Boosting active contours for weld pool visual tracking in automatic arc welding

Jinchao Liu; Zhun Fan; Søren Ingvor Olsen; Kim Hardam Christensen; Jens Klæstrup Kristensen

doi:10.1109/TASE.2015.2498929

Boosting active contours for weld pool visual tracking in automatic arc welding

Jinchao Liu, Zhun Fan, Søren Ingvor Olsen, Kim Hardam Christensen, Jens Klæstrup Kristensen

Department of Computer Science

16 Citations (Scopus)

87 Downloads (Pure)

Abstract

Detecting the shape of the non-rigid molten metal during welding, so-called weld pool visual sensing, is one of the central tasks for automating arc welding processes. It is challenging due to the strong interference of the high-intensity arc light and spatters as well as the lack of robust approaches to detect and represent the shape of the nonrigid weld pool. We propose a solution using active contours including an prior for the weld pool boundary composition. Also, we apply Adaboost to select a small set of features that captures the relevant information. The proposed method is applied to weld pool tracking and the presented results verified its feasibility.

Original language	English
Journal	IEEE Transactions on Automation Science and Engineering
Volume	14
Issue number	2
Pages (from-to)	1096-1108
Number of pages	13
ISSN	1545-5955
DOIs	https://doi.org/10.1109/TASE.2015.2498929
Publication status	Published - Apr 2017

Keywords

Faculty of Science

Access to Document

10.1109/TASE.2015.2498929

Boosting_Active_Contours_for_Weld_Pool_Visual_Tracking_in_Automatic_Arc_Welding_2017_acceptedAccepted author manuscript, 2.39 MB

Cite this

@article{a78072a5f0704a15abdcc54847468ba6,

title = "Boosting active contours for weld pool visual tracking in automatic arc welding",

abstract = "Detecting the shape of the non-rigid molten metal during welding, so-called weld pool visual sensing, is one of the central tasks for automating arc welding processes. It is challenging due to the strong interference of the high-intensity arc light and spatters as well as the lack of robust approaches to detect and represent the shape of the nonrigid weld pool. We propose a solution using active contours including an prior for the weld pool boundary composition. Also, we apply Adaboost to select a small set of features that captures the relevant information. The proposed method is applied to weld pool tracking and the presented results verified its feasibility.",

keywords = "Faculty of Science, Image analysis, computer vision, Machine vision, Welding",

author = "Jinchao Liu and Zhun Fan and Olsen, {S{\o}ren Ingvor} and Christensen, {Kim Hardam} and Kristensen, {Jens Kl{\ae}strup}",

year = "2017",

month = apr,

doi = "10.1109/TASE.2015.2498929",

language = "English",

volume = "14",

pages = "1096--1108",

journal = "IEEE Transactions on Automation Science and Engineering",

issn = "1545-5955",

publisher = "Institute of Electrical and Electronics Engineers",

number = "2",

}

TY - JOUR

T1 - Boosting active contours for weld pool visual tracking in automatic arc welding

AU - Liu, Jinchao

AU - Fan, Zhun

AU - Olsen, Søren Ingvor

AU - Christensen, Kim Hardam

AU - Kristensen, Jens Klæstrup

PY - 2017/4

Y1 - 2017/4

N2 - Detecting the shape of the non-rigid molten metal during welding, so-called weld pool visual sensing, is one of the central tasks for automating arc welding processes. It is challenging due to the strong interference of the high-intensity arc light and spatters as well as the lack of robust approaches to detect and represent the shape of the nonrigid weld pool. We propose a solution using active contours including an prior for the weld pool boundary composition. Also, we apply Adaboost to select a small set of features that captures the relevant information. The proposed method is applied to weld pool tracking and the presented results verified its feasibility.

AB - Detecting the shape of the non-rigid molten metal during welding, so-called weld pool visual sensing, is one of the central tasks for automating arc welding processes. It is challenging due to the strong interference of the high-intensity arc light and spatters as well as the lack of robust approaches to detect and represent the shape of the nonrigid weld pool. We propose a solution using active contours including an prior for the weld pool boundary composition. Also, we apply Adaboost to select a small set of features that captures the relevant information. The proposed method is applied to weld pool tracking and the presented results verified its feasibility.

KW - Faculty of Science

KW - Image analysis

KW - computer vision

KW - Machine vision

KW - Welding

U2 - 10.1109/TASE.2015.2498929

DO - 10.1109/TASE.2015.2498929

M3 - Journal article

SN - 1545-5955

VL - 14

SP - 1096

EP - 1108

JO - IEEE Transactions on Automation Science and Engineering

JF - IEEE Transactions on Automation Science and Engineering

IS - 2

ER -

Boosting active contours for weld pool visual tracking in automatic arc welding

Abstract

Keywords

Access to Document

Fingerprint

Cite this