Dynamic Video Research Articles

Spatial adaptation in children with autism - a study based on behavioural dynamic video data

Children with autism show unique behavioural patterns and sensitivity to spatial elements; therefore, size and furniture arrangement at rehabilitation facilities can affect behaviour. In this study, spatial adaptation during three situations (learning, playing with toys, and finding objects) was evaluated for different spatial sizes in children with autism using video data. In particular, 330 videos of training sessions involving 15 boys with autism aged 4–6 years in spaces classified as training space (large, medium, and small) and immediate surroundings (activity areas and hallways) were evaluated. Skeletal data were acquired using AI motion capture technology and transformed into movement volume and positions using Grasshopper. Differences between children with autism in normal and aggressive states in different spaces were analyzed. The movement of volume increased in all space sizes during the aggressive state, especially in large spaces. In large spaces, the movement volume during learning was significantly larger, but object-seeking was significantly smaller in the aggressive state than in the normal state. In the immediate surrounding, the volume of movement varied significantly across behavioural states. Additionally, compared with the normal state, the movement location of children with autism in the aggressive state were more dispersed. The movement of location for learning, activity area and hallway were closer to the wall. Playing with toys and finding objects overlapped more with the furniture. This study provides a basis for the spatial adaptation of intervention services for children with autism and a reference for comparisons with current design standards.

Category-dependent contribution of dog facial and bodily cues in human perception of dog emotions

The increasing popularity of human-dog interaction in our society calls for fuller understanding of humans’ ability to appraise dogs’ affective states, yet most research only focuses on recognizing dog facial expressions of primary/basic emotions. While the face is the dominant human emotional expression channel, bodily cues are also informative indicators of dog emotional states. In this online study, with dynamic and naturalistic videos depicting a common range of dog primary (anger, disgust, fear, happiness, sadness, surprise) and secondary emotions (appeasement, frustration, pain, positive anticipation, separation-distress), we compared human performance from 447 participants in categorizing dog facial expressions (with a visible dog face only) and bodily expressions (with a visible dog face and body). The analysis revealed when averaging across all tested emotions, bodily expression tended to attract higher categorization accuracy than facial expression. However, the two expression channels demonstrated category-dependent modification of dog emotion categorization accuracy (e.g., higher accuracy in recognizing facial expressions of anger and surprise, but bodily expressions of happiness and fear) and bias (e.g., mistaking fear facial expression as happiness, but fear bodily expression as sadness). Furthermore, the impact of owner experience on recognizing dog emotions was also modulated by the expression channel and emotion category (e.g., prolonged experience with dogs tended to improve performance in recognizing the fear facial expression, and the appeasement bodily expression). Taken together, these results suggest that different channels of emotional expression by dogs may transmit category-specific diagnostic emotional cues, which aid human appraisal of their affective states.

Dynamic Music Video: Categorizing the Convergence of Video Games and Music Videos

The present article examines how the aesthetics of a specific format can be applied to another, thus creating a new autonomous product. This is the case of a distinctive point in video games wherein the playthrough is imbued with music video aesthetics, and the player interacts with the music, camera movements and landscape, becoming the protagonist and architect of what I propose to define as a “Dynamic Music Video”—following Collins’ definition of “dynamic music” (2008, 139). This study analyzes the musical transmedia narratives created from Death Stranding and other contemporary games, both regarding the gameplay experience and the User-Generated Content, focusing on their bidirectional motion: one that converts the players’ experience into a music video inserted into a video game, and one that converts the video game into an autonomous music video.

Click to Correction: Interactive Bidirectional Dynamic Propagation Video Object Segmentation Network.

High-quality video object segmentation is a challenging visual computing task. Interactive segmentation can improve segmentation results. This paper proposes a multi-round interactive dynamic propagation instance-level video object segmentation network based on click interaction. The network consists of two parts: a user interaction segmentation module and a bidirectional dynamic propagation module. A prior segmentation network was designed in the user interaction segmentation module to better segment objects of different scales that users click on. The dynamic propagation network achieves high-precision video object segmentation through the bidirectional propagation and fusion of segmentation masks obtained from multiple rounds of interaction. Experiments on interactive segmentation datasets and video object segmentation datasets show that our method achieves state-of-the-art segmentation results with fewer click interactions.

