scholarly journals Detection of Personal Protective Equipment (PPE) Compliance on Construction Site Using Computer Vision Based Deep Learning Techniques

2020 ◽  
Vol 6 ◽  
Author(s):  
Venkata Santosh Kumar Delhi ◽  
R. Sankarlal ◽  
Albert Thomas
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Personal Protective Equipment ◽  
Protective Equipment ◽  
Construction Site ◽  
Learning Techniques

scholarly journals Fast Personal Protective Equipment Detection for Real Construction Sites Using Deep Learning Approaches

Sensors ◽  
2021 ◽  
Vol 21 (10) ◽  
pp. 3478
Author(s):  
Zijian Wang ◽  
Yimin Wu ◽  
Lichao Yang ◽  
Arjun Thirunavukarasu ◽  
Colin Evison ◽  
...  
Keyword(s):  
Deep Learning ◽  
Personal Protective Equipment ◽  
Superior Performance ◽  
Protective Equipment ◽  
Detection Accuracy ◽  
Learning Approaches ◽  
The Novel ◽  
Construction Site ◽  
Construction Sites ◽  
Comparison Result

The existing deep learning-based Personal Protective Equipment (PPE) detectors can only detect limited types of PPE and their performance needs to be improved, particularly for their deployment on real construction sites. This paper introduces an approach to train and evaluate eight deep learning detectors, for real application purposes, based on You Only Look Once (YOLO) architectures for six classes, including helmets with four colours, person, and vest. Meanwhile, a dedicated high-quality dataset, CHV, consisting of 1330 images, is constructed by considering real construction site background, different gestures, varied angles and distances, and multi PPE classes. The comparison result among the eight models shows that YOLO v5x has the best mAP (86.55%), and YOLO v5s has the fastest speed (52 FPS) on GPU. The detection accuracy of helmet classes on blurred faces decreases by 7%, while there is no effect on other person and vest classes. And the proposed detectors trained on the CHV dataset have a superior performance compared to other deep learning approaches on the same datasets. The novel multiclass CHV dataset is open for public use.

A Smart System for Personal Protective Equipment Detection in Industrial Environments Based on Deep Learning

2021 ◽  
Author(s):  
Gionatan Gallo ◽  
Francesco Di Rienzo ◽  
Pietro Ducange ◽  
Vincenzo Ferrari ◽  
Alessandro Tognetti ◽  
...  
Keyword(s):  
Deep Learning ◽  
Personal Protective Equipment ◽  
Protective Equipment ◽  
Smart System ◽  
Industrial Environments

scholarly journals DeepOSN: Bringing deep learning as malicious detection scheme in online social network

2020 ◽  
Vol 9 (1) ◽  
pp. 146
Author(s):  
Putra Wanda ◽  
Marselina Endah Hiswati ◽  
Huang J. Jie
Keyword(s):  
Social Networks ◽  
Computer Vision ◽  
Deep Learning ◽  
Online Social Networks ◽  
Link Prediction ◽  
Online Social Network ◽  
Detection Scheme ◽  
Malicious Activity ◽  
Manual Analysis ◽  
Learning Techniques

Manual analysis for malicious prediction in Online Social Networks (OSN) is time-consuming and costly. With growing users within the environment, it becomes one of the main obstacles. Deep learning is growing algorithm that gains a big success in computer vision problem. Currently, many research communities have proposed deep learning techniques to automate security tasks, including anomalous detection, malicious link prediction, and intrusion detection in OSN. Notably, this article describes how deep learning makes the OSN security technique more intelligent for detecting malicious activity by establishing a classifier model.

scholarly journals Utilization of Personal Protective Equipment and Associated Factors among Building Construction Workers in Addis Ababa, Ethiopia 2019

2019 ◽  
Author(s):  
Meseret Yitayew ◽  
Aklilu Azazeh ◽  
Sofia Kebede ◽  
Addisu Alehegn
Keyword(s):  
Personal Protective Equipment ◽  
Associated Factors ◽  
Occupational Safety ◽  
Safety Management ◽  
Occupational Injuries ◽  
Addis Ababa ◽  
Protective Equipment ◽  
Construction Site ◽  
Cross Sectional Survey ◽  
Cross Sectional

