Identifying Image of the Correct Use of Face Mask Using Semantic Segmentation Technique

In recent years, the world is facing Covid-19 pandemic which has spread to more than 200 countries. WHO recommend everyone to always wearing a mask and keeping a distance to reduce transmission since Covid-19 is very susceptible to infection in a crowded area. In fact, many people misuse masks, such as wearing a mask but not covering the nose, and thus, monitoring the correct use of masks on a large-scale area is not easy. A technology implementing a high precision computer vision is needed to help monitoring the correct use of human mask automatically. This paper proposes a deep learning method that performs semantic segmentation and classification tasks to precisely identify the use of human face mask. Since it is rarely done so far, a sufficient dataset for this task is still lacking. Therefore, we also construct a dataset for face mask semantic segmentation task, including the fine-grained annotated ground truth. Based on our experiments, the proposed method that uses U-Net base model provides the best Mean IoU performance, which is 95%, compared to several comparative models. The segmentation output is then forwarded to a classification process, to decide whether it is a correct or an incorrect use of mask, and provides an accuracy rate that reaches 100%. Details of the experimental results are shown both quantitatively and qualitatively in this paper. The current results of this study may inspire the development of a better system in the future. © 2022 IEEE.

Managing 4 (Four) Major Offshore Projects Amid COVID 19 Pandemic - A Case Study from Health & Safety (H&S) and Quarantine Management

For an upstream oil and gas company, avoiding an offshore COVID-19 outbreak while executing four different offshore projects poses a huge challenge, particularly in a country experiencing a daily COVID-19 test positivity rate over 20%. Even minor mismanagement of the quarantine process can lead to an offshore COVID-19 outbreak, with the risk of shutting down campaigns and severely impacting business objectives. The challenge is therefore to avoid an offshore COVID-19 outbreak, ensuring well-being of personnel during the quarantine period and managing quarantine related costs, including COVID-19 test costs. To ensure effective quarantine management, a new approach was created that applied a combination of medical assessments, Health & Safety (H&S) and security measures. Quarantine management was led by a special task force responsible for ensuring the readiness of transportations, rooms, PCR tests, as well as overall compliance to quarantine rules. In compliance with government regulations and WHO recommendations, another complimentary approach was applied that sequestered personnel who tested positive in an isolation room. Effective quarantine management was established with the assistance of the company Business Continuity Management Team (BCMT). The company was able to complete four different major offshore projects with no offshore COVID-19 outbreaks. During these operations, over 1,000 personnel were quarantined and tested with a 5.37% positivity rate at the pre-work quarantine site. Confirmed cases were managed in full compliance with government regulations. The result of this effective quarantine management system, has allowed the company to achieve scorecard performance goals while delivering all four of the major offshore work-scopes, as per the original business plan. This paper discusses quarantine management as part of business continuity management covering medical assessment, H&S and security measures amidst a national COVID-19 pandemic. These programs were applied in an adaptive method-based risk assessment, which based on evidence base approaches, during frequently changing government regulations. Copyright © 2022, Society of Petroleum Engineers.

Face Recognition Concept for Reservation System in Trainer Kit Computer Vision

The COVID-19 pandemic has an impact on changes in human lifestyles, one of the aspects affected is the field of education where students are encouraged to take part in learning activities from home. The teacher also has to come up with a new learning strategy, especially for practicum. One of the solutions is to create a trainer kit that can be accessed remotely. In Universitas Pendidikan Indonesia this solution would be implemented. But along the trials of the trainer kit we've facing trouble to identify who's using the trainer. To verify the student is the one who's using the trainer, we come up with a solution to implement a face recognition system. The system is implemented on a web application integrated with the reservation system. The results of this additional feature can bring more certainty to the learning process. Furthermore, it has proven to distinguish and recognize students' identities by storing their faces as a sample. The local test has shown a significant performance on how this system can work by making 7 out of 10 correct face recognition. © 2021 IEEE.