Cr, Mn)2AlC

In the present work, we experimentally studied the interaction of a pure copper melt with a dense MAX-phase (Cr, Mn)2AlC after sintering by the electric pulse plasma method and a porous phase obtained by pressing at room temperature. The porous phase (20 % porosity) absorbs molten copper at temperatures above 1200 °C; the kinetics of absorption was directly measured using high-speed thermal and video cameras. The experiments were carried out in a vacuum of 10–3 Pa. Studies using scanning electron microscopy, EDX spectral analysis and X-ray diffraction have shown that a chemical interaction of the MAX-phase with a copper melt occurs with the formation of a solution of aluminum and chromium in copper and the decomposition of the MAX-phase to chromium carbides (stable or metastable). The dense, sintered sample also actively interacts with the melt, although the contact angles exceed 100°. The difference between porous and dense samples lies in the kinetics of interaction. The results were compared with experiments on wetting the Cr2AlC MAX-phase with a Cu (0.8 at.% Cr) melt conducted earlier. The described experimental conditions and the results of determining chemical and phase changes in the process of capillary interaction indicate the possibility of creating a composite material with a submicron structure of chromium carbide impregnated with aluminum bronze.

Diferente aroma, mismo color floral: el caso de dos especies de <i>Salvia</i> de corola blanca

Background: Plants emit floral signals that are attractive to pollinators. Floral volatile organic compounds (VOCs) are considered a key signal in attracting pollinators. However, it has been scarcely explored whether flowers of the same color emit the same scent. Questions: Do different species of Salvia with white corolla flowers emit the same floral scent and attract the same floral visitors? Study species: Salvia assurgens and Salvia madrigalii, two species with white corolla but different floral morphology. Study site: Temperate forest southeast of Morelia, Michoacán. Methods: The floral scent was analyzed by gas/mass chromatography and floral visitor observations were carried out with video cameras. Results: The chemical profile of floral scent (composition and relative quantity) differed between S. assurgens and S. madrigalii. In S. madrigalii we found 16 VOCs and it was visited exclusively by the hummingbird Amazilia beryllina, and in S. assurgens we found 11 VOCs and it was visited by four species of insects, being the butterfly Thorybes dorantes the most frequent visitor. Canonical correspondence analysis (CCA) showed that floral volatiles were significantly correlated with the visitation rate of floral visitors. Conclusions: Our study shows evidence that Salvia species with white corolla flowers with different morphology emit different floral scents and attract particular floral visitors.

Ventilatory and Perceived Ergogenic Effects of Mandibular Forward Repositioning During Running at Maximal Oxygen Uptake Intensity.

Cardoso, F, Costa, MJ, Colaço, P, Vilas-Boas, JP, Pinho, JC, Pyne, DB, and Fernandes, RJ. Ventilatory and perceived ergogenic effects of mandibular forward repositioning during running at maximal oxygen uptake intensity. J Strength Cond Res XX(X): 000-000, 2024-Wearing an intraoral dental splint may enhance ventilatory function and exercise performance. Nineteen runners performed on a 400-m outdoor track: (a) an incremental protocol to assess the velocity at maximal oxygen uptake (vV̇ o2 max) and (b) 2 square wave bouts wearing 2 intraoral splints (with and without mandibular forward repositioning). The time until exhaustion at vV̇ o2 max (TLimv V̇ o2 max), ventilatory variables, oxygen uptake (V̇ o2 ) kinetics, energetic profiling, perceived exertion and kinematics, were all measured. Ventilatory data were assessed breath-by-breath and perceived exertion evaluated using the Borg 6-20-point scale at the end of TLimv V̇ o2 max bouts. Images were recorded by video cameras (120 Hz) and kinematic measures retrieved using Kinovea. A paired t test was computed for comparison of splints ( p ≤ 0.05). With (vs. without) mandibular forward repositioning, runners increased their TLimv V̇ o2 max by ∼6% ( p = 0.03), coupled with higher ventilation (151 ± 22 vs. 147 ± 23 L·min -1 , p = 0.04), end-tidal oxygen tension (114.3 ± 3.7 vs. 112.9 ± 3.9 mm Hg, p = 0.003), and lower inspiratory time (0.526 ± 0.083 vs. 0.540 ± 0.090 seconds, p = 0.02), despite similar V̇ o2 kinetics (e.g., 49.0 ± 8.7 vs. 47.7 ± 8.6 ml∙kg∙min -1 of fast component amplitude) being observed. The energy expenditure was ∼8% higher ( p = 0.03) with the mandible forward, coupled with lower perceived exertion scores ( p = 0.04). Mandibular forward repositioning was effective in acutely improving running performance at vV̇ o2 max with ergogenic effects on ventilatory and perceived variables.

