ABSTRACT
The whole world has been witnessing the gigantic enemy in the form of COVID-19 since March 2020. With its super-fast spread, it has devastated a major part of the world and found to be the most dangerous virus of the 21st Century. All countries went into a lockdown to control the spread of the virus, and the economy dropped down to an all- time low index. The major guideline to avoid the spread of diseases like COVID- 19 at work is avoiding contact with people and their belongings. It is not safe to use computing devices because it may result in the spread of the virus by touching them. This paper presents an Artificial Intelligence- based virtual mouse that detects or recognizes hand gestures to control the various functions of a personal computer. The virtual mouse Algorithm uses a webcam or a built-in camera of the system to capture hand gestures, then uses an algorithm to detect the palm boundaries similar to that of the face detection model of the media pipe face mesh algorithm. After tracing the palm boundaries, it uses a regression model and locates the 21 3D hand-knuckle coordinate points inside the recognized hand/palm boundaries. Once the Hand Landmarks are detected, they are used to call windows Application Programming Interface (API) functions to control the functionalities of the system. The proposed algorithm is tested for volume control and cursor control in a laptop with the Windows operating system and a webcam. The proposedsystem took only 1ms to identify the gestures and control the volume and cursor in real-time. © 2023 IEEE.
ABSTRACT
Since the breakout of Corona Virus Disease 2019 (COVID-19), the global fight against influenza has begun. Various technologies have been developed to support the fast-growing contactless service market, and hence contactless services are rapidly becoming a new growth strategy. In particular, the retail service industry most urgently needs contactless service technology. A representative technical case is the self-checkout machine, which can reduce labor costs and provide customer satisfaction. We present a solution in this article. We propose a hand gesture recognition contactless self-checkout system, which is a hand gesture recognition model based on YOLOv5s. The hand gesture recognition mAP (0.5) value reaches 0.995, the mAP (0.5:0.95) value reaches 0.865, and the F1 score is 0.96, together with the accuracy and recall rate is close to 1. Compared with the excellent algorithm YOLOx-s, the FPS value of YOLOv5s can reach 123 (YOLOx-s is 108). In addition, the model can be used to detect recorded static and dynamic hand gestures in real-time. Practical results show that the YOLOv5s can effectively recognize hand gestures and realize the contactless checkout process.
ABSTRACT
PurposeThe COVID-19 pandemic transformed angel investment meetings from in-person to online. The purpose of this paper is to explore whether this move affected angel investors' perception of subjective behavioral cues in pitch sessions within a large Brazilian angel group.Design/methodology/approachThis study followed an exploratory approach using a triangulation process that combined observation, documents and interviews. Data collected by observation, document studies, and interviews were themed, coded, and organized during the research.FindingsThe move from in-person to online pitches did not seem to affect levels of trustworthiness or arrogance as angels assessed more message content during Q&A sessions. Body movement, gestures and "eye gaze” (i.e. the look on a presenter's face) played a central role in passion assessment during in-person meetings. Body language was highly limited during online sessions and tone of voice became the main source of passion assessment.Research limitations/implicationsThe findings of this study suggest that pitches at online meetings affect angel investors' perception of founders' subjective cues, particularly cues pertaining to passion. Entrepreneurs should be trained to convey passion with tone of voice and to improve their body language in the context of webcam use. The interviews with volunteer sampling were subject to volunteer bias. Additionally, the findings may be affected by cultural context.Practical implicationsA practical contribution of this study is to highlight the need for entrepreneurs to be trained for online pitches. In an online setting, body language is limited, but it is still possible to use one's hands and tone of voice to connect better to investors.Originality/valueThis study is unique because it captures the transition of angel investment meetings from in-person affairs before the pandemic to online meetings during the pandemic crisis. These unique circumstances provided a real-world laboratory to observe founders' subjective cue effects on angel investment decision-making.