The Role of Mucociliary Clearance Function of Eustachian Tube as an Outcome Predictor for Type 1 Tympanoplasty.

To evaluate the association between mucociliary function of the Eustachian tube using the Saccharin test preoperatively and its correlation with dynamic slow-motion video endoscopy on the outcome of Type-I Tympanoplasty in patients with inactive mucosal chronic otitis media. Eighty patients diagnosed with inactive mucosal chronic otitis media who underwent Type-I Tympanoplasty were included in the study. Preoperative assessment of Eustachian tube function was conducted using the Saccharin test. Results of this test were categorized as normal, partial, or gross dysfunction. Dynamic slow-motion video endoscopy was performed to assess motion and pathological factors of the Eustachian tube. Results were evaluated based on a previously validated Visual Analogue Score (VAS). Patients were followed up postoperatively for 3 months. The proportion of patients with surgical failure at the end of the 1st and 3rd month postoperatively was significantly higher in cases of gross Eustachian tube dysfunction compared to those with normal and partial dysfunction (p-value < 0.0001 and p-value = 0.0001, respectively). Preoperative VAS scores in normal Eustachian tubes were significantly higher compared to those with partial dysfunction and gross dysfunction. The Saccharin test is a valuable tool for preoperative evaluation of mucociliary clearance of the Eustachian tube, and dynamic slow-motion video endoscopy serves as a useful adjunct in predicting the outcome of Type-I Tympanoplasty. Routine evaluation of mucociliary clearance function of the Eustachian tube should be included in the preoperative workup for patients undergoing Tympanoplasty to achieve optimal surgical outcomes.

Dynamic assessment of visual fatigue during video watching: Validation of dynamic rating based on post-task ratings and video features

People watching video displays for long durations experience visual fatigue and other symptoms associated with visual discomfort. Fatigue-reduction techniques are often applied but may potentially degrade the immersive experience. To appropriately adjust fatigue-reduction techniques, the changes in visual fatigue over time should be analyzed which is crucial for the appropriate adjustment of fatigue-reduction techniques. However, conventional methods used for assessing visual fatigue are inadequate because they rely entirely on post-task surveys, which cannot easily determine dynamic changes. This study employed a dynamic assessment method for evaluating visual fatigue in real-time. Using a joystick, participants continuously evaluated subjective fatigue whenever they perceived changes. A Simulator Sickness Questionnaire (SSQ) validated the results, which indicated significant correlations between dynamic assessments and the SSQ across five items associated with symptoms associated with visual discomfort. Furthermore, we explored the potential relationship between dynamic visual fatigue and objective video features, e.g., optical flow and the V-values of the hue/saturation value (HSV) color space, which represent the motion and brightness of the video. The results revealed that dynamic visual fatigue significantly correlated with both the optical flow and the V-value. Moreover, based on machine learning models, we determined that the changes in visual fatigue can be predicted based on the optical flow and V-value. Overall, the results validate that dynamic assessment methods can form a reliable baseline for real-time prediction of visual fatigue.

Tangled Physics: Knots Strain Intuitive Physical Reasoning.

