Video Analysis Research Articles

Relationship Between Multi-Teaching Styles and Didactics Effectiveness on Rugby Instructors and Minirugby Players

Background/Objectives: The concept of educational systems thinking shows the rugby educational system as a network of multiple interactive and interconnected elements. However, the frameworks presented in the literature for developing sports practice through an educational vision and multisport engagement do not always have direct transferability to instructors’ training courses. The study aims to evaluate the correlation between rugby instructors’ methodological and didactical competencies and compare them with children’s motor competence and psychological aspects. Methods: Two hundred twenty children (9.6 ± 1.1 years) and 50 instructors (39.0 ± 13.6 years) were enrolled. Instructors’ competencies were investigated during the internship through evaluation sheets, questionnaires, and video analysis. Children’s motor competence and psychological aspects were investigated through motor tests, questionnaires, and video analysis. Results: The correlation between methodological competencies and didactical-communicative competencies showed a positive significance, especially regarding production styles. Motor competence and play skills in children showed poor results. The group of instructors with more methodological competencies (a greater number of teaching styles used) showed a strong correlation between motor competence and psychological aspects. Conclusions: For successful teaching, knowledge of specific technical skills is not enough, and it is important to consider all the factors (in particular, the teaching-communicative and methodological skills) that contribute most to instructors’ skills.

Artificial Intelligence Assisted Surgical Scene Recognition: A Comparative Study Amongst Healthcare Professionals.

This study aimed to compare the ability of a deep-learning platform (the MACSSwin-T model) with healthcare professionals in detecting cerebral aneurysms from operative videos. Secondly, we aimed to compare the neurosurgical team's ability to detect cerebral aneurysms with and without AI-assistance. Modern microscopic surgery enables the capture of operative video data on an unforeseen scale. Advances in computer vision, a branch of artificial intelligence (AI), have enabled automated analysis of operative video. These advances are likely to benefit clinicians, healthcare systems, and patients alike, yet such benefits are yet to be realised. In a cross-sectional comparative study, neurosurgeons, anaesthetists, and operating room (OR) nurses, all at varying stages of training and experience, reviewed still frames of aneurysm clipping operations and labelled frames as "aneurysm not in frame" or "aneurysm in frame". Frames then underwent analysis by the AI platform. A second round of data collection was performed whereby the neurosurgical team had AI-assistance. Accuracy of aneurysm detection was calculated for human only, AI only, and AI-assisted human groups. 5,154 individual frame reviews were collated from 338 healthcare professionals. Healthcare professionals correctly labelled 70% of frames without AI assistance, compared to 78% with AI-assistance (OR 1.77, P<0.001). Neurosurgical Attendings showed the greatest improvement, from 77% to 92% correct predictions with AI-assistance (OR 4.24, P=0.003). AI-assisted human performance surpassed both human and AI alone. Notably, across healthcare professionals surveyed, frame accuracy improved across all subspecialties and experience levels, particularly among the most experienced healthcare professionals. These results challenge the prevailing notion that AI primarily benefits junior clinicians, highlighting its crucial role throughout the surgical hierarchy as an essential component of modern surgical practice.

Technical and Morphometric Comparisons Between Vertical and Horizontal Functional Hemispherotomies-A Juxtaposed 2D Video Analysis: 2-Dimensional Operative Video.

Technical and Morphometric Comparisons Between Vertical and Horizontal Functional Hemispherotomies-A Juxtaposed 2D Video Analysis: 2-Dimensional Operative Video.