ABSTRACT
In April 2020, by the start of isolation all around the world to counter the spread of COVID-19, an increase in violence against women and kids has been observed such that it has been named The Shadow Pandemic. To fight against this phenomenon, a Canadian foundation proposed the "Signal for Help” gesture to help people in danger to alert others of being in danger, discreetly. Soon, this gesture became famous among people all around the world, and even after COVID-19 isolation, it has been used in public places to alert them of being in danger and abused. However, the problem is that the signal works if people recognize it and know what it means. To address this challenge, we present a workflow for real-time detection of "Signal for Help” based on two lightweight CNN architectures, dedicated to hand palm detection and hand gesture classification, respectively. Moreover, due to the lack of a "Signal for Help” dataset, we create the first video dataset representing the "Signal for Help” hand gesture for detection and classification applications which includes 200 videos. While the hand-detection task is based on a pre-trained network, the classifying network is trained using the publicly available Jesture dataset, including 27 classes, and fine-tuned with the "Signal for Help” dataset through transfer learning. The proposed platform shows an accuracy of 91.25% with a video processing capability of 16 fps executed on a machine with an Intel i9-9900K@3.6 GHz CPU, 31.2 GB memory, and NVIDIA GeForce RTX 2080 Ti GPU, while it reaches 6 fps when running on Jetson Nano NVIDIA developer kit as an embedded platform. The high performance and small model size of the proposed approach ensure great suitability for resource-limited devices and embedded applications which has been confirmed by implementing the developed framework on the Jetson Nano Developer Kit. A comparison between the developed framework and the state-of-the-art hand detection and classification models shows a negligible reduction in the validation accuracy, around 3%, while the proposed model required 4 times fewer resources for implementation, and inference has a speedup of about 50% on Jetson Nano platform, which make it highly suitable for embedded systems. The developed platform as well as the created dataset are publicly available. © 2022
ABSTRACT
A User Interface is a form of establishing a platform in which a human interacts with machines. There have been different types of user interfaces evolving over the period in line with the rapid growth of technology. Some of the most popular input devices used are mice, keyboards, touchscreens and styluses. A graphical interface is user friendly and, as a result, is widely used. Systems of contactless communication surfaces for interactions have been introduced to decrease the spread of germs and combat diseases like covid-19. This system also can be utilized by disabled people who still retain motor function in the hand and forearm. This paper put forward an AI-assisted virtual mouse system where these drawbacks are solved by utilizing a webcam/built-in camera for recording the motions of the hand and translating them into mouse actions via ML algorithms. The mouse actions are performed based on hand gestures, which are used to control the computer virtually. The hand detection algorithm is based on a deep learning model. So, the proposed system can reduce the spread of germs and help a computer be more accessible to people with special needs. © 2022 IEEE.
ABSTRACT
An increasing number of companies move to a touchless user interface, partly because of the pandemic's impact and the restricted rules of using public access objects. The market for Zero User Interface is increasing and industrial implementations are growing and promising. Currently, the knowledge of keeping yourself healthy and clean is essential to prevent the spread of Covid-19 disease. A proposed project - a hand gesture-controlled application to properly guide the user through the handwashing process can increase the overall level of hygiene in public. The solution is realized with a transfer learning method based on EfficientNet Lite models making it possible to run on Android, iOS, embedded Linux devices, and microcontrollers. © 2022 IEEE.
ABSTRACT
Due to the current labor shortage situation, combined with the spread of COVID-19, the researchers came up with the idea of developing a contactless remote robotic arm system based on IoT. This research focuses on developing prototypes of remote control three-axis robotic arm via the Internet that can be applied in industrial, medical, and other applications. Abiding by the new normal situation, the Kinect sensor control input, a device capable of receiving commands from human gestures without touching, is used to alleviate the spread of the virus. From the development and experiment, it can be shown that the developed artifact can receive commands from human gestures to remotely control the robotic arm via the Internet in accordance with the intended purpose. © 2021 IEEE.