Advances and Challenges in Pest Management for Protected Cultivation in India: Integrative Approaches and Future Prospects

Poly house farming in India has transformed agriculture by enabling year-round crop production and protecting crops from adverse weather. However, the controlled environment of poly houses represents unique challenges in pest management, making it crucial to implement effective strategies to maintain crop health and yield. Integrated Pest Management (IPM) offers a comprehensive approach that combines cultural, biological and chemical practices to control pests while minimizing environmental impact. The advantages of protected cultivation include increased productivity, improved produce quality and efficient resource utilization. Despite these benefits, poly house farming faces limitations such as high initial costs, the need for meticulous planning and ongoing crop protection requirements. Pest identification is vital for effective management, as misidentification can lead to inappropriate control measures. Common pests in poly houses include insects, slugs, mites, nematodes, pathogens and weeds. Pest monitoring strategies such as scouting, using monitoring tools and record-keeping are essential for timely and effective management interventions. Management strategies encompass physical, biological and chemical methods. Physical approaches include the use of sticky and pheromone traps, while biological control involves the release of natural predators and entomopathogens. Chemical management involves both biorational pesticides and conventional chemicals, with IPM emphasizing the integration of these methods to reduce reliance on harmful chemicals. Preventive measures like insect-proof screens and soil solarization, along with curative measures and advanced technologies like video camera networks and decision support systems, are pivotal for effective pest control. Future prospects include improving technology standards, enhancing computerized control systems, and fostering research and government support to advance protected cultivation in India.

RGB-D visual odometry by constructing and matching features at superpixel level

Abstract Visual odometry (VO) is a key technology for estimating camera motion from captured images. In this paper, we propose a novel RGB-D visual odometry by constructing and matching features at the superpixel level that represents better adaptability in different environments than state-of-the-art solutions. Superpixels are content-sensitive and perform well in information aggregation. They could thus characterize the complexity of the environment. Firstly, we designed the superpixel-based feature SegPatch and its corresponding 3D representation MapPatch. By using the neighboring information, SegPatch robustly represents its distinctiveness in various environments with different texture densities. Due to the inclusion of depth measurement, the MapPatch constructs the scene structurally. Then, the distance between SegPatches is defined to characterize the regional similarity. We use the graph search method in scale space for searching and matching. As a result, the accuracy and efficiency of matching process are improved. Additionally, we minimize the reprojection error between the matched SegPatches and estimate camera poses through all these correspondences. Our proposed VO is evaluated on the TUM dataset both quantitatively and qualitatively, showing good balance to adapt to the environment under different realistic conditions.

Enhanced 2D Hand Pose Estimation for Gloved Medical Applications: A Preliminary Model.

(1) Background: As digital health technology evolves, the role of accurate medical-gloved hand tracking is becoming more important for the assessment and training of practitioners to reduce procedural errors in clinical settings. (2) Method: This study utilized computer vision for hand pose estimation to model skeletal hand movements during in situ aseptic drug compounding procedures. High-definition video cameras recorded hand movements while practitioners wore medical gloves of different colors. Hand poses were manually annotated, and machine learning models were developed and trained using the DeepLabCut interface via an 80/20 training/testing split. (3) Results: The developed model achieved an average root mean square error (RMSE) of 5.89 pixels across the training data set and 10.06 pixels across the test set. When excluding keypoints with a confidence value below 60%, the test set RMSE improved to 7.48 pixels, reflecting high accuracy in hand pose tracking. (4) Conclusions: The developed hand pose estimation model effectively tracks hand movements across both controlled and in situ drug compounding contexts, offering a first-of-its-kind medical glove hand tracking method. This model holds potential for enhancing clinical training and ensuring procedural safety, particularly in tasks requiring high precision such as drug compounding.

