Video Research Articles

Creation of a Prototype Cochlear Training Model.

Creation of a novel 3D-printed physical cochlear model that demonstrated the feasibility of creating the model, and impact of a Graphical User Interface (GUI) system on training insertion metrics. Feasibility study with a pilot prospective data collection. Tertiary academic center. The study was IRB exempt. Five resident trainees (PGY1-PGY5) practiced electrode insertions in cadaveric temporal bones before using the simulator. Nine students were educated on how to hold the electrodes and position them, and then allowed to use the simulator. All trainees were instructed that slower insertions were favorable. One cochlear implant (CI) surgeon used the simulator. The GUI captured the real video feed, but also provided distance, trajectory, and velocity measurements. The program is designed to plot the real-time depth of insertion and speed of insertion of the electrode; the user is also provided real-time occurrence of any kinks and back-outs. A total of 14 trainees and 1 CI surgeon inserted the electrode at least 5 times without the use of the GUI (before) and then at least 5 times with the use of the GUI (after). Average Speed before and after (100.84 and 53.23 mm/s); Average minimum speed before and after (59.34 and 9.65 mm/s); and Average maximum speed before and after (416 and 285.81 mm/s). Statistically significant improvements were noted in all the measured speeds of insertion (P < .001). The other variables improved but not to a statistical significance. Real-time training using the 3D-printed model and GUI for cochlear implantation can help improve surgical resident training and comfort levels with electrode insertion for surgical trainees. The advantage of this model is that surgeons/trainees can use it as many times as they like, as the whole set-up is easy, economical, and reusable. The real time graphical user interface enhances training and retention of the practiced skills.

Loopholes in the Indian Banking System concerning Non-Performing Assets (NPAs) – A Case Study of “Axis Bank and HDFC Bank”

This paper presents the development and implementation of an innovative IoT-based Surveillance Robot designed for remote control, utilizing a Wi-Fi module and a smartphone interface. The portable espionage robot integrates cutting-edge technology, featuring an AI Thinker ESP32-CAM module with an ESP32-S processor, an OV2640 camera, motor drivers, and a robust chassis with two moving wheels. The ESP32-CAM allows the capture and storage of images on a microSD card, facilitating efficient data management. The robot employs the HTTP Communication protocol, enabling users to access live video streaming from the OV2640 camera through a standard web browser. The web interface includes intuitive directional buttons for seamless control, allowing users to command the robot to move left, right, forward, and backward. The locomotion of the robot is achieved through two DC motors integrated with a Robot chassis and an L293D motor driver module. The real-time video feed is transmitted wirelessly to the user's smartphone over a Wi-Fi infrastructure, providing a live- streaming experience. This wireless surveillance robot finds applications in various scenarios such as war fields, disaster management, and beyond, showcasing its versatility in remote monitoring and reconnaissance tasks. Keywords: IoT, Surveillance Robot, Wireless Control, ESP32- CAM, HTTP Communication, Video Streaming, Smartphone Control, Disaster Management, Robotics, Remote Monitoring, Reconnaissance.

SLoN: a spiking looming perception network exploiting neural encoding and processing in ON/OFF channels.

Looming perception, the ability to sense approaching objects, is crucial for the survival of humans and animals. After hundreds of millions of years of evolutionary development, biological entities have evolved efficient and robust looming perception visual systems. However, current artificial vision systems fall short of such capabilities. In this study, we propose a novel spiking neural network for looming perception that mimics biological vision to communicate motion information through action potentials or spikes, providing a more realistic approach than previous artificial neural networks based on sum-then-activate operations. The proposed spiking looming perception network (SLoN) comprises three core components. Neural encoding, known as phase coding, transforms video signals into spike trains, introducing the concept of phase delay to depict the spatial-temporal competition between phasic excitatory and inhibitory signals shaping looming selectivity. To align with biological substrates where visual signals are bifurcated into parallel ON/OFF channels encoding brightness increments and decrements separately to achieve specific selectivity to ON/OFF-contrast stimuli, we implement eccentric down-sampling at the entrance of ON/OFF channels, mimicking the foveal region of the mammalian receptive field with higher acuity to motion, computationally modeled with a leaky integrate-and-fire (LIF) neuronal network. The SLoN model is deliberately tested under various visual collision scenarios, ranging from synthetic to real-world stimuli. A notable achievement is that the SLoN selectively spikes for looming features concealed in visual streams against other categories of movements, including translating, receding, grating, and near misses, demonstrating robust selectivity in line with biological principles. Additionally, the efficacy of the ON/OFF channels, the phase coding with delay, and the eccentric visual processing are further investigated to demonstrate their effectiveness in looming perception. The cornerstone of this study rests upon showcasing a new paradigm for looming perception that is more biologically plausible in light of biological motion perception.