ABSTRACT
In the current critical situation of novel coronavirus, the use of contactless gesture recognition method can reduce human contact and decrease the probability of virus transmission. In this context, ultrasound-based sensing has been widely concerned for its slow propagation speed, low sampling rate, and easy access to devices. However, limited by the complexity of gestural movements and insufficient training data, the accuracy and robustness of gesture recognition are low. To solve this problem, we propose UltrasonicG, a system for highly robust gesture recognition on ultrasonic devices. The system first converts a single audio signal into a Doppler shift and subsequently extracts the feature values using the Residual Neural Network (ResNet34) and uses Bi-directional Long Short-Term Memory (Bi-LSTM) for gesture recognition. The method effectively improves the accuracy of gesture recognition by combining the information of feature dimension with time dimension. To overcome the challenge of insufficient dataset, we use data extension to expand the dataset. We have conducted extensive experiments and evaluations on UltrasonicG in a variety of real scenarios. The experimental results show that UltrasonicG can recognize 15 kinds of gestures with a recognition distance of 0.5 m. And it has a high accuracy and robustness with a comprehensive recognition rate of 98.8% under different environments and influencing factors. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
ABSTRACT
The aim of this research was to understand the teacher' s perceptions of his didactic gestures on Emergency Remote Teaching (ERT). The study was classified as an exploratory and cross-sectional type, and data were collected through an online questionnaire (using a Likert scale), with statements to be judged by 108 Higher Education professors of a University at ABC of Sao Paulo. The data were analyzed by the Chi-square test (X2). The main findings were that the participants: a) still do not realizes if the students are really learning in this new scenario;b) they value the interaction with students through dialogue and questioning;c) they had to study hard to help students how to learn on ERT;d) they still need to develop the regulation founder gesture, which allows them to diagnose students difficulties and obstacles in relation to stages of the learning process and, from that, to establish goals for the development of capacities. In conclusion, it is necessary to include technologies in teacher training courses, as tools for interaction and pedagogical mediation in order to develop new pedagogical skills in the participating teacher.
ABSTRACT
Online teaching has been encouraged for many years but the COVID-19 pandemic has promoted it to an even greater extent. Teachers had to quickly shift to online teaching methods and processes and conduct all the classroom activities online. The global pandemic has accelerated the transition from chalk and board learning to mouse and click - digital learning. Even though there are online whiteboards available for teaching, teachers often find it difficult to draw using a mouse. A solution for this would be to get an external digital board and stylus but not everyone would be able to afford it. The Hand-Gesture Controlled Presentation Viewer With AI Virtual Painter is a project where one can navigate through the presentation slides and draw anything on them just like how one would on a normal board, just by using their fingers. This project aims to digitalise the traditional blackboard-chalk system and eliminate the need for using a mouse or keyboard while taking classes. Hand-Gesture controlled devices especially laptops and computers have recently gained a lot of attraction. This system works by detecting landmarks on one’s hand to recognise the gestures. The project recognises five hand gestures. It uses a thumb finger for moving to the next slide, a little finger for moving to the previous slide, two fingers for displaying the pointer, one finger for drawing on the screen and three fingers for erasing whatever has been drawn. The infrastructure is provided between the user and the system using only a camera. The camera’s output will be presented on the system’s screen so that the user can further calibrate it. © 2022 University of Stockholm. All rights reserved.
ABSTRACT
Hand hygiene has become even more im-portant in light of the COVID-19 pandemic, where hands are one of the high-risk transmission routes. Existing hand-hygiene education is focused on one-time training and does not ensure that correct handwashing procedures are undertaken. Our study, therefore, proposes a hand-hygiene education and facilitation system. Compared to previous systems, through an external RGB camera with our proposed image preprocessing and use the 3-D convo-lution and convolutional long short-term memory (Con-vLSTM) models to detect correctness of handwashing postures, which also facilitates children's ability to wash their hands properly through an on-screen tutorial. It also encourages children to develop good handwashing habits through a positive competition and reward system, and helps teachers to understand children's learning pro-gresses. The experimental results showed that the model was able to identify handwashing postures in real-time with 95.12% accuracy in a realistic and variable environ-ment. © 2022 IEEE.
