Path Planning of Follow-up Transport Robot Based on Machine Vision

With the upgrading and innovation of the logistics industry, the requirements for the level of transportation smart technologies continue to increase. The outbreak of the COVID-19 has further promoted the development of unmanned transportation machines. Aimed at the requirements of intelligent following and automatic obstacle avoidance of mobile robots in dynamic and complex environments, this paper uses machine vision to realize the visual perception function, and studies the real-time path planning of robots in complicated environment. And this paper proposes the Dijkstra-ant colony optimization (ACO) fusion algorithm, the environment model is established by the link viewable method, the Dijkstra algorithm plans the initial path. The introduction of immune operators improves the ant colony algorithm to optimize the initial path. Finally, the simulation experiment proves that the fusion algorithm has good reliability in a dynamic environment. © 2022 IEEE.

Modelling Proper and Improper Sitting Posture of Computer Users Using Machine Vision for a Human–Computer Intelligent Interactive System during COVID-19

Featured ApplicationThe study could be used for sitting posture monitoring in a work-from-home setup. This could also be used for rehabilitation purposes of patients who has posture-related problems.Human posture recognition is one of the most challenging tasks due to the variation in human appearance, changes in the background and illumination, additional noise in the frame, and diverse characteristics and amount of data generated. Aside from these, generating a high configuration for recognition of human body parts, occlusion, nearly identical parts of the body, variations of colors due to clothing, and other various factors make this task one of the hardest in computer vision. Therefore, these studies require high-computing devices and machines that could handle the computational load of this task. This study used a small-scale convolutional neural network and a smartphone built-in camera to recognize proper and improper sitting posture in a work-from-home setup. Aside from the recognition of body points, this study also utilized points' distances and angles to help in recognition. Overall, the study was able to develop two objective datasets capturing the left and right side of the participants with the supervision and guidance of licensed physical therapists. The study shows accuracies of 85.18% and 92.07%, and kappas of 0.691 and 0.838, respectively. The system was developed, implemented, and tested in a work-from-home environment.

Teaching Industrial Robot Programming using FANUC ROBOGUIDE and iRVision Software

Industrial automation has become increasingly more prominent in many industries, such as manufacturing, automotive, pharmaceuticals, and food processing industries, as the technology evolves and Industry 4.0 revolution advances. Th demand of automation and personnel with automation skills has ever been increasing since Covid-19 Pandemic. Industrial robots and machine vision inspection are essential systems for manufacturing automation. Industrial robots are capable of performing various tasks like part handling, machine tending, assembly, palletizing, arc welding, or laser cutting with high speeds, repeatability and accuracy. Machine Vision Inspection (MVI) systems are used for part quality inspection, manufacturing and assembly supervision and robot guidance. A MVI system integrated with an industrial robot provides a hand-eye coordination to the robot for flexible material handling and operations. Vision-guided robotics serves as the next-generation research instrument that opens new opportunities to advance the boundaries in science and engineering research. This paper focuses on teaching industrial robot programming to engineering students using an offline virtual robotic simulation software, Fanuc ROBOGUIDE and iRVision software. Using a virtual robot and offline programming with ROBOGUIDE reduces a risk by enabling visualization of the robot operations before an actual installation and operations. The ROBOGUIDE software will provide students with an experience of programming an industrial robot and will enhance the effectiveness of the teaching and learning process. The developed programs can be imported and implemented onto a real robot with a minimum configuration setup. The step by step approach of developing and programming a 2D vision guided material handling cell using ROBOGUIDE has been discussed in the paper such that other educators and students can learn and implement the project with ease. Copyright 2022. © by the International Institute of Informatics and Systemics. All rights reserved.