Guiding the Pious Self: Morality and Affect in Muslim Instructional YouTube Videos

Abstract Based on a discourse analysis of German-language YouTube videos that attempt to instruct their audiences in Islamic practice, the article examines the interplay of moral statements and audiovisual elements in religious web videos. YouTube constitutes an affective space for the promotion of normative Islamic models of gendered subjectivity that instruct how to understand and guide oneself. Considering the tensions in the lives of young Muslims in the German context, the videos offer clear notions of gendered Muslim morality within an arrangement of discursive and affective elements that draw on both Islamic oratory and elements of secular popular culture. On a linguistic level, producers address their audiences as immoral subjects alienated from a divine order and call for a self-transformation towards piety. At the audiovisual level, discursive statements are entangled with a fluctuating stream of affective intensities that have the potential to charge moral codes with aesthetic legitimacy and attach viewers to gender norms.

The Role of Instagram Videos on the Growth of Female-Owned Businesses in Lagos

Although videos are a compelling form of content on Instagram, women entrepreneurs on Instagram exist within a highly competitive space, and they need to seek out approaches that will give them a competitive edge while creating content for promoting their businesses. The study aimed to explore how Instagram videos can engage potential consumers, promote products, and increase brand awareness. Twenty-three women entrepreneurs were chosen using a snowball sampling technique and were then interviewed in detail, using a qualitative approach. The study showed that Instagram videos and other marketing campaigns influence the growth of women-owned businesses. The key metrics that indicated growth were engagement rates, direct communication channels, lead generation and conversion rates, website traffic, testimonials, and follower growth and retention. These metrics helped women entrepreneurs assess and improve their marketing strategies, identify areas that need improvement, and make decisions to maintain and improve company success. The study recommends that future research should combine both qualitative and quantitative research designs to provide statistical validation for the study's findings as well as content analysis of Instagram videos used by women-owned businesses on Instagram.

Real-Time Smoke Detection in Surveillance Videos Using an Enhanced RT-DETR Framework with Triplet Attention and HS-FPN

This study addresses the urgent need for an efficient and accurate smoke detection system to enhance safety measures in fire monitoring, industrial safety, and urban surveillance. Given the complexity of detecting smoke in diverse environments and under real-time constraints, our research aims to solve challenges related to low-resolution imagery, limited computational resources, and environmental variability. This study introduces a novel smoke detection system that utilizes the real-time detection Transformer (RT-DETR) architecture to enhance the speed and precision of video analysis. Our system integrates advanced modules, including triplet attention, ADown, and a high-level screening-feature fusion pyramid network (HS-FPN), to address challenges related to low-resolution imagery, real-time processing constraints, and environmental variability. The triplet attention mechanism is essential for detecting subtle smoke features, often overlooked due to their nuanced nature. The ADown module significantly reduces computational complexity, enabling real-time operation on devices with limited resources. Furthermore, the HS-FPN enhances the system’s robustness by amalgamating multi-scale features for reliable detection across various smoke types and sizes. Evaluation using a diverse dataset showcased notable improvements in average precision (AP50) and frames per second (FPS) metrics compared to existing state-of-the-art networks. Ablation studies validated the contributions of each component in achieving an optimal balance between accuracy and operational efficiency. The RT-DETR-based smoke detection system not only meets real-time requirements for applications like fire monitoring, industrial safety, and urban surveillance but also establishes a new performance benchmark in this field.

Current application of artificial intelligence in laparoscopic cholecystectomy

Recent advances in artificial intelligence (AI) have sparked a surge in the application of computer vision (CV) in surgical video analysis. Surgical complications often occur due to lapses in judgment and decision-making. In laparoscopic cholecystectomy, achievement of the critical view of safety is commonly advocated to prevent bile duct injuries. However, bile duct injuries rates remain stable, probably due to inconsistent application or a poor understanding of critical view of safety. Advances in AI have made it possible to train algorithms that identify anatomy and interpret the surgical field. AI-based CV techniques may leverage surgical video data to develop real-time automated decision support tools and surgeon training systems. The effectiveness of CV application in surgical procedures is still under early evaluation. The review considers the commonly used deep learning algorithms in CV and describes their usage in detail in four application scenes, including phase recognition, anatomy detection, instrument detection and action recognition in laparoscopic cholecystectomy. The MedLine, Scopus, and IEEE Xplore databases were searched for publications up to 2024. The keywords used in the search were “laparoscopic cholecystectomy”, “artificial intelligence”. The currently described applications of CV in laparoscopic cholecystectomy are limited. Most current research focus on the identification of workflow and anatomical structure, while the identification of instruments and surgical actions is still awaiting further breakthroughs. Future research on the use of CV in laparoscopic cholecystectomy should focus on application in more scenarios, such as surgeon skill assessment and the development of more efficient models.

