Evaluating the effectiveness of training image dataset for computer vision applications in construction

Automation in civil engineering – and more specifically, in the construction industry – has long been regarded as the next phase in its evolution with the times. However, a resistance to harness new technologies has seen the industry fall behind many of its counterparts more willing to embrace the l...

Full description

Saved in:
Bibliographic Details
Main Author: Lee, Shi Yuan
Other Authors: Fu Yuguang
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2024
Subjects:
Online Access:https://hdl.handle.net/10356/177288
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-177288
record_format dspace
spelling sg-ntu-dr.10356-1772882024-05-24T15:34:53Z Evaluating the effectiveness of training image dataset for computer vision applications in construction Lee, Shi Yuan Fu Yuguang School of Civil and Environmental Engineering yuguang.fu@ntu.edu.sg Engineering Civil engineering Computer vision Object detection Automation in civil engineering – and more specifically, in the construction industry – has long been regarded as the next phase in its evolution with the times. However, a resistance to harness new technologies has seen the industry fall behind many of its counterparts more willing to embrace the latest and greatest. One critical aspect of this evolution involves equipping construction site machineries with the ability to understand visual scenes. The identification of human workers is seen as a fundamental step towards achieving the end goal of complete automation. In order to accomplish this, object detection algorithms can be implemented. ​This study aims to compare and identify the best performing object detection model in the context of worker identification in a construction setting. Furthermore, this study also explores the importance and effectiveness of the quantity of training data. In a field where training data is scarce and often found wanting, it is important to evaluate the most optimal training dataset sizes, and consequently investigate the significance and impact of insufficiently large training data sets. Bachelor's degree 2024-05-24T07:16:48Z 2024-05-24T07:16:48Z 2024 Final Year Project (FYP) Lee, S. Y. (2024). Evaluating the effectiveness of training image dataset for computer vision applications in construction. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/177288 https://hdl.handle.net/10356/177288 en CM-01 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
Civil engineering
Computer vision
Object detection
spellingShingle Engineering
Civil engineering
Computer vision
Object detection
Lee, Shi Yuan
Evaluating the effectiveness of training image dataset for computer vision applications in construction
description Automation in civil engineering – and more specifically, in the construction industry – has long been regarded as the next phase in its evolution with the times. However, a resistance to harness new technologies has seen the industry fall behind many of its counterparts more willing to embrace the latest and greatest. One critical aspect of this evolution involves equipping construction site machineries with the ability to understand visual scenes. The identification of human workers is seen as a fundamental step towards achieving the end goal of complete automation. In order to accomplish this, object detection algorithms can be implemented. ​This study aims to compare and identify the best performing object detection model in the context of worker identification in a construction setting. Furthermore, this study also explores the importance and effectiveness of the quantity of training data. In a field where training data is scarce and often found wanting, it is important to evaluate the most optimal training dataset sizes, and consequently investigate the significance and impact of insufficiently large training data sets.
author2 Fu Yuguang
author_facet Fu Yuguang
Lee, Shi Yuan
format Final Year Project
author Lee, Shi Yuan
author_sort Lee, Shi Yuan
title Evaluating the effectiveness of training image dataset for computer vision applications in construction
title_short Evaluating the effectiveness of training image dataset for computer vision applications in construction
title_full Evaluating the effectiveness of training image dataset for computer vision applications in construction
title_fullStr Evaluating the effectiveness of training image dataset for computer vision applications in construction
title_full_unstemmed Evaluating the effectiveness of training image dataset for computer vision applications in construction
title_sort evaluating the effectiveness of training image dataset for computer vision applications in construction
publisher Nanyang Technological University
publishDate 2024
url https://hdl.handle.net/10356/177288
_version_ 1800916171698995200