Feasibility and usefulness of video-based markerless two-dimensional automated gait analysis, in providing objective quantification of gait and complementing the evaluation of gait in children with cerebral palsy

BackgroundGait analysis aids in evaluation, classification, and follow-up of gait pattern over time in children with cerebral palsy (CP). The analysis of sagittal plane joint kinematics is of special interest to assess flexed knee gait and ankle joint deviations that commonly progress with age and indicate deterioration of gait. Although most children with CP are ambulatory, no objective quantification of gait is currently included in any of the known international follow-up programs. Is video-based 2-dimensional markerless (2D ML) gait analysis with automated processing a feasible and useful tool to quantify deviations, evaluate and classify gait, in children with CP?MethodsTwenty children with bilateral CP with Gross Motor Function Classification Scale (GMFCS) levels I–III, from five regions in Sweden, were included from the national CP registry. A single RGB-Depth video camera, sensitive to depth and contrast, was positioned laterally to a green walkway and background, with four light sources. A previously validated markerless method was employed to estimate sagittal plane hip, knee, ankle kinematics, foot orientation and spatio-temporal parameters including gait speed and step length.ResultsMean age was 10.4 (range 6.8–16.1) years. Eight children were classified as GMFCS level I, eight as II and four as III. Setup of the measurement system took 15 min, acquisition 5–15 min and processing 50 min per child. Using the 2D ML method kinematic deviations from normal could be determined and used to implement the classification of gait pattern, proposed by Rodda et al. 2001.Conclusion2D ML assessment is feasible, since it is accessible, easy to perform and well tolerated by the children. The 2D ML adds consistency and quantifies objectively important gait variables. It is both relevant and reasonable to include 2D ML gait assessment in the evaluation of children with CP.

PSII-7 Development and assessment of a mobility scoring system for beef cattle

Abstract Lameness is a disruption of normal gait due to infection, injury, or abnormal conformation, causing pain and discomfort. Several scoring systems have been developed to determine lameness severity; a key indicator in deciding if an animal is fit to withstand transport. However, most scoring systems were developed for dairy cattle and may not be suited for use in feedlot cattle due to the large genetic variation between beef breeds as well as the highly variable environment in which they are housed. Lack of consistency when scoring lameness and reduced ability to detect early lame cattle can result in poor animal welfare and increased costs. The objectives of this study were 1) to develop a mobility scoring system that aids in transport decisions for beef cattle, and 2) to determine observer repeatability using this scoring system. Over a 7-mo period, video cameras were placed in an alley to record the ambulation of individual cattle exiting the processing barn at 4 commercial feedlots in Southern Alberta. Cameras were set to record whole-body videos of cattle walking, running, or trotting. Five researchers trained to use this mobility scoring system, individually evaluated 174 cattle from the collected videos, for fitness for transport and the presence/absence of gait abnormalities: shortness of stride, stiffness (mild, moderate, or severe), limp (mild, moderate, or severe), hip hike, head dropped, head bob, arched back, non-weight bearing, or reluctance to move. The mobility scoring system used was a modified (NCBA and Zinpro) 4-point scale (0-3) for locomotion: 0) an animal with no gait abnormalities; 1) an animal with mild stiffness and shortness of stride; 2) an animal with difficulty taking some steps and one or more of the following: severe stiffness, limp favoring affected limb, limps with a head bob when walking but still bears weight; and 3) an animal reluctant or unable to move, bearing little or no weight on affected limb, the head of the animal is dropped and back arched with pronounced head bob and severe limp detected, or incoordination. Fitness for transport was scored as fit, compromised, or unfit according to the humane transportation guidelines of the Canadian Food Inspection Agency. A kappa statistic was calculated to assess inter-observer reliability for both mobility and transport fitness scoring systems as well as gait abnormalities. The combined mobility scores had substantial agreement between observers (Κ = 0.63; P < 0.001). Mobility score of 2 had the highest agreement among all variables (Κ = 0.88; P < 0.001), followed by head bob (Κ = 0.85; P < 0.001), and arched back (Κ = 0.76; P < 0.001). Results of this study will aid in the development of a mobility score that improves industry stakeholder agreement regarding lameness severity and transport loading decisions.