ABSTRACT
The increased use of video-mediated communication (VMC) due to the COVID-19 pandemic has led to widespread acceptance of mediated healthcare appointments. Mental health care is one area in which researchers might examine the effects of VMC. Therefore, the current study employed an experiment to test the relative influence of video therapists’ eye contact and gesture on a patient. Each participant was assigned to one of the four possible video conditions using a 2 (Gestures present versus absent) x 2 (Eye contact present versus absent) factorial design. Study participants (n= 359) rated actors portraying themselves as video therapists on items related to impression formation (i.e. likable, warm, understanding). Findings suggest that participants in the eye contact condition reported more positive impressions than in the no eye contact condition. Similarly, participants in the gesture condition reported more positive impressions than in the no gesture condition. However, gestures had a larger effect on impression formation than eye contact, and there was no interaction effect considering the combined impact of gestures and eye contact. These results contribute to understanding how nonverbal cues impact health outcomes in VMC. . [ FROM AUTHOR] Copyright of Counselling Psychology Quarterly is the property of Routledge and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full . (Copyright applies to all s.)
ABSTRACT
All over the world new and fast spreading disease have been affecting human health. This led to degradation of the living being's health immunity, support system, mental and physical stability. So the need of assistance requirement for all bed ridden patients is an increasing demand on daily basis. In our present situation the COVID-19 virus's crisis have caused a drastic change to the world. An enormous number of fields such as destruction of employment, economic losses, pandemic growth, food supplies and etc. have been affected. In this paper, an initiative step towards the replacement of man power supply to take care of COVID-19 patients have been proposed. A flex sensor glove wore by a patient would be able to communicate commands to the nurse or a care taker. The system consists of a 2.2 and 4.5 inches' flex sensors fixed over the right hand of the patient, connected with a microcontroller and wireless transmission unit. A corresponding receiver unit would be placed in the nurse station or to the care taker. The movement of patient's hand is associated to different commands. This reduces the need of the nurse to accompany a patient for 24 hours, in this crisis situation and also supports them with an electronic assistance. This flex controlled assist device have been designed and tested with an accuracy of 82.85%. © 2022 Author(s).
ABSTRACT
This paper presents AcousticPAD, a contactless and robust handwriting recognition system that extends the input and interactions beyond the touchscreen using acoustic signals, thus very useful under the impact of the COVID-19 epidemic. To achieve this, we carefully exploit acoustic pulse signals with high accuracy of time of fight (ToF) measurements. Then we employ trilateration localization method to capture the trajectory of handwriting in air. After that, we incorporate a data augmentation module to enhance the handwriting recognition performance. Finally, we customize a back propagation neural network that leverages augmented image dataset to train a model and recognize the acoustic system generated handwriting characters. We implement AcousticPAD prototype using cheap commodity acoustic sensors, and conduct extensive real environment experiments to evaluate its performance. The results validate the robustness of AcousticPAD, and show that it supports 10 digits and 26 English letters recognition at high accuracies. © 2022, The Author(s).
