Evaluating the Efficacy of a Peripheral Nerve Simulator-Guided Brachial Plexus Block in Rabbits Undergoing Orthopaedic Surgery Compared to Systemic Analgesia.

Locoregional anaesthetic techniques are invaluable for providing multimodal analgesia for painful surgical procedures. This prospective, randomised study describes a nerve stimulator-guided brachial plexus blockade (BPB) in rabbits undergoing orthopaedic surgery in comparison to systemic lidocaine. Premedication was provided with intramuscular (IM) medetomidine, fentanyl, and midazolam. Anaesthesia was induced (propofol IV) and maintained with isoflurane. Nine rabbits received a lidocaine BPB (2%; 0.3 mL kg-1), and eight received a lidocaine constant rate infusion (CRI) (2 mg kg-1 IV, followed by 100 µg kg-1 min-1). Rescue analgesia was provided with fentanyl IV. Carprofen was administered at the end of the surgery. Postoperative pain was determined using the Rabbit Grimace Scale (RGS) and a composite pain scale. Buprenorphine was administered according to the pain score for two hours after extubation. Rabbits were filmed during the first two hours to measure distance travelled and behaviours. Food intake and faeces output were compared. Every rabbit in CRI required intraoperative rescue analgesia compared to none in BPB. However, rabbits in both groups had similar pain scores, and there was no difference in the administration of postoperative analgesia. There were no significant differences in food intake or faeces production over 18 h, and no significant differences in distance travelled or behaviours examined during the first two hours. BPB seems superior for intraoperative analgesia. Postoperatively, both groups were comparable.

Improved likelihood ratios for face recognition in surveillance video by multimodal feature pairing.

In forensic and security scenarios, accurate facial recognition in surveillance videos, often challenged by variations in pose, illumination, and expression, is essential. Traditional manual comparison methods lack standardization, revealing a critical gap in evidence reliability. We propose an enhanced images-to-video recognition approach, pairing facial images with attributes like pose and quality. Utilizing datasets such as ENFSI 2015, SCFace, XQLFW, ChokePoint, and ForenFace, we assess evidence strength using calibration methods for likelihood ratio estimation. Three models-ArcFace, FaceNet, and QMagFace-undergo validation, with the log-likelihood ratio cost (Cllr) as a key metric. Results indicate that prioritizing high-quality frames and aligning attributes with reference images optimizes recognition, yielding similar Cllr values to the top 25% best frames approach. A combined embedding weighted by frame quality emerges as the second-best method. Upon preprocessing facial images with the super resolution CodeFormer, it unexpectedly increased Cllr, undermining evidence reliability, advising against its use in such forensic applications.

Digital monitoring of the microchannel filling flow dynamics using a non-contactless smartphone-based nano-liter precision flow velocity meter.

Microfluidic systems find widespread applications in diagnostics, biological research, chemistry, and engineering studies. Among their many critical parameters, flow rate plays a pivotal role in maintaining the functionality of microfluidic systems, including droplet-based microfluidic devices and those used in cell culture. It also significantly influences microfluidic mixing processes. Although various flow rate measurement devices have been developed, the challenge remains in accurately measuring flow rates within customized channels. This paper presents the development of a 3D-printed smartphone-based flow velocity meter. The 3D-printed platform is angled at 30° to achieve transparent flow visualization, and it doesn't require any external optical components such as external lenses and filters. Two LED modules integrated into the platform create a uniform illumination environment for video capture, powered directly by the smartphone. The performance of our platform, combined with a customized video processing algorithm, was assessed in three different channel types: uniform straight channels, straight channels with varying widths, and vessel-like channel patterns to demonstrate its versatility. Our device effectively measured flow velocities from 5.43 mm/s to 24.47 mm/s, with video quality at 1080p resolution and 60 frames per second, for which the measurement range can be extended by adjusting the frame rate. This flow velocity meter can be a useful analytical tool to evaluate and enhance microfluidic channel designs of various lab-on-a-chip applications.

Cluster2Former: Semisupervised Clustering Transformers for Video Instance Segmentation.