Experimental Design of Self-Tracking Camera Gimbal Robot Based on OpenCV

The emergence of COVID-19 has reduced the opportunities for offline meetings, making people's work and study more transfer to the internet platform. However, the viewing angle and distance of the camera cannot be considered both. Therefore, machine vision is used to identify and track the presenter, and the camera pan-tilt control function of automatically tracking the presenter is realized. In many tests, the target tracking function works normally and works well. The experimental design involves relatively comprehensive disciplines, with good functional scalability and high practicability. It is an innovative experiment integrating robotics teaching, machine learning practice and embedded systems. © 2022 IEEE.

Fruit-CoV: An efficient vision-based framework for speedy detection and diagnosis of SARS-CoV-2 infections through recorded cough sounds.

COVID-19 is an infectious disease caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). This deadly virus has spread worldwide, leading to a global pandemic since March 2020. A recent variant of SARS-CoV-2 named Delta is intractably contagious and responsible for more than four million deaths globally. Therefore, developing an efficient self-testing service for SARS-CoV-2 at home is vital. In this study, a two-stage vision-based framework, namely Fruit-CoV, is introduced for detecting SARS-CoV-2 infections through recorded cough sounds. Specifically, audio signals are converted into Log-Mel spectrograms, and the EfficientNet-V2 network is used to extract their visual features in the first stage. In the second stage, 14 convolutional layers extracted from the large-scale Pretrained Audio Neural Networks for audio pattern recognition (PANNs) and the Wavegram-Log-Mel-CNN are employed to aggregate feature representations of the Log-Mel spectrograms and the waveform. Finally, the combined features are used to train a binary classifier. In this study, a dataset provided by the AICovidVN 115M Challenge is employed for evaluation. It includes 7,371 recorded cough sounds collected throughout Vietnam, India, and Switzerland. Experimental results indicate that the proposed model achieves an Area Under the Receiver Operating Characteristic Curve (AUC) score of 92.8% and ranks first on the final leaderboard of the AICovidVN 115M Challenge. Our code is publicly available.

Adversarial Autoencoders for Agriculture Yield Forecasting

For sustainable food production. In agriculture, crop yields are increasingly affected by warmer temperatures, and pest infestations caused by climate change have increased agricultural losses. Increasing local production is important to reduce our dependence on imported food and provide a buffer in case of supply disruptions such as those caused by the COVID-19 pandemic. To increase food security, it is important to optimize agricultural yields, despite the high costs associated with factors such as supplemental feeding, pest control measures, or operating costs. We present a Machine Vision method (MV) with Adversarial Autoencoder (AAE) as an approach to crop yield optimization. Predicted leaf area is projected from initial germination to early vegetative stages. Generative machine learning models are analyzed to determine a suitable architecture for crop yield prediction. Images of romaine lettuce grown over time under different conditions (e.g., light intensity) are used as the data set. Preliminary results show that the model created is able to predict an image with sufficient accuracy based on a single condition. With our method, corrective actions can be taken early, and yields recover from initial below-average values. Further work can be done to extend the model to other conditions such as moisture, strength of available sunlight, or soil nutrient content.

Machine Vision Surveillance System - Artificial Intelligence for Covid-19 Norms

This paper presents the design and implementation of the Machine Vision Surveillance System Artificial Intelligence (MaViSS-AI) for Covid-19 Norms using jetson nano. This system is designed to be cost-effective, accurate, efficient, and secure. The proposed system tracks and counts humans for monitoring social distancing and detects face masks using object detection methods. We used YOLO as an object detection method and neural network to detect a person and count them. And for social distancing monitoring the concept of the centroid is based on calculating the distance between pairs of centroids, and thus checking whether there are any violations of the threshold or not. To detect the face mask, a YOLO V4 deep learning model is used as the mask detection algorithm. The system also raises alerts when any suspicious event occurs. Given this alert, security personnel can take relevant actions. This research aims to provide a holistic approach to overcoming the real-time challenges encountered during the monitoring of Covid-19 norms. © 2022 IEEE.