Whereas decades of research have cataloged striking errors in physical reasoning, a resurgence of interest in intuitive physics has revealed humans' remarkable ability to successfully predict the unfolding of physical scenes. A leading interpretation intended to resolve these opposing results is that physical reasoning recruits a general-purpose mechanism that reliably models physical scenarios (explaining recent successes), but overly contrived tasks or impoverished and ecologically invalid stimuli can produce poor performance (accounting for earlier failures). But might there be tasks that persistently strain physical understanding, even in naturalistic contexts? Here, we explore this question by introducing a new intuitive physics task: evaluating the strength of knots and tangles. Knots are ubiquitous across cultures and time-periods, and evaluating them correctly often spells the difference between safety and peril. Despite this, 5 experiments show that observers fail to discern even very large differences in strength between knots. In a series of two-alternative forced-choice tasks, observers viewed a variety of simple "bends" (knots joining two pieces of thread) and decided which would require more force to undo. Though the strength of these knots is well-documented, observers' judgments completely failed to reflect these distinctions, across naturalistic photographs (E1), idealized renderings (E2), dynamic videos (E3), and even when accompanied by schematic diagrams of the knots' structures (E4). Moreover, these failures persisted despite accurate identification of the topological differences between the knots (E5); in other words, even when observers correctly perceived the underlying structure of the knot, they failed to correctly judge its strength. These results expose a blindspot in physical reasoning, placing new constraints on general-purpose theories of scene understanding.

Quantifying the Domino Effect of Septoplasty on Eustachian Tube Function and Nasal Resistance in Patients With Chronic Otitis Media: A Cross-Sectional Study.

Background Eustachian tube dysfunction is characterized by insufficient dilation, leading to secondary pathologies in the middle ear. By comparing pre- and post-operative grades of Eustachian tube functionand nasal resistance measurements, this study seeks to determine if septoplasty can improve Eustachian tube function in cases where nasal septal deviation is likely to cause mechanical dysfunction. We also aim to validate the JainBhalerao endoscopic classification of nasal septal deviation by assessing its utility in identifying septal deviations at a higher risk of causing Eustachian tube dysfunction. The ultimate goal is to establish guidelines for aural indications of septoplasty in treating Eustachian tube dysfunction-related middle ear disorders. Material and methods This prospective observational study was carried out from 1stJune 2022 to 31st March 2024 in the Department of Otorhinolaryngology at Acharya Vinoba Bhave Rural Hospital, involving 66 patients diagnosed with chronic otitis media and a deviated nasal septum with Eustachian tube dysfunction. Pre-operative and post-operative improvement in Eustachian tube function and Nasal resistance and their correlation werestudied using dynamic slow-motion video endoscopy and active anterior rhinomanometry, respectively. Statistical analysis included the chi-square test. Results Sixty-six patients diagnosed with chronic otitis media and deviated nasal septum with Eustachian tube dysfunction included in this study had a mean age of 35.6 years with 43 (65.2%) male predominance. Gross luminal narrowing and discrepancy of the volume of both nasal cavities led to higher degrees of Eustachian tube dysfunction due to pressure drop on the affected side, as observed in types 6, 7, and 8 as per Jain Bhalerao classification of deviated nasal septum. Nasal resistance measured using active anterior Rhinomanometry (Rhinodebitometry) showed a positive association of severity of nasal resistance in the types 6, 7, and 8 DNS of the Jain Bhalerao classification of deviated nasal septum. It demonstrated an improvement in the grade of Eustachian tube function and nasal resistance post-septoplasty. Conclusion The deviated nasal septum is one of the causes of Eustachian tube dysfunction and increased nasal resistance. Certain types of DNS are adversely associated with the causation of greater degrees of Eustachian tube dysfunction of mechanical type. Nasal septal deviation correction improved Eustachian dysfunction and nasal resistance after septoplasty.

Impaired Social Attention and Cognitive Empathy in a Paediatric Sample of Children with Symptoms of Anxiety.