ABSTRACT
The pandemic caused by COVID-19 was inscribed in our bodies and in our senses. The pandemic represented the reconfiguration of our times, rhythms, processes of subjectivation, socialization, and productivity, even the ways of conceiving the world as the cycles of life and the rituals of death. Although this event is due to biological and epidemiological factors, it has also been established as an operator that has produced discourses, practices, imaginations, and desires, where power flows and organizes new rearrangements in the condition of entropy, social terror, and the pandemic risk. The objective of this article was to analyze the new material and immaterial conditions that were reconfigured in civil society during the pandemic period as coping and resistance mechanisms aimed at safeguarding life in the health emergency condition. The first one delves into the ways in which we reconstitute ourselves as subjects, the relationship and organization of bodies with the habitat, and the emergence of new commercial relationships. In the immaterial dimension, discursive aspects such as discriminatory practices, the generation of new affects and the production of subjectivities are analyzed, such gestures and politicities are oriented to the continuity of the sustainability of life, however, they reveal contradictions, deficiencies, discriminatory processes and distinct types of violence that make up a new aseptic society.Alternate :La pandemia provocada por COVID-19 se inscribió en nuestros cuerpos y en nuestros sentidos. Habitar la pandemia representó la reconfiguración de nuestros tiempos, ritmos, procesos de subjetivación, socialización y productividad, formas de concebir el mundo, así como los ciclos de la vida y los rituales de la muerte. Aunque este acontecimiento se debe en gran parte a factores biológicos y epidemiológicos, también se ha constituido como un operador que ha producido discursos, prácticas, imaginarios y deseos, donde el poder fluye y maquina nuevos reordenamientos a la luz de la entropía, el terror social y el riesgo pandémico. En este artículo se tuvo como objetivo analizar los nuevos condicionamientos materiales e inmateriales que se reconfiguraron en la sociedad civil durante el marco temporal pandémico como mecanismos de afrontamiento y resistencia orientados al resguardo de la vida en la condición de emergencia sanitaria. En la dimensión material se profundiza en las formas en cómo nos reconstituimos como sujetos, la relación y organización de los cuerpos con el hábitat, y la emergencia de nuevas relaciones mercantiles. En la dimensión inmaterial se analizan los aspectos discursivos como las prácticas discriminatorias, la generación de nuevos afectos y la producción de subjetividades. Tales gestos y politicidades están orientados a la continuidad de la sostenibilidad de la vida, sin embargo, desocultan contradicciones, deficiencias, procesos discriminatorios y diversos tipos de violencia que confeccionan una nueva sociedad aséptica.Alternate :A pandemia provocada pela COVID-19 foi inscrita em nossos corpos e em nossos sentidos. Habitar a pandemia representou a reconfiguração de nossos tempos, ritmos, processos de subjetivação, socialização e produtividade, formas de conceber o mundo, assim como os ciclos da vida e os rituais da morte. Embora este evento seja em grande parte devido a fatores biológicos e epidemiológicos, ele também se constituiu como um operador que produziu discursos, práticas, imaginários e desejos, onde a energia flui e maquina novos rearranjos à luz da entropia, do terror social e do risco pandêmico. O objetivo deste artigo era analisar os novos fatores materiais e imateriais condicionantes que foram reconfigurados na sociedade civil durante o período da pandemia como mecanismos de enfrentamento e resistência destinados a salvaguardar a vida na emergência sanitária. Na dimensão material, as formas como nos reconstituímos como sujeitos, a relação e organização dos corpos com o habitat e o surgimento de novas relações mercantis são examinados em profundidade. A dimensão imaterial analisa aspectos discursivos, como práticas discriminatórias, a geração de novos efeitos e a produção de subjetividades. Tais gestos e politizações são orientados para a continuidade da sustentabilidade da vida;contudo, revelam contradições, deficiências, processos discriminatórios e vários tipos de violência que criam uma nova sociedade asséptica.
ABSTRACT
The buddy system, where a pair of divers look out for one another, is used by the diving community to mitigate danger. They inspect each other's breathing apparatus, monitor remaining air supplies, health status, and can provide emergency support during a dive. Due to buddy unavailability however, some divers dive solo, forgoing the safety aspects of the buddy system. We propose a dedicated dive-buddy robot as a solution to this problem. The robot, an autonomous underwater vehicle, could operate as an assistant, controlled by the diver using hand gesture-based communication;a communication method commonly used amongst divers. To capture the gestures, we have developed a smart dive glove integrated with 5 dielectric elastomer strain sensors. The capacitance of each sensor was measured with on-board electronics, translated into a command using machine learning and transmitted underwater using acoustics. Due to travel restrictions relating to the Covid-19 pandemic, a demonstration with the diver and vehicle in the same pool was not possible. Therefore, here we present a demonstration with the diver performing gestures in a pool in Auckland, New Zealand, sending commands to the robot in a pool in Zagreb, Croatia. The commands were sent through acoustics to a computer in Auckland, over cellular internet to a computer in Zagreb, which then relayed instructions to the robot using acoustics. The robot was sent four commands and successfully completed all manoeuvres. The performance of the communication with regards to time delays is assessed and future improvements are discussed. © 2022 SPIE.