Patients rehabilitation with musculoskeletal sequel from covid-19 using vision artificial in the city of Huancayo

Technology and its applications are here to improve our lives, it is used ever more these days with the pandemic Covid-19. This article is aimed to reduce the attendance to Hospitals and clinics where you would be treated with musculoskeletal muscular treatments in the city of Huancayo. With the help of modern technology it is offered an alternative software with artificial vision in order to monitor most patients in real time. The development of this investigation is set in 5 stages, the first stage talks about a posture recognition with artificial vision with framework mediapipe. The second stage explains the design interface and the mathematics formula which controls a patient development, the third stage describes the integration from the first and the second stage with a treat method. The fourth stage describes de development of a webpage using services to develop and monitor in real time. The last stage describes the process of the software validation having the last usuary with a chart of questions. Finally, the results of validations show the patient acceptation, as so 63.6% of patients who had no difficulties doing the software exercises. As Such a monitoring from the initial stage from the patien is hey factor before starting the therapy. © 2022 IEEE.

Recognition of Freezing of Gait in Parkinson's Disease Based on Machine Vision.

Background: Freezing of gait (FOG) is a common clinical manifestation of Parkinson's disease (PD), mostly occurring in the intermediate and advanced stages. FOG is likely to cause patients to fall, resulting in fractures, disabilities and even death. Currently, the pathogenesis of FOG is unclear, and FOG detection and screening methods have various defects, including subjectivity, inconvenience, and high cost. Due to limited public healthcare and transportation resources during the COVID-19 pandemic, there are greater inconveniences for PD patients who need diagnosis and treatment. Objective: A method was established to automatically recognize FOG in PD patients through videos taken by mobile phone, which is time-saving, labor-saving, and low-cost for daily use, which may overcome the above defects. In the future, PD patients can undergo FOG assessment at any time in the home rather than in the hospital. Methods: In this study, motion features were extracted from timed up and go (TUG) test and the narrow TUG (Narrow) test videos of 50 FOG-PD subjects through a machine learning method; then a motion recognition model to distinguish between walking and turning stages and a model to recognize FOG in these stages were constructed using the XGBoost algorithm. Finally, we combined these three models to form a multi-stage FOG recognition model. Results: We adopted the leave-one-subject-out (LOSO) method to evaluate model performance, and the multi-stage FOG recognition model achieved a sensitivity of 87.5% sensitivity and a specificity of 79.82%. Conclusion: A method to realize remote PD patient FOG recognition based on mobile phone video is presented in this paper. This method is convenient with high recognition accuracy and can be used to rapidly evaluate FOG in the home environment and remotely manage FOG-PD, or screen patients in large-scale communities.

Cov-Net: A computer-aided diagnosis method for recognizing COVID-19 from chest X-ray images via machine vision.

In the context of global pandemic Coronavirus disease 2019 (COVID-19) that threatens life of all human beings, it is of vital importance to achieve early detection of COVID-19 among symptomatic patients. In this paper, a computer aided diagnosis (CAD) model Cov-Net is proposed for accurate recognition of COVID-19 from chest X-ray images via machine vision techniques, which mainly concentrates on powerful and robust feature learning ability. In particular, a modified residual network with asymmetric convolution and attention mechanism embedded is selected as the backbone of feature extractor, after which skip-connected dilated convolution with varying dilation rates is applied to achieve sufficient feature fusion among high-level semantic and low-level detailed information. Experimental results on two public COVID-19 radiography databases have demonstrated the practicality of proposed Cov-Net in accurate COVID-19 recognition with accuracy of 0.9966 and 0.9901, respectively. Furthermore, within same experimental conditions, proposed Cov-Net outperforms other six state-of-the-art computer vision algorithms, which validates the superiority and competitiveness of Cov-Net in building highly discriminative features from the perspective of methodology. Hence, it is deemed that proposed Cov-Net has a good generalization ability so that it can be applied to other CAD scenarios. Consequently, one can conclude that this work has both practical value in providing reliable reference to the radiologist and theoretical significance in developing methods to build robust features with strong presentation ability.

