MIdentification System of Personal Protective Equipment Using Convolutional Neural Network (CNN) Method

Pradana, Rifki Dita Wahyu; Wahidin, Aang; Ruddianto,; Budianto, Agus; Rochiem, Nasyith Hananur; Sholahuddin,; Adhitya, Ryan Yudha; Syai’in, Mat; Sudibyo, Rafidan Maulana; Abiyoga, Dio Rizky Ardhya; Jami'in, Mohammad Abu; Subiyanto, Lilik; Herijono, Budi

doi:10.1109/isesd.2019.8909629

Cited by 9 publications

(3 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wu et al [ 19 ] adopted K-Nearest Neighbors (KNN) to capture moving objects from videos, which were then input into CNN models for classification of the pedestrian, head, and helmet. Similarly, Pradana et al [ 20 ] used a CNN-based model to classify twelve situations, which were the combination of five PPE, such as glasses and helmet. However, the experiments only tested the images with a pure-color indoor background (not real construction sites), which might limit further deployment in outdoor environment.…”

Section: Introductionmentioning

confidence: 99%

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

Wang

Yang

et al. 2021

Sensors

103

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 99%

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

Wang

Yang

et al. 2021

Sensors

103

View full text Add to dashboard Cite

show abstract

“…1) Gate-based Check: Gate-based systems located in strategic points exploit RFID tags on the PPE to either control the presence of the PPE itself when entering dangerous areas [47]- [50], [53], [54], or to identify the worker while a camera checks for the PPE compliance through images processing [51], [52].…”

Section: B Appropriate Use Of Ppementioning

confidence: 99%

A Survey on Radio Frequency Identification as a Scalable Technology to Face Pandemics

Bianco,

Occhiuzzi,

Panunzio

et al. 2021

Preprint

View full text Add to dashboard Cite

The COVID-19 pandemic forced mankind to unprecedented global challenges, drastically changing our way of living. To minimize life losses, multi-level strategies requiring collective efforts were adopted, while waiting for researchers and Pharma companies to develop vaccines. The management of so complex processes has partly taken benefit from a network vision and from the rising framework of the Internet of Things (IoT). Among the several technologies converging to IoT, the Radiofrequency Identification (RFID), based on backscattering communication, is probably the approach that is most suitable to both the micro (the user) and the macro (the processes) scale. Accordingly, a single infrastructure can support almost all the logistic and monitoring issues related to the war against a pandemic. Based on the earned COVID-19 experience, this paper is a guide about how state-of-the-art RFID systems can be employed in facing future pandemic outbreaks. The three pillars of the contrast are addressed, namely: 1) use and managing of Personal Protective Equipment (PPE), 2) access control and social distancing, and 3) early detection of symptoms. For each class, the envisaged RFID devices and procedures are identified and discussed based on the already available technology and on the state of the art of worldwide research. The presented guide tells us that this technology has a real potentiality to play a key role in generating an extraordinary amount of data, so that complementary paradigms of Edge Computing and Artificial intelligence should be tightly integrated to extract profiles and identify anomalous events, in compliance with privacy and security.

show abstract

“…The literature [3] proposed a PPE detection and door control system. The authors employ a convolutional neural network (CNN) approach trained on images of workers wearing PPE, including Safety Helmets, Safety Glasses, Safety Mask, and Safety Earmuff.…”

Section: Introductionmentioning

confidence: 99%

ACStalk: Design and Implementation of An Access/Entry Control System using an Internet of Things (IoT) Platform

Syuan-You Chen,

Shih-Wen Jiang

2023

Journal of Internet Technology

View full text Add to dashboard Cite

<p>An access/entry control system usually consists of many subsystems. These subsystems have different Application Programming Interfaces (APIs), but they need to be integrated and interacted well. Without a good integrated platform, the communications between subsystems will be very complicated. In addition, except user name and password, Radio Frequency Identification (RFID), and the human’s biometrics (e.g., fingerprint and face) are used to identify users. Wireless Local Area Network (WLAN), mobile communications (e.g. 4G/5G) and Bluetooth are adopted as the remote access technologies. In addition, with the COVID-19 pandemic, public health and personal safety are getting more concerns. People are required to wear personal protective equipment (PPE) in some special areas (e.g., barns and factories) to ensure the personal healthy and food’s safety. To identify the user and detect whether the PPE is correctly worn, this paper proposes an access/entry control system by using an Internet of Things (IoT) platform. Through the proposed IoT system architecture, different identification mechanisms and communication technologies can be adopted, and the messages can be exchanged between two mechanisms. This paper elaborates the architecture design of the IoT platform and discusses the implementation/deployment issues of the PPE detection by using machine learning mechanisms.</p> <p> </p>

show abstract

MIdentification System of Personal Protective Equipment Using Convolutional Neural Network (CNN) Method

Cited by 9 publications

References 6 publications

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

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

A Survey on Radio Frequency Identification as a Scalable Technology to Face Pandemics

ACStalk: Design and Implementation of An Access/Entry Control System using an Internet of Things (IoT) Platform

Contact Info

Product

Resources

About