Wearable smart glasses for first‐person video analysis to evaluate nursing skills: A pilot study with a mixed method design

AbstractBackgroundComprehensive assessment of skills and performance are necessary to improve the quality of care in nursing education. Various factors pose challenges to accurate assessments, including high student–teacher ratio and observer bias.ObjectivesTo establish an assessment system based on first‐person video of smart glasses and validate its usability and feasibility.MethodsWe used two cameras (smart glasses for first‐person perspective and a web cam) to perform video analysis for skill and performance assessments. Usability tests were conducted using quantitative and qualitative questionnaires for the usefulness and acceptability of the current assessment system. Data from standardised checklists for three clinical nursing skills (intramuscular injection, endotracheal suction, and Levin tube feeding) were used to analyse the inter‐rater reliability in addition to Fleiss' Kappa coefficient analysis. A total of 22 participants (18 students and 4 reviewers) were recruited. They completed the study. Apart from physical discomfort component, the proposed smart glasses‐based first‐person video assessment system achieved good usability scores from both students and reviewers.Results and ConclusionsFleiss' Kappa values for individual items ranged from 0.450 to 0.808, with an overall average value of 0.592. Results of this study validated the potential of smart glasses‐based assessment system where a set of beneficial mechanisms may meaningfully support the formative learning process. However, issues regarding upgrading the device and need for guidelines for roles of raters and students still remain.

A Staged Framework for Computer Vision Education: Integrating AI, Data Science, and Computational Thinking

Computer vision education is increasingly important in modern technology curricula; yet, it often lacks a systematic approach integrating both theoretical concepts and practical applications. This study proposes a staged framework for computer vision education designed to progressively build learners’ competencies across four levels. This study proposes a four-staged framework for computer vision education, progressively introducing concepts from basic image recognition to advanced video analysis. Validity assessments were conducted twice with 25 experts in the field of AI education and curricula. The results indicated high validity of the staged framework. Additionally, a pilot program, applying computer vision to acid–base titration activities, was implemented with 40 upper secondary school students to evaluate the effectiveness of the staged framework. The pilot program showed significant improvements in students’ understanding and interest in both computer vision and scientific inquiry. This research contributes to the AI educational field by offering a structured, adaptable approach to computer vision education, integrating AI, data science, and computational thinking. It provides educators with a structured guide for implementing progressive, hands-on learning experiences in computer vision, while also highlighting areas for future research and improvement in educational methodologies.

Foot Kinematics of Elite Female 59 kg Weightlifters in the 2018–2021 World Championships

Background/Objectives: Research on elite weightlifting performance is crucial for understanding the underlying attributes of efficient techniques. This study aimed to analyze the foot characteristics of elite female weightlifters in the 59 kg category during the snatch. Methods: Publicly available videos from the International Weightlifting Federation World Weightlifting Championships (2018–2021) were analyzed. Excluding the 2020 competition due to the COVID-19 pandemic and more unsuccessful attempts, a total of 20 videos were selected for kinematic analysis using Kenova video analysis software. Variables included the horizontal foot distance in the start and catch phases, horizontal displacement of sideway leg separation, and maximum vertical heel height of each foot. Results: The results revealed small to moderate significant negative correlations between snatch performance and maximum heel height (right: r = −0.28, p &lt; 0.05; left: r = −0.332 p &lt; 0.01). Snatch performance also demonstrated a small to moderate negative correlation with sideway leg separation and foot distance in the catch phase (r = −0.275, p &lt; 0.01; r = −0.467, p &lt; 0.01, respectively). Maximum heel height exhibited a very strong positive correlation between feet (r = 0.853, p &lt; 0.01). Conclusions: A relatively narrower stance was found to be more beneficial for elite weightlifter performance. Strong coordination suggests advanced movement strategies in this complex lift. These findings contribute to the existing knowledge on weightlifting techniques and offer valuable insights for athletes and coaches seeking to improve performance in competitive environments.