Social distancing detection by using deep neural network

This article helps in presenting a clear view of detecting social distance in order to evaluate the distance covered by the people from each other. It helps in providing alarming notification to the people in making safety during this pandemic period by the use of video feed. The frame of the video clipping is used as an input and is implemented based on the hybrid computer vision. The Deep neural network dependent algorithm named YOLOv3 has been used in alarming the detection of distance between the people. It is used along with the mapping technique known as Inverse Perspective Mapping (IPM) which is one of the tracking mechanisms that helps in monitoring the social distance. It is tested against MS COCO and image data sets that has been obtained from Google. The precision was found to be 97% that helps to design the outlook of the place where the public involvement is too high. It could help in controlling the violations of trespassers who does not obey the rules of social distancing and also servers to be precaution to control the disease prone zones.

Contactless robust 3D palmprint identification using photometric stereo

Palmprints are of considerable interest as a reliable biometric, since they offer significant advantages, such as greater user acceptance than fingerprint or iris recognition. 2D systems can be spoofed by a photograph of a hand;however, 3D avoids this by recovering and analysing 3D textures and profiles. 3D palmprints can also be captured in a contactless manner, which is critical for ensuring hygiene (something that is particularly important in relation to pandemics such as COVID-19), and ease of use. Prior work includes low-resolution (relatively unreliable) 3D analysis of wrinkles, or higher resolution ridge analysis that usually employs a commercial (contact based) palmprint scanner. This gap between low and high-resolution palmprint recognition is bridged here using high-resolution non-contact photometric stereo. A camera and illuminants are synchronised with image capture to recover high-definition 3D texture data from the palm, which are then analysed to extract ridges and wrinkles. This novel low cost approach can tolerate distortions inherent to unconstrained contactless palmprint acquisition. Features are found using discrete Fourier transforms. After alignment to a global ridge pattern, feature correspondences are matched, enabling reliable non-contact palmprint identification. The system was evaluated on a medium-sized database and matching was achieved with 0.1% equal error rate, which shows that the approach can achieve accurate and user-friendly palmprint recognition.

Social Distance Monitoring using AI techniques in AAL environments

The growing global epidemic of coronavirus, as well as the shortage in health care professionals, impose protection measures to be taken by citizens themselves. One of these measures is social distancing. In an autonomous and assisted living environment a set of technologies can offer protection to the tenants by monitoring the individuals’ distance between them. This paper proposes to leverage the social distancing application in Ambient assisted living environments, following the precautions proposed by the experts against Covid-19. The evaluation results were quite impressive and a high accuracy was achieved as the difference between application’s and real world measurements was up to 5%. © 2021 IEEE.

Hybrid Virtual Commissioning of a Robotic Manipulator with Machine Vision Using a Single Controller.

Digital twin (DT) is an emerging key technology that enables sophisticated interaction between physical objects and their virtual replicas, with applications in almost all engineering fields. Although it has recently gained significant attraction in both industry and academia, so far it has no unanimously adopted and established definition. One may therefore come across many definitions of what DT is and how to create it. DT can be designed for an existing process and help us to improve it. Another possible approach is to create the DT for a brand new device. In this case, it can reveal how the system would behave in given conditions or when controlled. One of purposes of a DT is to support the commissioning of devices. So far, recognized and used techniques to make the commissioning more effective are virtual commissioning and hybrid commissioning. In this article, we present a concept of hybrid virtual commissioning. This concept aims to point out the possibility to use real devices already at the stage of virtual commissioning. It is introduced in a practical case study of a robotic manipulator with machine vision controlled with a programmable logic controller in a pick-and-place application. This study presents the benefits that stem from the proposed approach and also details when it is convenient to use it.