A novel approach for video instance segmentation is presented using semisupervised learning. Our Cluster2Former model leverages scribble-based annotations for training, significantly reducing the need for comprehensive pixel-level masks. We augment a video instance segmenter, for example, the Mask2Former architecture, with similarity-based constraint loss to handle partial annotations efficiently. We demonstrate that despite using lightweight annotations (using only 0.5% of the annotated pixels), Cluster2Former achieves competitive performance on standard benchmarks. The approach offers a cost-effective and computationally efficient solution for video instance segmentation, especially in scenarios with limited annotation resources.

A fuzzy decision-making system for video tracking with multiple objects in non-stationary conditions.

Computer vision remains challenged by tracking multiple objects in motion frames, despite efforts to improve surveillance, healthcare, and human-machine interaction. This paper presents a method for monitoring several moving objects in non-stationary settings for autonomous navigation. Additionally, at each phase, movement information between successive frames, including the new frame and the previous frame, is employed to determine the location of moving objects inside the camera's field of view, and the background in the new frame is determined. With the help of a matching algorithm, the Kanade-Lucas-Tomasi (KLT) feature tracker for each frame is determined. To get the new frame, we access the matching feature points between two subsequent frames, calculate the movement size of the feature points and the camera movement, and subtract the previous frame of moving objects from the current frame. Every moving object within the camera's field of view is captured at every moment and location. The moving items are categorized and segregated using fuzzy logic based on their mass center and length-to-width ratio. Our algorithm was implemented to investigate autonomous navigation surveillance of three types of moving objects, such as a vehicle, a pedestrian, a bicycle, or a motorcycle. The results indicate high accuracy and an acceptable time requirement for monitoring moving objects. It has a tracking and classification accuracy of around 75 % and processes 43 frames per second, making it superior to existing approaches in terms of speed and accuracy.

Microscopic Video-Based Grouped Embryo Segmentation: A Deep Learning Approach.

PURPOSE: The primary aim of this research is to enhance the utilization of advanced deep learning (DL) techniques in the domain of in vitro fertilization (IVF) by presenting a more refined approach to the segmentation and organization of microscopic embryos. This study also seeks to establish a comprehensive embryo database that can be employed for future research and educational purposes. METHODS: This study introduces an advanced methodology for embryo segmentation and organization using DL. The approach comprises three primary steps: Embryo Segmentation Model, Segmented Embryo Image Organization, and Clear and Blur Image Classification. The proposed approach was rigorously evaluated on a sample of 5182 embryos extracted from 362 microscopic embryo videos. RESULTS: The study's results show that the proposed method is highly effective in accurately segmenting and organizing embryo images. This is evidenced by the high mean average precision values of 1.0 at an intersection over union threshold of 0.5 and across the range of 0.5 to 0.95, indicating a robust object detection capability that is vital in the IVF process. Segmentation of images based on various factors such as the day of development, patient, growth medium, and embryo facilitates easy comparison and identification of potential issues. Finally, appropriate threshold values for clear and blur image classification are proposed. CONCLUSION: The suggested technique represents an indispensable stage of data preparation for IVF training and education. Furthermore, this study provides a solid foundation for future research and adoption of DL in IVF, which is expected to have a significant positive impact on IVF outcomes.

Foldable low-cost point-of-care device for testing blood coagulation using smartphones.

Cardiovascular diseases (CVDs) caused by thrombotic events are a significant global health concern, affecting millions of people worldwide. The international normalized ratio (INR) is the most widely used measure of coagulation status, and frequent testing is required to adjust blood-thinning drug dosage, requiring hospital visits and experts to perform the test. Here we present a low-cost and portable smartphone-based device for screening INR levels from whole blood samples at the point of care. Our device uses a 3D printed platform and light-emitting diode backlight modules to create a uniform optical environment, and its foldable design allows for easy transport. Our device also features an algorithm that allows users to acquire and process video of sample flow in a microfluidic channel on their smartphone, providing a cost-effective and convenient option for blood coagulation monitoring at the point of care. We tested the performance of our smartphone-based INR device using both commercially available control samples and clinical human blood samples, demonstrating high accuracy and reliability. Our device has the potential to improve patient outcomes by enabling more frequent monitoring and, as appropriate, dosage adjustments of blood-thinning drugs, providing an affordable and portable option for screening INR levels at the point of care.