416 Implementation of virtual fencing in heifers for mountain summer grazing

Abstract A virtual fencing (VF) system is based on a smartphone application that defines an invisible grazing boundary based on global positioning. Animals are tracked via GPS collars. When reaching the virtual boundary, the collar emits an ascending audio tone, followed by a mild electric pulse (0.2 Joule) when crossing it. The technology is particularly promising in rough and extensive mountainous areas where physical fencing is difficult and more time-consuming. Environmental conditions may also affect the functionality of the VF system, with potential impacts on animal behavior. Therefore, the present study tested a VF system on 30 female heifers in a rotational grazing system on Swiss mountain pastures (approximately 1,300 to 1,500 m above sea level). Each heifer was equipped with a VF collar (Nofence AS, Batnfjordsør, Norway) for individual recording of audio tones and electric pulses. After two wk of VF training in the lowlands (approximately 700 m above sea level), during which the heifers learned to interpret the VF signals correctly, they were transported to the mountain pasture. For mountain grazing, the herd was divided into three groups of 10 heifers each, balanced for age (mean ± SD: 11.9 ± 1.6 mo) and breed (Holstein-Friesian, Montbeliarde, crossbreeds). The outer perimeter of the mountain pasture was surrounded by an electric fence. Its inner area was divided into 3 electrically fenced and 6 virtually fenced paddocks. For 83 d, all groups grazed simultaneously in separate paddocks and rotated sequentially through the 9 paddocks. Video cameras were placed along the virtual fences to record animal responses after receiving audio tones or electric pulses. Moreover, grass height was measured using a rising plate meter to estimate forage availability in the currently grazed paddocks. Throughout mountain grazing, each heifer received an average of 4.9 ± 6.9 audio tones and 0.3 ± 0.7 electric pulses per day. Generalized mixed-effects models revealed that the number of audio tones and electric pulses did not change over grazing periods or among days after paddock change. Behavioral responses of the animals were less pronounced once the heifers had learned the VF system. In addition, grazing interruptions after receiving an audio tone or electric pulse were shorter during mountain grazing compared with the training period (P < 0.001). Furthermore, lower grass heights (P < 0.05) as well as the occurrence of (common but) unpredictable events (P < 0.001), such as the presence of wildlife (e.g., lynx, deer) or neighboring cattle, increased the number of audio tones and electric pulses during mountain grazing. The VF system was still effective in keeping the heifers within their assigned paddocks under mountainous conditions. However, a well-considered handling when changing paddocks as well as a careful placement of the virtual fence is essential to avoid negative effects on the animals.

Effects of the number of ball touches among elite youth players during small-sided soccer games.

This study investigates the effects of manipulating the number of ball touches (free play vs. two touches) on the physical and technical actions of elite male youth soccer players during 5v5 + 2 goalkeepers (GKs) small-sided games (SSGs). Players played in two different SSGs: 1) free play, where the number of touches per possession was not restricted; and 2) two touches, where players were limited to a maximum of two touches per ball possession. A total of 24 male elite youth soccer players (age: 14.79±0.71 years; body mass: 56.02±1.41 kg; body height: 164±2.12 cm) participated in the study. Players' physical metric and technical performance data were captured using a global positioning system and video camera, respectively. A paired-samples t-test or Wilcoxon Signed-Rank Test was employed to examine differences in players' technical performance variables depending on SSGs' ball-touch rules. The results show significantly more unsuccessful passes (t=-3.48; P=0.04; d=1.92) when players were limited to two touches than when there were no pass limits. The physical metrics indicate that total distance covered (Z=-2.90; P=0.001; d=0.07), meters per minute (Z=-3.44; P=0.001; d=0.11), low-speed running (Z=-2.25; P=0.02; d=0.04) and high acceleration (Z=-1.90; P=0.05; d=0.28) were significantly higher when touches were unlimited than when they were not. Soccer coaches should decide the number of touches per ball possession they allow depending on their tactical and/or physical objectives in training.