ABSTRACT
To avoid the chance of getting covid-19, it's vital not to touch surfaces as well as switches, door knobs and keys that are often employed by people. Hand movements in our world are the foremost well-liked non vocal ways in which of communication that are of agreeable significance. Gesture recognition is associated in Nursing interaction with human computers, normally used for functions of education, medicine and recreation. So, we came upon a contactless switch that works with hand gestures. Today with expanded mechanical progressions, switches also require refreshing with current technology. So, a non-contactless switch that works with sensors is the next step. Our keen contactless switch incorporates a sensor that is equipped for recognizing hand developments and interprets them into orders for controlling lights fans and different home machines. We are using Arduino IDE where we can create a setup function in which we can initialize the sensor and set the pin mode output or the light and fan control. © 2022 IEEE.
ABSTRACT
Hand gesture is a new and promising interface for locomotion in virtual environments. While several previous studies have proposed different hand gestures for virtual locomotion, little is known about their differences in terms of performance and user preference in virtual locomotion tasks. In the present paper, we presented three different hand gesture interfaces and their algorithms for locomotion, which are called the Finger Distance gesture, the Finger Number gesture and the Finger Tapping gesture. These gestures were inspired by previous studies of gesture-based locomotion interfaces and are typical gestures that people are familiar with in their daily lives. Implementing these hand gesture interfaces in the present study enabled us to systematically compare the differences between these gestures. In addition, to compare the usability of these gestures to locomotion interfaces using gamepads, we also designed and implemented a gamepad interface based on the Xbox One controller. We conducted empirical studies to compare these four interfaces through two virtual locomotion tasks. A desktop setup was used instead of sharing a head-mounted display among participants due to the concern of the Covid-19 situation. Through these tasks, we assessed the performance and user preference of these interfaces on speed control and waypoints navigation. Results showed that user preference and performance of the Finger Distance gesture were close to that of the gamepad interface. The Finger Number gesture also had close performance and user preference to that of the Finger Distance gesture. Our study demonstrates that the Finger Distance gesture and the Finger Number gesture are very promising interfaces for virtual locomotion. We also discuss that the Finger Tapping gesture needs further improvements before it can be used for virtual walking.
ABSTRACT
The need for remote usability testing has increased during the ongoing COVID-19 global pandemic. However, lockdown and physical distancing regulations have affected how HCI researchers conduct in-person tests of systems and technologies under design. We present a Pop-Up Observation Kit, which serves as an affordable mobile usability lab. The kit is sent to participants of a study alongside the system they are testing. The Pop-Up Observation Kit provides a simple, unobtrusive form factor that enables the study participant to concentrate on the task itself and not on documenting the task they are performing. While initially developed to observe hand and finger gestures on a pressure sensor mat for the Rich Interactive Materials for everyday objects project, the Pop-up Observation Kit also applies to other use cases. Additionally, the kit is extensible with additional functionalities combined with the sensor mat to enable better data collection or unmoderated remote observations. © 2021 Owner/Author.
ABSTRACT
Domestic violence is a prevalent crime in our society, more so with the introduction of COVID19 restrictions. For the victim, it can be a traumatic experience, so much as to not report the crime. Consequently, the 'Signal for Help' hand gestures were recently introduced as a discrete method to enable the victim to confidently express their need for help. This research investigates the classification of these hand gestures using a deep learning approach, which has not previously been implemented in this context. A deep learning approach is chosen due to the favourable results obtained in different contexts on hand gesture classification. Due to the unavailability of a dataset containing images of these hand gestures, a 'Signal for Help' dataset containing 112 images is generated as part of this study. These images are pre-processed to be of size 50x50 dimensions. Furthermore, a synthetic version of this dataset is also generated from the pre-processed images containing 2,352 images. The aims of this research are to show that using a synthetic 'Signal for Help' dataset improves model performance, and using deep learning is effective in 'Signal for Help' hand gesture classification. The results in this research show that using a synthetic 'Signal for Help' dataset improves model performance and is effective for 'Signal for Help' hand gesture classification. © 2021 IEEE.