Impairments in social cognition, in particular empathy, have been associated with childhood psychopathology, though previous investigations have yielded inconsistent results. Measures of social attention can reveal processes involved in responses to emotional stimuli and highlight deficits in empathy, or emotional biases in those with anxiety. The current study examined symptoms of anxiety, cognitive and affective empathy scores, and eye-gaze patterns in a pediatric sample of children (n = 178; 51-98 months-old) referred by their teachers for emerging psychopathology symptoms at school. We used eye-tracking metrics to capture gaze patterns during a dynamic video task designed to elicit empathic responses. Anxiety symptomology was reported by parents using the Screen for Child Anxiety Related Disorders scale (SCARED). Associations between eye-tracking variables, cognitive and affective empathy, and anxiety scores were analysed dimensionally in accordance with the Research and Domain Criteria (RDoC) framework. Higher levels of anxiety were associated with lower cognitive empathy and shorter first and total fixation durations to the eyes, across emotions (happiness, sadness, fear). No such associations were found between affective empathy and anxiety. Hierarchical multiple regression analyses revealed that across emotion conditions, first fixation duration negatively predicted anxiety scores. Our results indicate that children high in anxiety display cognitive empathy impairments and shorter attention to the eyes. These findings could inform early intervention programs for individuals at risk of developing anxiety disorders, as educating those high in anxiety on ways to identify emotions in others through changes in social attention could help to reduce anxiety.

Luminance decomposition and reconstruction for high dynamic range Video Quality Assessment

High dynamic range (HDR) video represents a wider range of brightness, detail and colour than standard dynamic range (SDR) video. However, SDR-based VQA (Video Quality Assessment) models struggle to capture HDR distortions. In addition, some of the existing methods designed for HDR video focus on emphasising the distortion of local areas of the video frame, ignoring the distortion of the video frame as a whole. Therefore, we propose a no reference VQA model based on luminance decomposition and recombination that provides excellent performance for HDR videos, called HDR-DRVQA. Specifically, HDR-DRVQA utilises a luminance decomposition strategy to decompose video frames into different regions for explicit extraction of perceptual features in different regions of the high dynamic range. We then further propose a residual aggregation module for recombining multi-region features to extract static spatial distortion representations and dynamic motion perception (captured by feature differences). Taking advantage of the Transformer network in remote dependency modelling, this information is fed into the Transformer network for interactive learning of motion perception and adaptively constructs a stream of spatial distortion information from shallow to deep layers during temporal aggregation. We validate that our model significantly outperforms SDR VQA and existing HDR VQA methods on the publicly available HDR databases.

Fusing binocular vision and deep learning to detect dynamic wheel-rail displacement of high-speed trains

Large displacements between the wheel and rail lead to track damage or even train derailment. Detecting dynamic wheel-rail displacement (DWRD) can provide a technical means for discriminating the operational health status of rail vehicles and formulating active control strategies. In this paper, a new method, which fuses binocular vision (BV) and deep learning (DL), is proposed to detect the DWRD online, the method is abbreviated as BV-DL. First, a binocular camera is used to capture the dynamic wheel-rail contact video online, while two lasers are equipped to focus on the wheel-rail contact region to locate some keypoints in the wheel-rail contact images. Then, an ROI (region of interest) detection network is proposed to recognize the wheel-rail contact region automatically, and a keypoint detection network is proposed to detect the wheel-rail pixel displacement (WRPD). Finally, a 3D coordinate transformation (3DCT) model is built to calculate the wheel-rail world displacement in real-time, i.e., the DWRD between the keypoints. To test the performance of the method, a laser displacement sensor-based method is used to verify the reliability of the 3DCT model. Meanwhile, a traditional image processing method, a MobileNet V3-based method, and a YOLOX-s-based method are introduced to predict the WRPD. Experimental results show that compared with the four methods, the proposed BV-DL method can achieve optimal results in pixel coordinate calculation and 3D coordinate computation.

An effective ultrasound fetal palate screening software based on the “sequential sector scan through the oral fissure” and three-dimensional ultrasound