CNN-LSTM Model for Recognizing Video-Recorded Actions Performed in a Traditional Chinese Exercise.

Identifying human actions from video data is an important problem in the fields of intelligent rehabilitation assessment. Motion feature extraction and pattern recognition are the two key procedures to achieve such goals. Traditional action recognition models are usually based on the geometric features manually extracted from video frames, which are however difficult to adapt to complex scenarios and cannot achieve high-precision recognition and robustness. We investigate a motion recognition model and apply it to recognize the sequence of complicated actions of a traditional Chinese exercise (ie, Baduanjin). We first developed a combined convolutional neural network (CNN) and long short-term memory (LSTM) model for recognizing the sequence of actions captured in video frames, and applied it to recognize the actions of Baduanjin. Moreover, this method has been compared with the traditional action recognition model based on geometric motion features in which Openpose is used to identify the joint positions in the skeletons. Its performance of high recognition accuracy has been verified on the testing video dataset, containing the video clips from 18 different practicers. The CNN-LSTM recognition model achieved 96.43% accuracy on the testing set; while those manually extracted features in the traditional action recognition model were only able to achieve 66.07% classification accuracy on the testing video dataset. The abstract image features extracted by the CNN module are more effective on improving the classification accuracy of the LSTM model. The proposed CNN-LSTM based method can be a useful tool in recognizing the complicated actions.

A new YOLO-based method for social distancing from real-time videos.

The coronavirus disease (COVID-19) is primarily disseminated through physical contact. As a precaution, it is recommended that indoor spaces have a limited number of people and at least one meter apart. This study proposes a real-time method for monitoring physical distancing compliance in indoor spaces using computer vision and deep learning techniques. The proposed method utilizes YOLO (You Only Look Once), a popular convolutional neural network-based object detection model, pre-trained on the Microsoft COCO (Common Objects in Context) dataset to detect persons and estimate their physical distance in real time. The effectiveness of the proposed method was assessed using metrics including accuracy rate, frame per second (FPS), and mean average precision (mAP). The results show that the YOLO v3 model had the most remarkable accuracy (87.07%) and mAP (89.91%). On the other hand, the highest fps rate of up to 18.71 was achieved by the YOLO v5s model. The results demonstrate the potential of the proposed method for effectively monitoring physical distancing compliance in indoor spaces, providing valuable insights for future use in other public health scenarios.

Video Process Mining and Model Matching for Intelligent Development: Conformance Checking.

Traditional business process-extraction models mainly rely on structured data such as logs, which are difficult to apply to unstructured data such as images and videos, making it impossible to perform process extractions in many data scenarios. Moreover, the generated process model lacks analysis consistency of the process model, resulting in a single understanding of the process model. To solve these two problems, a method of extracting process models from videos and analyzing the consistency of process models is proposed. Video data are widely used to capture the actual performance of business operations and are key sources of business data. Video data preprocessing, action placement and recognition, predetermined models, and conformance verification are all included in a method for extracting a process model from videos and analyzing the consistency between the process model and the predefined model. Finally, the similarity was calculated using graph edit distances and adjacency relationships (GED_NAR). The experimental results showed that the process model mined from the video was better in line with how the business was actually carried out than the process model derived from the noisy process logs.

Preprocessing for Keypoint-Based Sign Language Translation without Glosses.

While machine translation for spoken language has advanced significantly, research on sign language translation (SLT) for deaf individuals remains limited. Obtaining annotations, such as gloss, can be expensive and time-consuming. To address these challenges, we propose a new sign language video-processing method for SLT without gloss annotations. Our approach leverages the signer's skeleton points to identify their movements and help build a robust model resilient to background noise. We also introduce a keypoint normalization process that preserves the signer's movements while accounting for variations in body length. Furthermore, we propose a stochastic frame selection technique to prioritize frames to minimize video information loss. Based on the attention-based model, our approach demonstrates effectiveness through quantitative experiments on various metrics using German and Korean sign language datasets without glosses.