In vivo video microscopy of the rupturing process of thin blood vessels to clarify the mechanism of bruising caused by blunt impact: an animal study

BackgroundThe thresholds of mechanical inputs for bruising caused by blunt impact are important in the fields of machine safety and forensics. However, reliable data on these thresholds remain inadequate owing to a lack of in vivo experiments, which are crucial for investigating the occurrence of bruising. Since experiments involving live human participants are limited owing to ethical concerns, finite-element method (FEM) simulations of the bruising mechanism should be used to compensate for the lack of experimental data by estimating the thresholds under various conditions, which requires clarifying the mechanism of formation of actual bruises. Therefore, this study aimed to visualize the mechanism underlying the formation of bruises caused by blunt impact to enable FEM simulations to estimate the thresholds of mechanical inputs for bruising.MethodsIn vivo microscopy of a transparent glass catfish subjected to blunt contact with an indenter was performed. The fish were anesthetized by immersing them in buffered MS-222 (75–100 mg/L) and then fixed on a subject tray. The indenter, made of transparent acrylic and having a rectangular contact area with dimensions of 1.0 mm × 1.5 mm, was loaded onto the lateral side of the caudal region of the fish. Blood vessels and surrounding tissues were examined through the transparent indenter using a microscope equipped with a video camera. The contact force was measured using a force-sensing table.ResultsOne of the processes of rupturing thin blood vessels, which are an essential component of the bruising mechanism, was observed and recorded as a movie. The soft tissue surrounding the thin blood vessel extended in a plane perpendicular to the compressive contact force. Subsequently, the thin blood vessel was pulled into a straight configuration. Next, it was stretched in the axial direction and finally ruptured.ConclusionThe results obtained indicate that the extension of the surrounding tissue in the direction perpendicular to the contact force as well as the extension of the thin blood vessels are important factors in the bruising mechanism, which must be reproduced by FEM simulation to estimate the thresholds.

The relationship between executed cut angle and speed with lower extremity joint angles during unanticipated side-step cutting in soccer players

BackgroundCertain movements patterns have been indicated in knee injuries during cutting while running tasks. Differences in the executed cut angle (ECA) could partially account for group differences in joint kinematics previously observed, including sex differences. Research QuestionAre there relationships between joint angles with entry speed and ECA during side-step cutting in soccer players? MethodsThis cross-sectional study recruited 21 (10 females) soccer players. Participants completed 45o unanticipated side-step cuts in both directions. Kinematic data were captured with a 12 camera motion capture system with 46 reflective markers placed on the participants. Peak joint angles were determined during the stance phase of the cutting task. Entry speed and ECA were determined from pelvis markers. Hierarchical linear models examined relationships between angles, entry speed, and ECA, after accounting for age, sex, and leg preference. Regression coefficients with 95% confidence intervals were reported and statistical significance (p<0.05) were examined using the Wald statistic. ResultsThe mean ECA (24.6o) was lower than the intended 45o angle. Peak joint angles were significantly related to both ECA and entry speed. Specifically, an increase in ECA by 10o (i.e., sharper cuts) would increase hip internal rotation and ankle plantarflexion by 1.8 to 2.1o, and decrease hip adduction, knee abduction and ankle eversion by 1.3 to 2.4o. Faster entry speeds by 0.5m/s would increase hip flexion, hip internal rotation and knee extension angles by 1.8 to 3.8o, and decrease knee abduction by 2.6o. SignificanceStudies evaluating cutting while running should consider ECA and entry speed in their design. Potential differences could confound between-group comparisons of joint angles, including when comparing sexes, and impact interpretations of injury risk.

Computer vision and statistical insights into cycling near miss dynamics

Across the globe, many transport bodies are advocating for increased cycling due to its health and environmental benefits. Yet, the real and perceived dangers of urban cycling remain obstacles. While serious injuries and fatalities in cycling are infrequent, “near misses”-events where a person on a bike is forced to avoid a potential crash or is unsettled by a close vehicle-are more prevalent. To understand these occurrences, researchers have turned to naturalistic studies, attaching various sensors like video cameras to bikes or cyclists. This sensor data holds the potential to unravel the risks cyclists face. Still, the sheer amount of video data often demands manual processing, limiting the scope of such studies. In this paper, we unveil a cutting-edge computer vision framework tailored for automated near-miss video analysis and for detecting various associated risk factors. Additionally, the framework can understand the statistical significance of various risk factors, providing a comprehensive understanding of the issues faced by cyclists. We shed light on the pronounced effects of factors like glare, vehicle and pedestrian presence, examining their roles in near misses through Granger causality with varied time lags. This framework enables the automated detection of multiple factors and understanding their significant weight, thus enhancing the efficiency and scope of naturalistic cycling studies. As future work, this research opens the possibility of integrating this AI framework into edge sensors through embedded AI, enabling real-time analysis.