CoFFEE: a codec-based forensic feature extraction and evaluation software for H.264 videos

The forensic analysis of digital videos is becoming increasingly relevant to deal with forensic cases, propaganda, and fake news. The research community has developed numerous forensic tools to address various challenges, such as integrity verification, manipulation detection, and source characterization. Each tool exploits characteristic traces to reconstruct the video life-cycle. Among these traces, a significant source of information is provided by the specific way in which the video has been encoded. While several tools are available to analyze codec-related information for images, a similar approach has been overlooked for videos, since video codecs are extremely complex and involve the analysis of a huge amount of data. In this paper, we present a new tool designed for extracting and parsing a plethora of video compression information from H.264 encoded files, including macroblocks structure, prediction residuals, and motion vectors. We demonstrate how the extracted features can be effectively exploited to address various forensic tasks, such as social network identification, source characterization, and double compression detection. We provide a detailed description of the developed software, which is released free of charge to enable its use by the research community to create new tools for forensic analysis of video files.

An Assessment of an Inpatient Robotic Nurse Assistant: A Mixed-Method Study

The worldwide nursing shortage has led to the exploration of using robotics to support care delivery and reduce nurses’ workload. In this observational, mixed-method study, we examined the implementation of a robotic nurse assistant (RNA) in a hospital ward to support vital signs measurements, medication, and item delivery. Human–robot interaction was assessed in four domains: usability, social acceptance, user experience, and its societal impact. Patients in a general medicine ward were recruited to participate in a one-time trial with the RNA and a post-trial 75-question survey. Patients’ interactions with the RNA were video recorded for analysis including patients’ behaviours, facial emotions, and visual attention. Focus group discussions with nurses elicited their perceptions of working with the RNA, areas for improvement, and scalability. Sixty-seven patients aged 21–79 participated in the trial. Eight in 10 patients reported positive interactions with the RNA. When the RNA did not perform to expectations, only 25% of patients attributed fault to the RNA. Video analysis showed patients at ease interacting with the RNA despite some technical problems. Nurses saw potential for the RNA taking over routine tasks. However, they were sceptical of real time savings and were concerned with the RNA’s ability to work well with older patients. Patients and nurses suggested greater interactivity between RNA and patients. Future studies should examine potential timesaving and whether time saved translated to nurses performing higher value clinical tasks. The utility of improved RNA’s social capability in a hospital setting should be explored as well.

Using Eye-Tracking to Evaluate Novel Augmented Reality Applications for Maritime Operations

This paper presents the developments across a multi-year collaborative industry-academia R&amp;D project designing and testing novel Augmented Reality (AR) solutions for differing maritime operations and work tasks. We describe the step-wise approach taken in our Human Factors testing program exploring the effects of AR on maritime operators. This paper focuses specifically on our empirical simulator laboratory experiments using differing data collection designs, tools and operational scenarios to investigate operator Situation Awareness, cognitive workload, performance and usability. Moving from comparatively rudimentary measures using static scenarios, desktop data collections and post hoc video analysis to implementing eye-tracking and automated object identification in dynamic scenarios and full-mission simulated environments, we present an overview of how our testing program has evolved and lessons learned. Further, we discuss ongoing research and future plans to better understand the effects of AR on maritime end-users to implement human-centred solutions more effectively in maritime settings.

