Chapter Identifying Hazards in Construction Sites Using Deep Learning-Based Multimodal with CCTV Data

The use of closed-circuit television (CCTV) for safety monitoring is crucial for reducing accidents in construction sites. However, the majority of currently proposed approaches utilize single detection models without considering the context of CCTV video inputs. In this study, a multimodal detectio...

Descrizione completa

Salvato in:
Dettagli Bibliografici
Autori principali: Son, Seongwoo, Quoc Tran, Dai, Jeon, Yuntae, Park, Minsoo, Park, Seunghee
Natura: Online
Lingua:inglese
Pubblicazione: Firenze University Press 2024
Soggetti:
Accesso online:ONIX_20240402_9791221502893_40
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1869527257782943744
author Son, Seongwoo
Quoc Tran, Dai
Jeon, Yuntae
Park, Minsoo
Park, Seunghee
author_browse Jeon, Yuntae
Park, Minsoo
Park, Seunghee
Quoc Tran, Dai
Son, Seongwoo
author_facet Son, Seongwoo
Quoc Tran, Dai
Jeon, Yuntae
Park, Minsoo
Park, Seunghee
author_sort Son, Seongwoo
collection Directory of Open Access Books
description The use of closed-circuit television (CCTV) for safety monitoring is crucial for reducing accidents in construction sites. However, the majority of currently proposed approaches utilize single detection models without considering the context of CCTV video inputs. In this study, a multimodal detection, and depth map estimation algorithm utilizing deep learning is proposed. In addition, the point cloud of the test site is acquired using a terrestrial laser scanning scanner, and the detected object's coordinates are projected into global coordinates using a homography matrix. Consequently, the effectiveness of the proposed monitoring system is enhanced by the visualization of the entire monitored scene. In addition, to validate our proposed method, a synthetic dataset of construction site accidents is simulated with Twinmotion. These scenarios are then evaluated with the proposed method to determine its precision and speed of inference. Lastly, the actual construction site, equipped with multiple CCTV cameras, is utilized for system deployment and visualization. As a result, the proposed method demonstrated its robustness in detecting potential hazards on a construction site, as well as its real-time detection speed
format Online
id doab-20.500.12854ir-136950
institution Directory of Open Access Books
language eng
publishDate 2024
publishDateRange 2024
publishDateSort 2024
publisher Firenze University Press
publisherStr Firenze University Press
record_format ojs
spelling doab-20.500.12854ir-1369502024-05-10T22:40:57Z Chapter Identifying Hazards in Construction Sites Using Deep Learning-Based Multimodal with CCTV Data Son, Seongwoo Quoc Tran, Dai Jeon, Yuntae Park, Minsoo Park, Seunghee deep learning multimodal multiCCTV synthetic data pointcloud thema EDItEUR::U Computing and Information Technology The use of closed-circuit television (CCTV) for safety monitoring is crucial for reducing accidents in construction sites. However, the majority of currently proposed approaches utilize single detection models without considering the context of CCTV video inputs. In this study, a multimodal detection, and depth map estimation algorithm utilizing deep learning is proposed. In addition, the point cloud of the test site is acquired using a terrestrial laser scanning scanner, and the detected object's coordinates are projected into global coordinates using a homography matrix. Consequently, the effectiveness of the proposed monitoring system is enhanced by the visualization of the entire monitored scene. In addition, to validate our proposed method, a synthetic dataset of construction site accidents is simulated with Twinmotion. These scenarios are then evaluated with the proposed method to determine its precision and speed of inference. Lastly, the actual construction site, equipped with multiple CCTV cameras, is utilized for system deployment and visualization. As a result, the proposed method demonstrated its robustness in detecting potential hazards on a construction site, as well as its real-time detection speed 2024-05-10T22:40:55Z 2024-05-10T22:40:55Z 2024-04-02T15:45:38Z 2023 chapter ONIX_20240402_9791221502893_40 2704-5846 https://library.oapen.org/handle/20.500.12657/89071 9791221502893 https://directory.doabooks.org/handle/20.500.12854/136950 eng Proceedings e report open access image/jpeg n/a https://library.oapen.org/bitstream/20.500.12657/89071/1/9791221502893_61.pdf Firenze University Press 10.36253/979-12-215-0289-3.61 10.36253/979-12-215-0289-3.61 2ec4474d-93b1-4cfa-b313-9c6019b51b1a 9791221502893 9 Florence open access
spellingShingle deep learning
multimodal
multiCCTV
synthetic data
pointcloud
thema EDItEUR::U Computing and Information Technology
Son, Seongwoo
Quoc Tran, Dai
Jeon, Yuntae
Park, Minsoo
Park, Seunghee
Chapter Identifying Hazards in Construction Sites Using Deep Learning-Based Multimodal with CCTV Data
title Chapter Identifying Hazards in Construction Sites Using Deep Learning-Based Multimodal with CCTV Data
title_full Chapter Identifying Hazards in Construction Sites Using Deep Learning-Based Multimodal with CCTV Data
title_fullStr Chapter Identifying Hazards in Construction Sites Using Deep Learning-Based Multimodal with CCTV Data
title_full_unstemmed Chapter Identifying Hazards in Construction Sites Using Deep Learning-Based Multimodal with CCTV Data
title_short Chapter Identifying Hazards in Construction Sites Using Deep Learning-Based Multimodal with CCTV Data
title_sort chapter identifying hazards in construction sites using deep learning based multimodal with cctv data
topic deep learning
multimodal
multiCCTV
synthetic data
pointcloud
thema EDItEUR::U Computing and Information Technology
topic_facet deep learning
multimodal
multiCCTV
synthetic data
pointcloud
thema EDItEUR::U Computing and Information Technology
url ONIX_20240402_9791221502893_40
work_keys_str_mv AT sonseongwoo chapteridentifyinghazardsinconstructionsitesusingdeeplearningbasedmultimodalwithcctvdata
AT quoctrandai chapteridentifyinghazardsinconstructionsitesusingdeeplearningbasedmultimodalwithcctvdata
AT jeonyuntae chapteridentifyinghazardsinconstructionsitesusingdeeplearningbasedmultimodalwithcctvdata
AT parkminsoo chapteridentifyinghazardsinconstructionsitesusingdeeplearningbasedmultimodalwithcctvdata
AT parkseunghee chapteridentifyinghazardsinconstructionsitesusingdeeplearningbasedmultimodalwithcctvdata