BackgroundOrofacial clefts are one of the most common congenital malformations of the fetal face and ultrasound is mainly responsible for its diagnosis. It is difficult to view the fetal palate, so there is currently no unified standard for fetal palate screening, and the diagnosis of cleft palate is not included in the relevant prenatal ultrasound screening guidelines. Many prenatal diagnoses for cleft palate are missed due to the lack of effective screening methods. Therefore, it is imperative to increase the display rate of the fetal palate, which would improve the detection rate and diagnostic accuracy for cleft palate. We aim to introduce a fetal palate screening software based on the “sequential sector scan though the oral fissure”, an effective method for fetal palate screening which was verified by our follow up results and three-dimensional ultrasound and to evaluate its feasibility and clinical practicability.MethodsA software was designed and programmed based on “sequential sector scan through the oral fissure” and three-dimensional ultrasound. The three-dimensional ultrasound volume data of the fetal face were imported into the software. Then, the median sagittal plane was taken as the reference interface, the anterior upper margin of the mandibular alveolar bone was selected as the fulcrum, the interval angles, and the number of layers of the sector scan were set, after which the automatic scan was performed. Thus, the sector scan sequential planes of the mandibular alveolar bone, pharynx, soft palate, hard palate, and maxillary alveolar bone were obtained in sequence to display and evaluate the palate. In addition, the feasibility and accuracy of the software in fetal palate displaying and screening was evaluated by actual clinical cases.ResultsFull views of the normal fetal palates and the defective parts of the cleft palates were displayed, and relatively clear sequential tomographic images and continuous dynamic videos were formed after the three-dimensional volume data of 10 normal fetal palates and 10 cleft palates were imported into the software.ConclusionsThe software can display fetal palates more directly which might allow for a new method of fetal palate screening and cleft palate diagnosis.

Accurate Recognition of Vascular Lumen Region from 2D Ultrasound Cine Loops for Bubble Detection.

Accurate identification of vascular lumen region founded the base of bubble detection and bubble grading, which played a significant role in the detection of vascular gas emboli for the diagnosis of decompression sickness. To assist in the detection of vascular bubbles, it is crucial to develop an automatic algorithm that could identify vascular lumen areas in ultrasound videos with the interference of bubble presence. This article proposed an automated vascular lumen region recognition (VLRR) algorithm that could sketch the accurate boundary between vessel lumen and tissues from dynamic 2D ultrasound videos. It adopts 2D ultrasound videos of the lumen area as input and outputs the frames with circled vascular lumen boundary of the videos. Normalized cross-correlation method, distance transform technique, and region growing technique were adopted in this algorithm. Results A double-blind test was carried out to test the recognition accuracy of the algorithm on 180 samples in the images of 6 different grades of bubble videos, during which, intersection over union and pixel accuracy were adopted as evaluation metrics. The average IOU on the images of different bubble grades reached 0.76. The mean PA on 6 of the images of bubble grades reached 0.82. It is concluded that the proposed method could identify the vascular lumen with high accuracy, potentially applicable to assist clinicians in the measurement of the severity of vascular gas emboli in clinics.

Contrast-Enhanced Ultrasound: A Real-Time, Noninvasive, Radiation-Free Method for Intraoperative Male Urethral Fistula Assessment.

To evaluate the feasibility of intraoperative transurethral contrast-enhanced ultrasound for the assessment of male urethral fistulas. Patients in a prospective database who underwent intraoperative two-dimensional ultrasound, transurethral saline-enhanced ultrasound, and contrast-enhanced ultrasound between January 2017 and July 2022 were included. All patients were clinically diagnosed with urethral fistulae (UF) in the outpatient setting based on clinical presentations, traditional two-dimensional ultrasound, and/or other imaging modalities and confirmed during surgical repair. Dynamic videos of the scans were independently analyzed by two experienced ultrasonologists. Thirty-nine patients with an average age of 51 years were included. The UF were located in the anterior urethra in 22 (56.4%) patients and in the bulbar urethra in 14 (63.6%) patients. UF were located in the posterior urethra in 17 (436%) patients and in the prostatic urethra in 13 (76.5%) patients. Contrast-enhanced ultrasonography revealed UF in all patients. In patients with anterior UF, saline-enhanced ultrasound images did not show a UF in 15 (68.2%, 15/22) patients, 13 (86.7%, 13/15) of whom had fistulae with diameters <3 mm. Saline-enhanced ultrasound images did not reveal posterior UF in 13 (76.5%, 13/17) patients. The fistula diameters in eight (61.5%, 8/13) patients were <3 mm. The duration for contrast-enhanced ultrasonography was approximately 3 minutes. The duration for surgical repair was approximately 2 hours. Transurethral contrast-enhanced ultrasound is a real-time, noninvasive, and radiation-free method that allows intraoperative imaging and accurate assessment of male UF. Its sensitivity is higher than that of both two-dimensional ultrasound and transurethral saline-enhanced ultrasound. The location, size, and course of the fistulae can be clearly seen due to greater contrast during contrast-enhanced ultrasound.