Safety Insights from E-Scooter Rider and Bicyclist Behavior Observations in Two U.S. Cities

E-scooters, a novel micromobility mode, have transformed U.S. transportation in urban cores, offering potential advantages like cost-effective mobility, congestion reduction, community accessibility, and lower emissions. However, owing to their novelty, their associated safety impacts and rider behaviors remain uncertain, complicating policy formulation. Specifically, e-scooter policy often mirrors bicycle policy, yet there have been few studies that have explicitly investigated how e-scooter and bicycle rider behaviors compare. This research investigated rider behavior relative to infrastructure by examining riding patterns through a video-based platform on 26 Nashville and Portland streets, offering insights on e-scooter and bicyclist behaviors, including riding location and helmet use. This study differs from other observational studies since it covers longer observation periods than prior in-person studies, including nighttime riding behavior. The video analysis also allows for observations of basic demographic characteristics. The findings revealed that bike lanes were well-used and dramatically reduced sidewalk riding and general travel lane usage. Without bike lanes, riders typically resorted to using sidewalks on high-capacity roads and sharing lanes with vehicles on low-capacity streets. The data also suggested demographic trends, such as riskier behavior among younger, male riders, and low helmet usage among e-scooter riders. The results emphasize the need for micromobility-supportive infrastructure in road design to encourage safer riding practices.

Players in the Women's National Basketball Association Are More Likely to Tear Their Anterior Cruciate Ligament if They Are a Guard, Forward, or Driving to the Basket: A Case-Control Study.

The Women's National Basketball Association (WNBA) has grown in popularity since its induction in 1996. Furthermore, it is well known that female athletes are at an increased risk of anterior cruciate ligament (ACL) tears compared with their male counterparts. The purpose was to examine the player positions and player movements during basketball games and practices that contribute to ACL tears in WNBA players. Player position and demographics from WNBA players who suffered an ACL tear from 1996 to 2021 were collected from publicly available sources. Entertainment and Sports Programming Network (ESPN) news reports and video analysis were reviewed to determine what movements each player was performing when the injury occurred. Injured players were matched with two noninjured players by age, position, height, and league experience. Performance statistics were collected one season prior to injury and compared with the matched controls. A total of 62 WNBA players with ACL injuries were identified with an average age of 26.7 (±3.9) years. More guards and forward were seen in the injured cohort and more players were injured while driving to the basket (p < 0.05). ACL injuries occurred more commonly during games than in practice (p < 0.05). Compared with controlled match cohort, the players who suffered ACL tears started more games (p = 0.007), had higher minutes played per game (p = 0.003), more field goals per game (p = 0.04), more field goal attempts per game (p = 0.03), more 3-point attempts per game (p = 0.04), more rebounds per game (p = 0.04), more steals per game (p = 0.02), and more points per game (p = 0.02). WNBA guards and forward were more likely to tear their ACL, especially while driving to the basket during real game play. Additionally, players with higher playing times, rebounds, and steals per game had higher rates of ACL tears. However, there was no impact on their performance on season statistics after returning to sport. LEVEL OF EVIDENCE: III.

Innovative methods of teaching the discipline "Gymnastics with teaching methods"

Gymnastics as a discipline in a modern higher education institution plays an important role in the physical and comprehensive development of students. It covers not only physical exercises, but also has pedagogical, social and educational value. Gymnastics contributes to the education of students in a conscious attitude to their health, physical activity and a healthy lifestyle. It also forms habits of regular physical exercises, which is an important factor in the prevention of various diseases. Innovative technologies can be introduced into the process of teaching gymnastics to improve the quality of teaching. This includes the use of video analysis, digital tools for monitoring physical fitness, and special programs for correcting exercise technique. Different forms of gymnastics can be taught at universities: sports, artistic, recreational, acrobatic. This gives students the opportunity to choose a direction according to their interests and level of training. Thus, gymnastics in a modern higher education institution is an integral part of the physical, professional and personal development of students, helping them not only to strengthen their health, but also to acquire important skills for later life.