Vision-Based Detection of Low-Emission Sources in Suburban Areas Using Unmanned Aerial Vehicles.

The paper discusses the problem of detecting emission sources in a low buildings area using unmanned aerial vehicles. The problem was analyzed, and methods of solving it were presented. Various data acquisition scenarios and their impact on the feasibility of the task were analyzed. A method for detecting smoke objects over buildings using stationary video sequences acquired with a drone in hover with the camera in the nadir position is proposed. The method uses differential frame information from stabilized video sequences and the YOLOv7 classifier. A convolutional network classifier was used to detect the roofs of buildings, using a custom training set adapted to the type of data used. Such a solution, although quite effective, is not very practical for the end user, but it enables the automatic generation of a comprehensive training set for classifiers based on deep neural networks. The effectiveness of such a solution was tested for the latest version of the YOLOv7 classifier. The tests proved the effectiveness of the described method, both for single images and video sequences. In addition, the obtained classifier correctly recognizes objects for sequences that do not meet some of the initial assumptions, such as the angle of the camera capturing the image.

A new YOLO-based method for real-time crowd detection from video and performance analysis of YOLO models.

As seen in the COVID-19 pandemic, one of the most important measures is physical distance in viruses transmitted from person to person. According to the World Health Organization (WHO), it is mandatory to have a limited number of people in indoor spaces. Depending on the size of the indoors, the number of persons that can fit in that area varies. Then, the size of the indoor area should be measured and the maximum number of people should be calculated accordingly. Computers can be used to ensure the correct application of the capacity rule in indoors monitored by cameras. In this study, a method is proposed to measure the size of a prespecified region in the video and count the people there in real time. According to this method: (1) predetermining the borders of a region on the video, (2) identification and counting of people in this specified region, (3) it is aimed to estimate the size of the specified area and to find the maximum number of people it can take. For this purpose, the You Only Look Once (YOLO) object detection model was used. In addition, Microsoft COCO dataset pre-trained weights were used to identify and label persons. YOLO models were tested separately in the proposed method and their performances were analyzed. Mean average precision (mAP), frame per second (fps), and accuracy rate metrics were found for the detection of persons in the specified region. While the YOLO v3 model achieved the highest value in accuracy rate and mAP (both 0.50 and 0.75) metrics, the YOLO v5s model achieved the highest fps rate among non-Tiny models.

Adaptive Remote Sensing Paradigm for Real-Time Alerting of Convulsive Epileptic Seizures.

Epilepsy is a debilitating neurological condition characterized by intermittent paroxysmal states called fits or seizures. Especially, the major motor seizures of a convulsive nature, such as tonic-clonic seizures, can cause aggravating consequences. Timely alerting for these convulsive epileptic states can therefore prevent numerous complications, during, or following the fit. Based on our previous research, a non-contact method using automated video camera observation and optical flow analysis underwent field trials in clinical settings. Here, we propose a novel adaptive learning paradigm for optimization of the seizure detection algorithm in each individual application. The main objective of the study was to minimize the false detection rate while avoiding undetected seizures. The system continuously updated detection parameters retrospectively using the data from the generated alerts. The system can be used under supervision or, alternatively, through autonomous validation of the alerts. In the latter case, the system achieved self-adaptive, unsupervised learning functionality. The method showed improvement of the detector performance due to the learning algorithm. This functionality provided a personalized seizure alerting device that adapted to the specific patient and environment. The system can operate in a fully automated mode, still allowing human observer to monitor and override the decision process while the algorithm provides suggestions as an expert system.

Evaluating the robustness of a contact-less mHealth solution for personal and remote monitoring of blood oxygen saturation.