An Improved Classification of Chest X-ray Images U sing Adaptive Activation Function

Machine vision techniques particularly convolutional neural networks (CNNs) have attained major breakthrough in medical image analysis and classification because of their ability to learn representative features from the input in a hierarchical manner. A couple of years back performing an effective and accurate CNN based classification was a tremendous challenge due to non-availability of large and good quality chest X-ray image (CXR) database. In this paper, we have presented the experiment based on state of the art deep CNN architectures like AlexNet, Res Net and VGG16. These experiments were conducted based on two types of study, one containing dataset with chest Xray images of subjects who contracted Covid-19, viral pneumonia and no respiratory disorder(normal) mentioned as study II and the other dataset containing only Covid-19 and healthy subjects mentioned as study I. A comparison has been drawn with the proposed architecture and classification results based on standard metrics have been carried out on test dataset. The raw chest Xray (CXR) images were passed to the CNN during the training phase without any prior image processing techniques applied on them. Also, we have proposed a new CNN architecture which incorporates the use of an adaptive activation function and it classified the above mentioned studies(I and II) with an accuracy of 96.89 % and 96.75 % and proved to be better than some of the very deep and much more advanced CNN architectures in terms of number of parameters, training time and the amount of space it occupied. © 2021 IEEE.

Drive Through Robotics: Robotic Automation for Last Mile Distribution of Food and Essentials During Pandemics.

The COVID-19 pandemic unraveled the weak points in the global supply chain for goods. Specifically, people all over the world, including those in the most advanced nations have had to go without medical supplies and personal protective equipment. Scarcity of essentials increases anxiety and uncertainty exacerbating unproductive behaviors like hoarding and price gouging. Left to market forces, such unfair practices are likely to aggravate hardships and increase the loss of lives. Thus, there is a critical need to ensure safe distribution of food and essential supplies to all citizens to sustain them through challenging times. To this end, we propose a simple, affordable and contact-less robotic system for preparing and dispensing food and survival-kits at community scale. The system has provisions to prevent hoarding and price gouging. Design, simulation, and, validation of the system has been completed to ensure readiness for real world implementation. This project is part of an open-source program and detailed designs are available upon request to entities interested in using it to serve their communities.

Deep Convolutional Neural Network-Based Computer-Aided Detection System for COVID-19 Using Multiple Lung Scans: Design and Implementation Study.

BACKGROUND: Owing to the COVID-19 pandemic and the imminent collapse of health care systems following the exhaustion of financial, hospital, and medicinal resources, the World Health Organization changed the alert level of the COVID-19 pandemic from high to very high. Meanwhile, more cost-effective and precise COVID-19 detection methods are being preferred worldwide. OBJECTIVE: Machine vision-based COVID-19 detection methods, especially deep learning as a diagnostic method in the early stages of the pandemic, have been assigned great importance during the pandemic. This study aimed to design a highly efficient computer-aided detection (CAD) system for COVID-19 by using a neural search architecture network (NASNet)-based algorithm. METHODS: NASNet, a state-of-the-art pretrained convolutional neural network for image feature extraction, was adopted to identify patients with COVID-19 in their early stages of the disease. A local data set, comprising 10,153 computed tomography scans of 190 patients with and 59 without COVID-19 was used. RESULTS: After fitting on the training data set, hyperparameter tuning, and topological alterations of the classifier block, the proposed NASNet-based model was evaluated on the test data set and yielded remarkable results. The proposed model's performance achieved a detection sensitivity, specificity, and accuracy of 0.999, 0.986, and 0.996, respectively. CONCLUSIONS: The proposed model achieved acceptable results in the categorization of 2 data classes. Therefore, a CAD system was designed on the basis of this model for COVID-19 detection using multiple lung computed tomography scans. The system differentiated all COVID-19 cases from non-COVID-19 ones without any error in the application phase. Overall, the proposed deep learning-based CAD system can greatly help radiologists detect COVID-19 in its early stages. During the COVID-19 pandemic, the use of a CAD system as a screening tool would accelerate disease detection and prevent the loss of health care resources.