Abstract BackgroundPersonal Protective Equipment (PPE) is a material, device, equipment or clothing which is used or worn by a worker to protect them from exposure or contact with any harmful material or energy which may cause injury, disease or even death. The use of personal protective equipment is a universal legal requirement to protect workers against occupational injuries and illnesses in their workplace. The international labor office estimates that every year there are some 125 million work-related accidents, 220, 000 of them are fatal. This study assessed personal protective equipment utilization and associated factors among building construction workers in Addis Ababa, Ethiopia 2019.MethodsInstitution based cross-sectional survey was conducted on the selected construction sites in April 2019. Data was collected by using pre-tested Amharic questioner from 206 study subjects with a response rate of 100% via face to face interviews. Epi info version 7.1 and SPSS version 25 were used for data cleaning and analysis respectively. Independent variables with P<0.2 were transformed from bivariate to multivariate logistic regression. P<0.05 and was declared as an associated factor.ResultsThis study showed that (38.3%) of construction site workers were used at least one personal protective equipment. Presence of safety training, safety brief before commencing work and the availability of governmental visits were associated factors for utilization of personal protective equipment. Regarding, the type of injuries that occur on a majority of workers were abrasion (35%) and climbing at high was the common cause of injury. ConclusionsPPE utilization and safety measure in construction industries is insignificant and construction site workers are not adapted to take care of themselves as it manifested by low use of PPE. An effort for occupational safety assurance should be put in practice to avoid accidents on building a site with an unconditional commitment to all the projects. Riddance of hazards and deterrence of accidents on-site should be within the proficiency of each site. The client should be involved in safety management coupled with having a great craving for safety.

scholarly journals Underwater Gesture Recognition Using Classical Computer Vision and Deep Learning Techniques

2020 ◽  
Vol 8 (1) ◽  
pp. 9-14
Author(s):  
Mygel Andrei M. Martija ◽  
Jakov Ivan S. Dumbrique ◽  
Prospero C., Jr Naval
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Gesture Recognition ◽  
Learning Techniques ◽  
Classical Computer

scholarly journals ASSESSMENT OF THE AWARENESS AND SAFETY PRACTICES IN MITIGATING HAZARDS OF SILICA DUST EXPOSURE AMONG CONSTRUCTION WORKERS

2021 ◽  
Vol 5 (10) ◽  
Author(s):  
Engr. Jeferd E. Saong ◽  
Abigail L. Babaran ◽  
Glenn Dale A. Balaho
Keyword(s):  
Health Effects ◽  
Personal Protective Equipment ◽  
Construction Workers ◽  
Dust Exposure ◽  
Protective Equipment ◽  
Construction Site ◽  
Construction Sites ◽  
Safety Practices ◽  
Silica Dust ◽  
Mode Of Transmission

Construction sites generate high levels of dust typically from concrete, silica, asbestos, cement, wood, stone, and sand. Workers who are exposed to the said environment are faced with the risk of inhaling particulate materials that might lead to adverse respiratory problems. The lack of publication on the awareness of construction workers on the risk associated with silica dust exposure was the basis of the study. This study assessed the level of awareness of construction workers on the risk associated with silica dust exposure and the safety practices to minimize it. Purposive sampling was used in the selection of 65 respondents from different construction sites located in Baguio City, Philippines. A survey questionnaire containing four point Likert scales were used to determine the level of awareness on the health effects, mode of transmission, and sources of silica dust. The study further assessed the level of safety practices in mitigating the effects of silica dust exposure. The respondents were moderately aware (M=2.52) of the health effects, moderately aware (M=2.69) of the mode of transmission, and moderately aware (M=3.08) of the sources of silica dust. The results further showed that the respondents moderately practiced (M=2.84) activities to mitigate the health effects of silica dust exposure and moderately practiced (M=3.17) the use of personal protective equipment in the construction site. The results suggest that construction workers must be made more aware of the health effects of silica dust exposure and, mitigation activities and utilization of personal protective equipment must be strictly imposed in the construction site.

Sign in / Sign up

Export Citation Format

Share Document