MACHINE LEARNING AND BLOCKCHAIN-BASED REAL-TIME FACIAL RECOGNITION ATTENDANCE SYSTEM

In a vast majority of fields, the use of facial recognition for authentication is expanding. In this information age, authentication has become vital, and the need for faster and more secure methods of user authentication has been on the rise. The introduction of image processing technologies such as OpenCV has increased society’s reliance on face recognition. Using blockchain, information could be stored in blocks throughout the blockchain network. Blockchain is an extremely secure means for storing and protecting data from intruders. It is a highly disruptive technology that has the ability to alter every plane of society. This paper intends to implement opensource computer vision (OpenCV) to construct a facial detection model that will be employed in a blockchain-secured Attendance Monitoring System. It will not only automate the attendance procedure but also give the system unassailable security. This system will take a live video feed from a camera using OpenCV and identify the faces of students and record their attendance along with the entry time. The data will be kept in a distributed way over the blockchain network that will be accessible to everyone, but data cannot be manipulated.

Improvement of Machine Vision Video Signal Processing Algorithm for Higher Accuracy in Extended Object Speed Measurements

Machine vision systems are widely used for monitoring of the railway infrastructure condition. High reliability of machine vision systems allows using them not only for video recording but also for automation of technological processes. One of the important tasks in the process automation is measurement of an extended object speed (rail-road cars, electric locomotives and rolling stock). Some systems have a requirement to estimate speed in real time (braking of cars at a shunting yard). In this case the speed is calculated by two adjacent frames to ensure the minimum delay for measurement. However, the image of an extended object can be uninformative (image fragments are uniform in brightness), the weather can cause interference. It leads to high speed estimation error. This article describes the improvement for the existing real-time algorithm which allows for higher accuracy in speed measurements. The improvement implies selection of an informative image area corresponding to an extended object. A comparative analysis of the existing and improved algorithm showed a significant reduction in the estimation error in speed measurements.

Validating the Use of Smart Glasses in Industrial Quality Control: A Case Study

Effective quality control is crucial in industrial manufacturing for influencing efficiency, product dependability, and customer contentment. In the constantly changing landscape of industrial production, conventional inspection methods may fall short, prompting the need for inventive approaches to enhance precision and productivity. In this study, we investigate the application of smart glasses for real-time quality inspection during assembly processes. Our key innovation involves combining smart glasses’ video feed with a server-based image recognition system, utilizing the advanced YOLOv8 model for accurate object detection. This integration seamlessly merges mixed reality (MR) with cutting-edge computer vision algorithms, offering immediate visual feedback and significantly enhancing defect detection in terms of both speed and accuracy. Carried out in a controlled environment, our research provides a thorough evaluation of the system’s functionality and identifies potential improvements. The findings highlight that MR significantly elevates the efficiency and reliability of traditional inspection methods. The synergy of MR and computer vision opens doors for future advancements in industrial quality control, paving the way for more streamlined and dependable manufacturing ecosystems.

