{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T12:47:06Z","timestamp":1785761226397,"version":"3.56.0"},"reference-count":31,"publisher":"MDPI AG","issue":"15","license":[{"start":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T00:00:00Z","timestamp":1785628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Accurate weld seam tracking under severe arc interference remains a major challenge for intelligent robotic welding systems because radiometric saturation and transient visual degradation significantly reduce the reliability of vision-based measurements. Existing YOLO-based tracking methods generally use detector outputs directly for state estimation, assuming that the detection confidence adequately reflects localization reliability. However, this assumption often breaks down under strong arc interference, leading to unstable tracking and occasional tracking failure. To address this problem, this paper proposes a scene-aware confidence-guided YOLO (SACG-YOLO) framework for robust weld seam tracking. The proposed method introduces a scene-aware confidence estimator that evaluates the observability of the current welding scene by jointly considering structural consistency and photometric variation. The estimated scene confidence is fused with the detector confidence to assess measurement reliability, which is subsequently used to adaptively regulate the Kalman filter update process. As a result, reliable observations are incorporated into state estimation, while unreliable measurements are rejected in favor of motion prediction, thereby improving tracking continuity during severe visual degradation. Experiments on industrial welding image sequences demonstrate that the proposed framework consistently outperforms conventional YOLO-based tracking methods. Under stable and weak arc interference, the average tracking error is reduced from 0.492 mm to 0.155 mm, while the maximum error decreases from 0.829 mm to 0.354 mm. Under severe arc interference, where standalone YOLO tracking fails, SACG-YOLO maintains continuous weld seam localization with a maximum tracking error of 0.406 mm. These results demonstrate that explicitly modeling measurement reliability through scene-aware confidence estimation significantly improves the accuracy, robustness, and continuity of weld seam tracking in complex industrial welding environments.<\/jats:p>","DOI":"10.3390\/s26154861","type":"journal-article","created":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T11:50:21Z","timestamp":1785757821000},"page":"4861","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Scene-Aware Confidence-Guided YOLO Framework for Robust Weld Seam Tracking Under Intense Arc Interference"],"prefix":"10.3390","volume":"26","author":[{"given":"Lin","family":"Gao","sequence":"first","affiliation":[{"name":"School of Electrical Engineering, Yanshan University, Qinhuangdao 066004, China"},{"name":"The 54th Research Institute of China Electronics Technology Group Corporation, Shijiazhuang 050050, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feichi","family":"Cai","sequence":"additional","affiliation":[{"name":"International School of Transportation, Shijiazhuang Institute of Railway Technology, Shijiazhuang 050062, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaobo","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Yanshan University, Qinhuangdao 066004, China"},{"name":"Department of Information Engineering, Hebei Construction Material Vocational and Technical College, Qinhuangdao 066004, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,2]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"111255","DOI":"10.1016\/j.engstruct.2020.111255","article-title":"Tensile Bearing Capacity for Bolted Spherical Joints with Different Screwing Depths of High-Strength Bolts","volume":"225","author":"Ding","year":"2020","journal-title":"Eng. Struct."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"819","DOI":"10.1016\/j.proeng.2014.12.356","article-title":"A Study on Development of Optimal Noise Filter Algorithm for Laser Vision System in GMA Welding","volume":"97","author":"Wu","year":"2014","journal-title":"Procedia Eng."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1007\/s00170-007-0939-6","article-title":"A Visual Seam Tracking System for Robotic Arc Welding","volume":"37","author":"Xu","year":"2008","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1108\/01439910910950559","article-title":"Efficient Weld Seam Detection for Robotic Welding Based on Local Image Processing","volume":"36","author":"Shi","year":"2009","journal-title":"Ind. Robot Int. J."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1016\/j.rcim.2017.09.018","article-title":"Seam Tracking of Large Pipe Structures for an Agile Robotic Welding System Mounted on Scaffold Structures","volume":"50","author":"Chen","year":"2018","journal-title":"Robot. Comput. Integr. Manuf."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.rcim.2011.06.001","article-title":"A New Seam-Tracking Algorithm through Characteristic-Point Detection for a Portable Welding Robot","volume":"28","author":"Chang","year":"2012","journal-title":"Robot. Comput. Integr. Manuf."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"101821","DOI":"10.1016\/j.rcim.2019.101821","article-title":"A Robust Weld Seam Recognition Method under Heavy Noise Based on Structured-Light Vision","volume":"61","author":"Wang","year":"2020","journal-title":"Robot. Comput. Integr. Manuf."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"102261","DOI":"10.1016\/j.mechatronics.2019.102261","article-title":"Automatic Seam Detection and Tracking System for Robots Based on Laser Vision","volume":"63","author":"Zou","year":"2019","journal-title":"Mechatronics"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.ymssp.2017.04.001","article-title":"Tight Butt Joint Weld Detection Based on Optical Flow and Particle Filtering of Magneto-Optical Imaging","volume":"96","author":"Gao","year":"2017","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"5609","DOI":"10.1109\/JSEN.2017.2730280","article-title":"Robust Welding Seam Tracking and Recognition","volume":"17","author":"Li","year":"2017","journal-title":"IEEE Sens. J."