STDAN: Deformable Attention Network for Space-Time Video Super-Resolution.

The target of space-time video super-resolution (STVSR) is to increase the spatial-temporal resolution of low-resolution (LR) and low-frame-rate (LFR) videos. Recent approaches based on deep learning have made significant improvements, but most of them only use two adjacent frames, that is, short-term features, to synthesize the missing frame embedding, which cannot fully explore the information flow of consecutive input LR frames. In addition, existing STVSR models hardly exploit the temporal contexts explicitly to assist high-resolution (HR) frame reconstruction. To address these issues, in this article, we propose a deformable attention network called STDAN for STVSR. First, we devise a long short-term feature interpolation (LSTFI) module that is capable of excavating abundant content from more neighboring input frames for the interpolation process through a bidirectional recurrent neural network (RNN) structure. Second, we put forward a spatial-temporal deformable feature aggregation (STDFA) module, in which spatial and temporal contexts in dynamic video frames are adaptively captured and aggregated to enhance SR reconstruction. Experimental results on several datasets demonstrate that our approach outperforms state-of-the-art STVSR methods. The code is available at https://github.com/littlewhitesea/STDAN.

CDGT: Constructing diverse graph transformers for emotion recognition from facial videos

Recognizing expressions from dynamic facial videos can find more natural affect states of humans, and it becomes a more challenging task in real-world scenes due to pose variations of face, partial occlusions and subtle dynamic changes of emotion sequences. Existing transformer-based methods often focus on self-attention to model the global relations among spatial features or temporal features, which cannot well focus on important expression-related locality structures from both spatial and temporal features for the in-the-wild expression videos. To this end, we incorporate diverse graph structures into transformers and propose a CDGT method to construct diverse graph transformers for efficient emotion recognition from in-the-wild videos. Specifically, our method contains a spatial dual-graphs transformer and a temporal hyperbolic-graph transformer. The former deploys a dual-graph constrained attention to capture latent emotion-related graph geometry structures among local spatial tokens for efficient feature representation, especially for the video frames with pose variations and partial occlusions. The latter adopts a hyperbolic-graph constrained self-attention that explores important temporal graph structure information under hyperbolic space to model more subtle changes of dynamic emotion. Extensive experimental results on in-the-wild video-based facial expression databases show that our proposed CDGT outperforms other state-of-the-art methods.

IDSSI: Image Deturbulence with Semantic and Spatial–Temporal Information

The propagation of light through turbulent media results in refractive index fluctuations, causing distortion and blurring of images captured by imaging equipment. Consequently, it is of paramount importance to mitigate turbulence effects. Deep convolutional neural networks incorporating attention mechanisms have demonstrated remarkable success in dynamic video restoration. However, in most networks, the attention mechanism is limited to capturing simple contextual features, failing to adequately exploit multi-level image features. This paper introduces IDSSI, an effective model that utilizes semantic and spatio–temporal information for turbulence mitigation. A novel two-branch feature extraction structure is proposed, capable of extracting multi-scale enhanced features with semantic information under limited supervision. These perceived semantic features are subsequently fused into global features, enhancing multi-scale perception for turbulence repair. Furthermore, a new Spatial–Temporal feature learning strategy is proposed. This approach facilitates the extraction and modulation of temporal information by obtaining edge cues, effectively concatenating and merging with spatial features. This strategy serves as an efficient alternative to 3D convolution. Experimental results on relevant datasets demonstrate the superiority of the proposed model over current state-of-the-art turbulence repair methods.