Frequency-Multiplexing Transmission of Video and Wireless Signals Utilizing FM Conversion Method

Frequency-Multiplexing Transmission of Video and Wireless Signals Utilizing FM Conversion Method

МЕТОД ИТЕРАЦИОННОГО СОВМЕЩЕНИЯ ТЕЛЕВИЗИОННЫХ СИГНАЛОВ В ИЗМЕРИТЕЛЬНЫХ СИСТЕМАХ ТЕХНИЧЕСКОГО ЗРЕНИЯ

Measuring systems of machine vision have become widely used in solving technical problems. The operating conditions of such machine vision systems are very aggressive: precipitation, dirt, dust, a wide temperature range, etc. Despite the equipment is work, measuring systems lose the data in such conditions. Data loss leads to measurement distortions and an increase in the probability of false positive of the object detection. Such situations are an urgent problem for organizations operating measurement systems of machine vision. The repeating measurements are necessary for restoring the data. But it leads to waste the time, labor and financial costs. In some cases, data loss poses a potential threat to the safety of people's lives and equipment. Various types of measuring systems of machine vision generate various television signals: one-dimensional signals, profiles and images. A method has been developed that allows superposition different types of television signals of machine vision measuring systems for data recovery. The tests have shown that method makes improving the reliability of the measurements.

FAVER: Blind quality prediction of variable frame rate videos

Video quality assessment (VQA) remains an important and challenging problem that affects many applications at the widest scales. Recent advances in mobile devices and cloud computing techniques have made it possible to capture, process, and share high resolution, high frame rate (HFR) videos across the Internet nearly instantaneously. Being able to monitor and control the quality of these streamed videos can enable the delivery of more enjoyable content and perceptually optimized rate control. Accordingly, there is a pressing need to develop VQA models that can be deployed at enormous scales. While some recent effects have been applied to full-reference (FR) analysis of variable frame rate and HFR video quality, the development of no-reference (NR) VQA algorithms targeting frame rate variations has been little studied. Here, we propose a first-of-a-kind blind VQA model for evaluating HFR videos, which we dub the Framerate-Aware Video Evaluator w/o Reference (FAVER). FAVER uses extended models of spatial natural scene statistics that encompass space–time wavelet-decomposed video signals, and leverages the advantages of the deep neural network to provide motion perception, to conduct efficient frame rate sensitive quality prediction. Our extensive experiments on several HFR video quality datasets show that FAVER outperforms other blind VQA algorithms at a reasonable computational cost. To facilitate reproducible research and public evaluation, an implementation of FAVER is being made freely available online: https://github.com/uniqzheng/HFR-BVQA.

Education Source Ultimate

Education Source Ultimate is one of many databases offered by EBSCO. It offers access to hundreds of videos and thousands of journals and magazines on education studies, many of them full text, peer reviewed, and/or open access. These different print and media resources address numerous educational topics, including research methodology, training, assessment, literacy, technology, and ethics, among many others. This database can be viewed in any of 31 different Asian and European languages. It offers both documents and videos, often on point for the query submitted, using a standard Advanced Search mechanism that is both usable and understandable. Pricing for this resource is determined by various factors, including full-time enrollment (FTE), consortium agreements, other EBSCO databases subscribed to, royalty requirements, and buying groups—all of which imply considerable variability in subscription price. The licensing agreement for this database, the standard one for all EBSCO resources, is 16 pages long and can be very detailed and technical. As such, it may not be easily understood by subscribers without the assistance of legal and/or information technology specialists. The quality and quantity of the content in this database are impressive and will certainly prove valuable to many researchers in education studies. Consequently, its primary audience will be colleges and universities, specifically those with education programs. It will be of only marginal use to others.

