Recognition of Manual Welding Positions from Depth Hole Image Remotely Sensed by RGB-D Camera
The proportion of welding work in total man-hours required for shipbuilding processes has been perceived to be significant, and welding man-hours are greatly affected by working posture. Continuous research has been conducted to identify the posture in welding by utilizing the relationship between m...
Guardado en:
Autores principales: | , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
MDPI AG
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/115d63f4d4114f7987b138ca9b72bb53 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:115d63f4d4114f7987b138ca9b72bb53 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:115d63f4d4114f7987b138ca9b72bb532021-11-11T15:24:32ZRecognition of Manual Welding Positions from Depth Hole Image Remotely Sensed by RGB-D Camera10.3390/app1121104632076-3417https://doaj.org/article/115d63f4d4114f7987b138ca9b72bb532021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/21/10463https://doaj.org/toc/2076-3417The proportion of welding work in total man-hours required for shipbuilding processes has been perceived to be significant, and welding man-hours are greatly affected by working posture. Continuous research has been conducted to identify the posture in welding by utilizing the relationship between man-hours and working posture. However, the results that reflect the effect of the welding posture on man-hours are not available. Although studies on posture recognition based on depth image analysis are being positively reviewed, welding operation has difficulties in image interpretation because an external obstacle caused by arcs exists. Therefore, any obstacle element must be removed in advance. This study proposes a method to acquire work postures using a low-cost RGB-D camera and recognize the welding position through image analysis. It removes obstacles that appear as depth holes in the depth image and restores the removed part to the desired state. The welder’s body joints are extracted, and a convolution neural network is used to determine the corresponding welding position. The restored image showed significantly improved recognition accuracy. The proposed method acquires, analyzes, and automates the recognition of welding positions in real-time. It can be applied to all areas where image interpretation is difficult due to obstacles.Jun-Hyeon KimJong-Ho NamMDPI AGarticleworking posturewelding positionmotion capturedepth holeCNNRGB-DTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10463, p 10463 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
working posture welding position motion capture depth hole CNN RGB-D Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 |
spellingShingle |
working posture welding position motion capture depth hole CNN RGB-D Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Jun-Hyeon Kim Jong-Ho Nam Recognition of Manual Welding Positions from Depth Hole Image Remotely Sensed by RGB-D Camera |
description |
The proportion of welding work in total man-hours required for shipbuilding processes has been perceived to be significant, and welding man-hours are greatly affected by working posture. Continuous research has been conducted to identify the posture in welding by utilizing the relationship between man-hours and working posture. However, the results that reflect the effect of the welding posture on man-hours are not available. Although studies on posture recognition based on depth image analysis are being positively reviewed, welding operation has difficulties in image interpretation because an external obstacle caused by arcs exists. Therefore, any obstacle element must be removed in advance. This study proposes a method to acquire work postures using a low-cost RGB-D camera and recognize the welding position through image analysis. It removes obstacles that appear as depth holes in the depth image and restores the removed part to the desired state. The welder’s body joints are extracted, and a convolution neural network is used to determine the corresponding welding position. The restored image showed significantly improved recognition accuracy. The proposed method acquires, analyzes, and automates the recognition of welding positions in real-time. It can be applied to all areas where image interpretation is difficult due to obstacles. |
format |
article |
author |
Jun-Hyeon Kim Jong-Ho Nam |
author_facet |
Jun-Hyeon Kim Jong-Ho Nam |
author_sort |
Jun-Hyeon Kim |
title |
Recognition of Manual Welding Positions from Depth Hole Image Remotely Sensed by RGB-D Camera |
title_short |
Recognition of Manual Welding Positions from Depth Hole Image Remotely Sensed by RGB-D Camera |
title_full |
Recognition of Manual Welding Positions from Depth Hole Image Remotely Sensed by RGB-D Camera |
title_fullStr |
Recognition of Manual Welding Positions from Depth Hole Image Remotely Sensed by RGB-D Camera |
title_full_unstemmed |
Recognition of Manual Welding Positions from Depth Hole Image Remotely Sensed by RGB-D Camera |
title_sort |
recognition of manual welding positions from depth hole image remotely sensed by rgb-d camera |
publisher |
MDPI AG |
publishDate |
2021 |
url |
https://doaj.org/article/115d63f4d4114f7987b138ca9b72bb53 |
work_keys_str_mv |
AT junhyeonkim recognitionofmanualweldingpositionsfromdepthholeimageremotelysensedbyrgbdcamera AT jonghonam recognitionofmanualweldingpositionsfromdepthholeimageremotelysensedbyrgbdcamera |
_version_ |
1718435351386652672 |