Tackle characteristics associated with suspected concussion in female varsity rugby union: a case-control video analysis study

ABSTRACT The tackle is the most frequent and injurious event in rugby union. Tackle-related risk factors for concussion are identified in elite men, but may differ for women. The objective of this study was to evaluate the association between tackle characteristics and suspected concussion-related vs. non-injurious tackle events in Canadian female varsity rugby. Nacsport software was used to code 325 tackle events (46 suspected-concussion, 279 non-concussion). A penalised logistic regression with cluster-robust standard errors was used to estimate odds ratios (OR) [95% confidence intervals (95% CI)]. Ball-carrier concussion was associated with a head contact intensity of 2/4 (OR 6.5, 95% CI 1.3–31.6) and 3–4/4 (OR 48.5, 95% CI 12.1–193.7), illegal tackle (OR = 13.4, 95% CI 2.9–61.0), tap tackle (OR = 6.2, 95% CI 2.0–19.7), and down pre-contact head position (OR = 4.0, 95% CI 1.1–14.8). Tackler concussion was associated with 3 tacklers in the event (OR = 7.0, 95% CI 1.4–36.1), tap tackle (OR = 15.0, 95% CI 1.6–138.3), head contact intensity of 3–4/4 (OR = 30.6, 95% CI 5.6–168.1), and away pre-contact head position (OR = 3.0, 95% CI 1.1–7.8). Interventions aiming to reduce head impacts are needed in female rugby. Future directions should evaluate sex-related tackle characteristic differences.

TCEDN: A Lightweight Time-Context Enhanced Depression Detection Network.

The automatic video recognition of depression is becoming increasingly important in clinical applications. However, traditional depression recognition models still face challenges in practical applications, such as high computational costs, the poor application effectiveness of facial movement features, and spatial feature degradation due to model stitching. To overcome these challenges, this work proposes a lightweight Time-Context Enhanced Depression Detection Network (TCEDN). We first use attention-weighted blocks to aggregate and enhance video frame-level features, easing the model's computational workload. Next, by integrating the temporal and spatial changes of video raw features and facial movement features in a self-learning weight manner, we enhance the precision of depression detection. Finally, a fusion network of 3-Dimensional Convolutional Neural Network (3D-CNN) and Convolutional Long Short-Term Memory Network (ConvLSTM) is constructed to minimize spatial feature loss by avoiding feature flattening and to achieve depression score prediction. Tests on the AVEC2013 and AVEC2014 datasets reveal that our approach yields results on par with state-of-the-art techniques for detecting depression using video analysis. Additionally, our method has significantly lower computational complexity than mainstream methods.

Retraction Note: Fuzzy hyperconnected proximity spaces and fuzzy summability over CW complexes. Application of Smirnov fuzzy similarity in video analysis

Retraction Note: Fuzzy hyperconnected proximity spaces and fuzzy summability over CW complexes. Application of Smirnov fuzzy similarity in video analysis

Danger, Nuisance, Disregard: Analyzing User-Generated Videos for Augmented Reality Gameplay on Hand-held Devices

Augmented Reality (AR) has been largely deployed on smartphones in recent years. AR gaming, featured with geo-reference, is anchored to our real-world environments. Nevertheless, designing such AR user interaction in-the-wild is under-explored. Therefore, we examined 242 YouTube videos regarding AR gameplay, primarily Pokémon GO, (1) to reveal personal and social threats during gameplay, and (2) to identify how such threats connect to the user and spatial contexts. Our video analysis generalises the threats, including but not limited to hitting bystanders, falling off a cliff, car crashes, crowds and blockages, and stampedes. Through video analysis, we connect the threats with the user and spatial contexts. Subsequently, we propose several design tactics to deliver safe and nuisance-free AR usages in physical environments. Finally, we suggest strategies to consider large-scale deployment of AR at the levels of individuals and local communities, such as an auditable and accountable framework for user safety and social acceptability.