Wavelet analysis-based techniques for processing voice and video signals in network communications

Wavelet analysis-based techniques for processing voice and video signals in network communications

A Multimodal Driver Emotion Recognition Algorithm Based on the Audio and Video Signals in Internet of Vehicles Platform

A Multimodal Driver Emotion Recognition Algorithm Based on the Audio and Video Signals in Internet of Vehicles Platform

Omnidirectional Video Super-Resolution Using Deep Learning

Omnidirectional Videos (or 360° videos) are widely used in Virtual Reality (VR) to facilitate immersive and interactive viewing experiences. However, the limited spatial resolution in 360° videos does not allow for each degree of view to be represented with adequate pixels, limiting the visual quality offered in the immersive experience. Deep learning Video Super-Resolution (VSR) techniques used for conventional videos could provide a promising software-based solution; however, these techniques do not tackle the distortion present in equirectangular projections of 360° video signals. An additional obstacle is the limited 360° video datasets to study. To address these issues, this paper creates a novel 360° Video Dataset (360VDS) with a study of the extensibility of conventional VSR models to 360° videos. This paper further proposes a novel deep learning model for 360° Video Super-Resolution (360° VSR), called Spherical Signal Super-resolution with a Proportioned Optimisation (S3PO). S3PO adopts recurrent modelling with an attention mechanism, unbound from conventional VSR techniques like alignment. With a purpose-built feature extractor and a novel loss-function addressing spherical distortion, S3PO outperforms most state-of-the-art conventional VSR models and 360° specific super-resolution models on 360° video datasets. A step-wise ablation study is presented to understand and demonstrate the impact of the chosen architectural sub-components, targeted training and optimisation.

Traffic Surveillance Using Computer Vision and Deep Learning Methods

From the early 21st century to the present date, Traffic surveillance has been one of the most challenging problems and over the years many solutions were proposed for tackling this problem. However, flaws are can still be noticed in the currently existing systems for performing this task and some of them will be further addressed in this work. In our project Traffic Surveillance using Computer Vision and Deep Learning, we propose a smart vision-based system which accurately provides live traffic statistics like the speed of the traffic and the count of Vehicles passed on a road in between a time interval. The system takes a video feed as an input, which could be live footage provided by a CCTV camera at a traffic junction, and on querying starting and ending timestamps, it outputs the count of the vehicles and speed of the traffic in between the queried timestamps. We divide this problem into two major sub-problems, firstly detecting a vehicle, followed by tracking the detected vehicle. Although there exist many algorithms for detecting objects as well as for tracking objects, one of the major problems is integrating both. As ambiguities like detecting an already detected vehicle, many occur while tracking the vehicles. In our work, we emphasize handling such ambiguities using Deep Learning and we also provide a comparative performance analysis of our system with the already existing ones.

Real-Time Sign Language Fingerspelling Recognition using Convolutional Neural Network

: Sign language allows mute people to communicate, problem occurs when a conversationalist fails to understand it. Despite efforts to address this problem, an effective solution is not yet found. In this work, Convolutional Neural Network (CNN) was trained on two different datasets separately- binary and Red Blue Green )RGB(, each contains 25,900 images of Nigerian Sign Language. A deep neural pre-trained module was used to detect hand gestures in the video feed which tackled the issue of complex backgrounds, also showed excellent detection in dimly lit areas. The accuracies of (98.95%, 76%) and (98.87%, 98.85%) were obtained respectively on the training and the validation sets. The real time system developed implemented both models as a single system which makes it a unique one.

Real-Time Sign Language Fingerspelling Recognition using Convolutional Neural Network

Sign Language allows mute people to communicate, problem occurs when a conversationalist fails to understand it. Despite efforts to address this problem, an effective solution is not yet found. In this work, Convolutional Neural Network was trained on two different datasets separately- Binary and Red Blue Green )RGB(, each contains 25,900 images of Nigerian Sign Language. A Deep Neural pre-trained module was used to detect hand gestures in the video feed which tackled the issue of complex backgrounds, also showed excellent detection in dimly lit areas. The accuracies of (98.95%, 76%) and (98.87%, 98.85%) were obtained respectively on the training and the validation sets. The real time system developed implemented both models as a single system which makes it a unique one.

How to Improve Immersive Experience?