Artificial intelligence model for automated surgical instrument detection and counting: an experimental proof-of-concept study

BackgroundRetained surgical items (RSI) are preventable events that pose a significant risk to patient safety. Current strategies for preventing RSIs rely heavily on manual instrument counting methods, which are prone to human error. This study evaluates the feasibility and performance of a deep learning-based computer vision model for automated surgical tool detection and counting.MethodsA novel dataset of 1,004 images containing 13,213 surgical tools across 11 categories was developed. The dataset was split into training, validation, and test sets at a 60:20:20 ratio. An artificial intelligence (AI) model was trained on the dataset, and the model’s performance was evaluated using standard object detection metrics, including precision and recall. To simulate a real-world surgical setting, model performance was also evaluated in a dynamic surgical video of instruments being moved in real-time.ResultsThe model demonstrated high precision (98.5%) and recall (99.9%) in distinguishing surgical tools from the background. It also exhibited excellent performance in differentiating between various surgical tools, with precision ranging from 94.0 to 100% and recall ranging from 97.1 to 100% across 11 tool categories. The model maintained strong performance on a subset of test images containing overlapping tools (precision range: 89.6–100%, and recall range 97.2–98.2%). In a real-time surgical video analysis, the model maintained a correct surgical tool count in all non-transition frames, with a median inference speed of 40.4 frames per second (interquartile range: 4.9).ConclusionThis study demonstrates that using a deep learning-based computer vision model for automated surgical tool detection and counting is feasible. The model’s high precision and real-time inference capabilities highlight its potential to serve as an AI safeguard to potentially improve patient safety and reduce manual burden on surgical staff. Further validation in clinical settings is warranted.

Unveiling the Potential: A Comprehensive Review of Dynamic Slow-Motion Video Endoscopy for Eustachian Tube Dysfunction Evaluation.

Eustachian tube dysfunction (ETD) poses diagnostic challenges due to its complex pathophysiology and varied clinical presentation. Traditional diagnostic methods often lack direct visualization of the Eustachian tube (ET) function, leading to suboptimal evaluation and management. Dynamic slow-motion video endoscopy (DSVE) has emerged as a novel approach to address these limitations, offering real-time visualization of ET dynamics with enhanced clarity and precision. This comprehensive review provides an overview of DSVE as a promising tool for evaluating ETD. We discuss its methodology, clinical applications, comparative analysis with traditional methods, and future directions. Key findings from the literature highlight DSVE's ability to enhance diagnostic accuracy, facilitate targeted treatment strategies, and improve patient outcomes. Integrating DSVE into routine clinical practice holds significant implications for the diagnosis and management of ETD, offering clinicians valuable insights into underlying pathophysiology and guiding personalized treatment interventions. Future research should focus on standardizing DSVE protocols, validating its diagnostic accuracy, and exploring its role in guiding novel treatment modalities. By advancing our understanding of ETD and optimizing diagnostic and therapeutic approaches, DSVE has the potential to revolutionize the management of this common yet challenging otologic condition.

A power-aware vision-based virtual sensor for real-time edge computing

Graphics processing units and tensor processing units coupled with tiny machine learning models deployed on edge devices are revolutionizing computer vision and real-time tracking systems. However, edge devices pose tight resource and power constraints. This paper proposes a real-time vision-based virtual sensors paradigm to provide power-aware multi-object tracking at the edge while preserving tracking accuracy and enhancing privacy. We thoroughly describe our proposed system architecture, focusing on the Dynamic Inference Power Manager (DIPM). Our proposed DIPM is based on an adaptive frame rate to provide energy savings. We implement and deploy the virtual sensor and the DIPM on the NVIDIA Jetson Nano edge platform to prove the effectiveness and efficiency of the proposed solution. The results of extensive experiments demonstrate that the proposed virtual sensor can achieve a reduction in energy consumption of about 36% in videos with relatively low dynamicity and about 21% in more dynamic video content while simultaneously maintaining tracking accuracy within a range of less than 1.2%.