Visual recognition using artificial intelligence (safety detection in the workplace using artificial intelligence)
Numerous studies have concluded that non-compliance with personal protective equipment (PPE) requirements dramatically affects the workplace’s safety level. Though currently available strategies for detecting compliance of PPE requirements could provide rapid and fast detection of helmets, it lac...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/157365 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-157365 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1573652023-07-07T19:10:43Z Visual recognition using artificial intelligence (safety detection in the workplace using artificial intelligence) Liu, Guang Yuan Yap Kim Hui School of Electrical and Electronic Engineering A*STAR EKHYap@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Numerous studies have concluded that non-compliance with personal protective equipment (PPE) requirements dramatically affects the workplace’s safety level. Though currently available strategies for detecting compliance of PPE requirements could provide rapid and fast detection of helmets, it lacks the capability of detecting other PPE such as vests, gloves, and masks. Furthermore, the lack of dynamic user interfaces further complicates the deployment and application of such techniques. Therefore, the objective of this project is to design a real-time PPE monitoring system that is both efficient and accurate. To achieve this, different you only look once (YOLO) models were tested and benchmarked against one another, and YOLOv5s was selected for its accuracy and detection speed. After selecting the model, multiple experiments such as hyperparameters fine-tuning, model structure modification and data augmentation were performed to increase detection accuracy further. Meanwhile, a novel dataset was constructed containing 3414 high-resolution images with 28,977 instances across 8 different classes. With the new dataset, the trained model obtained a 69.5% mean average precision at 32 frames per second. In addition, a flexible graphical user interface was developed to enable users to customise detection features as well as the camera source. Finally, a geofencing function was also implemented to allow users to customise the precise monitoring areas. Bachelor of Engineering (Electrical and Electronic Engineering) 2022-05-12T05:21:51Z 2022-05-12T05:21:51Z 2022 Final Year Project (FYP) Liu, G. Y. (2022). Visual recognition using artificial intelligence (safety detection in the workplace using artificial intelligence). Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/157365 https://hdl.handle.net/10356/157365 en A3300-211 application/pdf Nanyang Technological University |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence |
spellingShingle |
Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Liu, Guang Yuan Visual recognition using artificial intelligence (safety detection in the workplace using artificial intelligence) |
description |
Numerous studies have concluded that non-compliance with personal protective
equipment (PPE) requirements dramatically affects the workplace’s safety level. Though
currently available strategies for detecting compliance of PPE requirements could provide
rapid and fast detection of helmets, it lacks the capability of detecting other PPE such as
vests, gloves, and masks. Furthermore, the lack of dynamic user interfaces further
complicates the deployment and application of such techniques. Therefore, the objective
of this project is to design a real-time PPE monitoring system that is both efficient and
accurate. To achieve this, different you only look once (YOLO) models were tested and
benchmarked against one another, and YOLOv5s was selected for its accuracy and
detection speed. After selecting the model, multiple experiments such as hyperparameters
fine-tuning, model structure modification and data augmentation were performed to
increase detection accuracy further. Meanwhile, a novel dataset was constructed
containing 3414 high-resolution images with 28,977 instances across 8 different classes.
With the new dataset, the trained model obtained a 69.5% mean average precision at 32
frames per second. In addition, a flexible graphical user interface was developed to enable
users to customise detection features as well as the camera source. Finally, a geofencing
function was also implemented to allow users to customise the precise monitoring areas. |
author2 |
Yap Kim Hui |
author_facet |
Yap Kim Hui Liu, Guang Yuan |
format |
Final Year Project |
author |
Liu, Guang Yuan |
author_sort |
Liu, Guang Yuan |
title |
Visual recognition using artificial intelligence (safety detection in the workplace using artificial intelligence) |
title_short |
Visual recognition using artificial intelligence (safety detection in the workplace using artificial intelligence) |
title_full |
Visual recognition using artificial intelligence (safety detection in the workplace using artificial intelligence) |
title_fullStr |
Visual recognition using artificial intelligence (safety detection in the workplace using artificial intelligence) |
title_full_unstemmed |
Visual recognition using artificial intelligence (safety detection in the workplace using artificial intelligence) |
title_sort |
visual recognition using artificial intelligence (safety detection in the workplace using artificial intelligence) |
publisher |
Nanyang Technological University |
publishDate |
2022 |
url |
https://hdl.handle.net/10356/157365 |
_version_ |
1772827806227496960 |