MHealth technologies play a fundamental role in epidemiological situations such as the ongoing outbreak of COVID-19 because they allow people to self-monitor their health status (e.g. vital parameters) at any time and place, without necessarily having to physically go to a medical clinic. Among vital parameters, special care should be given to monitor blood oxygen saturation (SpO2), whose abnormal values are a warning sign for potential COVID-19 infection. SpO2 is commonly measured through the pulse oximeter that requires skin contact and hence could be a potential way of spreading contagious infections. To overcome this problem, we have recently developed a contact-less mHealth solution that can measure blood oxygen saturation without any contact device but simply processing short facial videos acquired by any common mobile device equipped with a camera. Facial video frames are processed in real-time to extract the remote photoplethysmographic signal useful to estimate the SpO2 value. Such a solution promises to be an easy-to-use tool for both personal and remote monitoring of SpO2. However, the use of mobile devices in daily situations holds some challenges in comparison to the controlled laboratory scenarios. One main issue is the frequent change of perspective viewpoint due to head movements, which makes it more difficult to identify the face and measure SpO2. The focus of this work is to assess the robustness of our mHealth solution to head movements. To this aim, we carry out a pilot study on the benchmark PURE dataset that takes into account different head movements during the measurement. Experimental results show that the SpO2 values obtained by our solution are not only reliable, since they are comparable with those obtained with a pulse oximeter, but are also insensitive to head motion, thus allowing a natural interaction with the mobile acquisition device.

Transformer-Based Multiple-Object Tracking via Anchor-Based-Query and Template Matching.

Multiple object tracking (MOT) plays an important role in intelligent video-processing tasks, which aims to detect and track all moving objects in a scene. Joint-detection-and-tracking (JDT) methods are thriving in MOT tasks, because they accomplish the detection and data association in a single stage. However, the slow training convergence and insufficient data association limit the performance of JDT methods. In this paper, the anchor-based query (ABQ) is proposed to improve the design of the JDT methods for faster training convergence. By augmenting the coordinates of the anchor boxes into the learnable queries of the decoder, the ABQ introduces explicit prior spatial knowledge into the queries to focus the query-to-feature learning of the JDT methods on the local region, which leads to faster training speed and better performance. Moreover, a new template matching (TM) module is designed for the JDT methods, which enables the JDT methods to associate the detection results and trajectories with historical features. Finally, a new transformer-based MOT method, ABQ-Track, is proposed. Extensive experiments verify the effectiveness of the two modules, and the ABQ-Track surpasses the performance of the baseline JDT methods, TransTrack. Specifically, the ABQ-Track only needs to train for 50 epochs to achieve convergence, while that for TransTrack is 150 epochs.

Backhand-Approach-Based American Sign Language Words Recognition Using Spatial-Temporal Body Parts and Hand Relationship Patterns.

Most of the existing methods focus mainly on the extraction of shape-based, rotation-based, and motion-based features, usually neglecting the relationship between hands and body parts, which can provide significant information to address the problem of similar sign words based on the backhand approach. Therefore, this paper proposes four feature-based models. The spatial-temporal body parts and hand relationship patterns are the main feature. The second model consists of the spatial-temporal finger joint angle patterns. The third model consists of the spatial-temporal 3D hand motion trajectory patterns. The fourth model consists of the spatial-temporal double-hand relationship patterns. Then, a two-layer bidirectional long short-term memory method is used to deal with time-independent data as a classifier. The performance of the method was evaluated and compared with the existing works using 26 ASL letters, with an accuracy and F1-score of 97.34% and 97.36%, respectively. The method was further evaluated using 40 double-hand ASL words and achieved an accuracy and F1-score of 98.52% and 98.54%, respectively. The results demonstrated that the proposed method outperformed the existing works under consideration. However, in the analysis of 72 new ASL words, including single- and double-hand words from 10 participants, the accuracy and F1-score were approximately 96.99% and 97.00%, respectively.

A video processing and machine vision-based automatic analyzer to determine sequentially total suspended and settleable solids in wastewater.