With the explosive growth of online multi-modal applications that typically include audio, video, and haptic signals, immersive experience (IE) improvement has been broadly regarded as one of the most important tasks. Compared with traditional quality of experience (QoE) improvement for online audio/video applications, it highlights two sequential technical challenges to be resolved: i) much more stringent demand of real-time improvement due to the incorporation of delay-sensitive haptic signals, and ii) high-dimensional instead of existing one-dimensional (<i>i.e.,</i> network-level) paradigm for better online improvement. To get over this dilemma, this work systematically addresses the following three fundamental problems: i) which factors influence IE, ii) how to online improve IE, and iii) to what extent of the corresponding IE improvement can be achieved. To this end, we first comprehensively explore and categorize the influence factors on IE from various dimensions. Then, by combing network resource scheduling with the multi-domain collaboration of user profile, device specification, and application type, an online IE improvement strategy is proposed based on the efficient linear contextual bandit with the <inline-formula><tex-math notation="LaTeX">$L_{1}$</tex-math></inline-formula>-norm estimation. Finally, we derive the theoretical bound of IE improvement, scaling at a poly-logarithmical function of data dimension. Numerical results on the practical system also demonstrate the remarkable improvement on IE.

Edge AI Enabled IoT Framework for Secure Smart Home Infrastructure

The synergy of Edge Computing, Artificial Intelligence, and Internet of Things in smart city camera-based surveillance offers notable advantages in resource allocation. Traditional approaches involving constant video data streaming to central servers incur significant bandwidth and storage costs. Our contribution involves proposing a cost-effective, lightweight Edge AI Enabled IoT Framework for Secure Smart Home Infrastructure, utilising a Raspberry Pi single-board computer and the open-source software motion for camera surveillance. The motion program monitors video signals from various cameras and triggers specific actions upon detecting movement. The framework efficiently notifies the smart home owner via email and smartphone message when motion is detected. We integrated four advanced motion detection and alert notification methodologies, conducting a thorough evaluation that positioned our framework as superior to existing solutions. Our research showcases impressive accuracy rates of 91% and 85% in indoor and outdoor scenarios, with minimal average delays of 12.8 seconds for email alerts and 1.6 seconds for messages which is approximately 41.6 % less than the state of the art methodologies. This innovative integration not only elevates surveillance capabilities but also establishes a swift and reliable alert system, contributing significantly to the efficiency and security of smart home environments.

Real-Time Implementation of a Cognitive Radio Node for Video Transmission with Dynamic Channel Selection

This paper endeavors to exploit the extent to which the radio spectrum can be utilized by almagating and enhancing various methods proposed by previous researchers in the field. Cognitive radio research addresses the challenge of spectrum scarcity and underutilization through cognitive radio technology. The realm of cognitive radio research encompasses diverse aspects of its architecture, ranging from spectrum sensing to higher-level strategies. Notably, the navigation strategy employed by cognitive radios constitutes a pivotal layer in these implementations. Thus, this paper focuses on the real-time implementation of a cognitive radio node in a spectrum of licensed users. Leveraging the capabilities of software-defined radios, GNU Radio, GStreamer and Ubuntu OS computers, this investigation introduces a streamlined channel strategy. This strategy uses both short-term and long-term historical data, along with a buffering mechanism, to facilitate the real-time transmission of a high-definition video signal. The successful implementation of this system yields a promising enhancement of approximately 32% in radio resource utilization. Furthermore, the sensing time of the cognitive radio experiences a significant reduction. This research contributes to the advancement of cognitive radio technology and demonstrates the consolidated strategies' practical implications, underscoring their potential to overcome spectrum-related challenges.

Substantiation of the technical characteristics of laser systems for transmitting information in the hydrosphere in the optical range

The exchange of information between correspondents in the optical range in the hydrosphere is an urgent and breakthrough direction of scientific and technological progress. Important tasks in this method of data transmission are the protection of the transmitted information, as well as ensuring sufficient data transfer speed when exchanging television im- ages. This article provides an explanation and calculation of the technical characteristics of laser systems for transmitting information in the optical range, with the help of which it is possible to transmit a digital television signal via a laser beam in the hydrosphere.