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"609","DOI":"10.1108\/IR-11-2016-0294","article-title":"Seam Tracking Investigation via Striped Line Laser Sensor","volume":"44","author":"Zou","year":"2017","journal-title":"Ind. Robot Int. J."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"7261","DOI":"10.1109\/TIE.2017.2694399","article-title":"Automatic Welding Seam Tracking and Identification","volume":"64","author":"Li","year":"2017","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"111533","DOI":"10.1016\/j.sna.2019.111533","article-title":"An Adaptive Feature Extraction Algorithm for Multiple Typical Seam Tracking Based on Vision Sensor in Robotic Arc Welding","volume":"297","author":"Xiao","year":"2019","journal-title":"Sens. Actuators A Phys."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1801","DOI":"10.1007\/s11760-022-02391-0","article-title":"Aweld Feature Points Detection Method Based on Improved YOLO for Welding Robots in Strong Noise Environment","volume":"17","author":"Song","year":"2023","journal-title":"Signal Image Video Process."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Gao, A., Li, A., Su, F., Yang, X., Liu, W., Du, F., and Chen, C. (2025). WeldLight: A Lightweight Weld Classification and Feature Point Extraction Model for Weld Seam Tracking. Sensors, 25.","DOI":"10.3390\/s25185761"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Wang, J., Huang, L., Yao, J., Liu, M., Du, Y., Zhao, M., and Su, Y. (2023). Weld Seam Tracking and Detection Robot Based on Artificial Intelligence Technology. Sensors, 23.","DOI":"10.3390\/s23156725"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.rcim.2018.08.003","article-title":"Advances in Weld Seam Tracking Techniques for Robotic Welding: A Review","volume":"56","author":"Rout","year":"2019","journal-title":"Robot. Comput. Integr. Manuf."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1027","DOI":"10.1007\/s00170-020-05524-2","article-title":"Advances Techniques of the Structured Light Sensing in Intelligent Welding Robots: A Review","volume":"110","author":"Yang","year":"2020","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Li, J., Li, B., Dong, L., Wang, X., and Tian, M. (2022). Weld Seam Identification and Tracking of Inspection Robot Based on Deep Learning Network. Drones, 6.","DOI":"10.3390\/drones6080216"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1016\/j.jmsy.2025.05.003","article-title":"Coarse-to-Fine Vision-Based Welding Spot Anomaly Detection in Production Lines of Body-in-White","volume":"81","author":"Liu","year":"2025","journal-title":"J. Manuf. Syst."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Zhao, M., Liu, X., Wang, K., Liu, Z., Dong, Q., Wang, P., and Su, Y. (2024). Welding Seam Tracking and Inspection Robot Based on Improved YOLOv8s-Seg Model. Sensors, 24.","DOI":"10.3390\/s24144690"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"121700","DOI":"10.1016\/j.eswa.2023.121700","article-title":"WeldNet: A Deep Learning Based Method for Weld Seam Type Identification and Initial Point Guidance","volume":"238","author":"Ma","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"315","DOI":"10.1016\/j.jmapro.2024.03.006","article-title":"Van Vision-Based Seam Tracking for GMAW Fillet Welding Based on Keypoint Detection Deep Learning Model","volume":"117","author":"Mobaraki","year":"2024","journal-title":"J. Manuf. Process."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"110778","DOI":"10.1016\/j.engappai.2025.110778","article-title":"Tracking the Weld Seam under Strong Interference in Laser-Arc Hybrid Welding via a Novel Local-Add U-Net","volume":"151","author":"Yang","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"21137","DOI":"10.1038\/s41598-024-71989-w","article-title":"Weld Seam Object Detection System Based on the Fusion of 2D Images and 3D Point Clouds Using Interpretable Neural Networks","volume":"14","author":"Wang","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_26","first-page":"1","article-title":"The Active Visual Sensing Methods for Robotic Welding: Review, Tutorial, and Prospect","volume":"73","author":"Wang","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1033","DOI":"10.1007\/s11263-024-02219-z","article-title":"Systematic Evaluation of Uncertainty Calibration in Pretrained Object Detectors","volume":"133","author":"Huseljic","year":"2025","journal-title":"Int. J. Comput. Vis."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"3370","DOI":"10.1109\/TPAMI.2023.3342285","article-title":"Revisiting Confidence Estimation: Towards Reliable Failure Prediction","volume":"46","author":"Zhu","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2746","DOI":"10.1109\/TIP.2024.3378457","article-title":"CCDet: Confidence-Consistent Learning for Dense Object Detection","volume":"33","author":"Liu","year":"2024","journal-title":"IEEE Trans. Image Process."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Oksuz, K., Joy, T., and Dokania, P.K. (2023). Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52729.2023.00894"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"110003","DOI":"10.1016\/j.patcog.2023.110003","article-title":"Monte Carlo DropBlock for Modeling Uncertainty in Object Detection","volume":"146","author":"Harsha","year":"2024","journal-title":"Pattern Recognit."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/15\/4861\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T11:52:34Z","timestamp":1785757954000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/15\/4861"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,2]]},"references-count":31,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["s26154861"],"URL":"https:\/\/doi.org\/10.3390\/s26154861","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,2]]}}}