The monitoring of total suspended (TSS) and settleable (SetS) solids in wastewater is essential to maintain the quality parameters for aquatic biota because they can transport pollutants and block light penetration. Determining them by their respective reference methods, however, is laborious, expensive, and time consuming. To overcome this, we developed a new analytical instrument called Solids in Wastewater's Machine Vision-based Automatic Analyzer (SWAMVA), which is equiped with an automatic sampler and a software for real-time digital movie capture to quantify sequentially the TSS and SetS contents in wastewater samples. The machine vision algorithm (MVA) coupled with the Red color plane (derived from color histograms in the Red-Green-Blue (RGB) system) showed the best prediction results with R2 of 0.988 and 0.964, and relative error of prediction (REP) of 6.133 and 9.115% for TSS and SetS, respectively. The constructed models were validated by Analysis of Variance (ANOVA), and the accuracy and precision of the predictions by the t- and F-tests, respectively, at a 0.05 significance level. The elliptical joint confidence region (EJCR) test confirmed the accuracy, while the coefficient of variation (CV) of 6.529 and 10.908% confirmed the good precisions, respectively. Compared with the reference method (Standard Methods For the Examination of Water and Wastewater), the proposed method reduced the analysis volume from 1.5 L to just 15 mL and the analysis time from 12 h to 24 s per sample. Therefore, SWAMVA can be considered an important alternative to the determination of TSS and SetS in wastewater as an automatic, fast, and low-cost analytical tool, following the principles of Green Chemistry and exploiting Industry 4.0 features such as intelligent processing, miniaturization, and machine vision.

Algorithmic insights of camera-based respiratory motion extraction.

Objective. Measuring the respiratory signal from a video based on body motion has been proposed and recently matured in products for contactless health monitoring. The core algorithm for this application is the measurement of tiny chest/abdominal motions induced by respiration (i.e. capturing sub-pixel displacement caused by subtle motion between subsequent video frames), and the fundamental challenge is motion sensitivity. Though prior art reported on the validation with real human subjects, there is no thorough or rigorous benchmark to quantify the sensitivities and boundary conditions of motion-based core respiratory algorithms.Approach. A set-up was designed with a fully-controllable physical phantom to investigate the essence of core algorithms, together with a mathematical model incorporating two motion estimation strategies and three spatial representations, leading to six algorithmic combinations for respiratory signal extraction. Their promises and limitations are discussed and clarified through the phantom benchmark.Main results. With the variation of phantom motion intensity between 0.5 mm and 8 mm, the recommended approach obtains an average precision, recall, coverage and MAE of 88.1%, 91.8%, 95.5% and 2.1 bpm in the day-light condition, and 81.7%, 90.0%, 93.9% and 4.4 bpm in the night condition.Significance. The insights gained in this paper are intended to improve the understanding and applications of camera-based respiration measurement in health monitoring. The limitations of this study stem from the used physical phantom that does not consider human factors like body shape, sleeping posture, respiratory diseases, etc., and the investigated scenario is focused on sleep monitoring, not including scenarios with a sitting or standing patient like in clinical ward and triage.

American Sign Language Words Recognition of Skeletal Videos Using Processed Video Driven Multi-Stacked Deep LSTM.

Complex hand gesture interactions among dynamic sign words may lead to misclassification, which affects the recognition accuracy of the ubiquitous sign language recognition system. This paper proposes to augment the feature vector of dynamic sign words with knowledge of hand dynamics as a proxy and classify dynamic sign words using motion patterns based on the extracted feature vector. In this method, some double-hand dynamic sign words have ambiguous or similar features across a hand motion trajectory, which leads to classification errors. Thus, the similar/ambiguous hand motion trajectory is determined based on the approximation of a probability density function over a time frame. Then, the extracted features are enhanced by transformation using maximal information correlation. These enhanced features of 3D skeletal videos captured by a leap motion controller are fed as a state transition pattern to a classifier for sign word classification. To evaluate the performance of the proposed method, an experiment is performed with 10 participants on 40 double hands dynamic ASL words, which reveals 97.98% accuracy. The method is further developed on challenging ASL, SHREC, and LMDHG data sets and outperforms conventional methods by 1.47%, 1.56%, and 0.37%, respectively.