Image Denoising of Seam Images With Deep Learning for Laser Vision Seam Tracking

doi:10.1109/JSEN.2022.3147489

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统管理与控制国家重点实验室 > 先进机器人控制团队

	Image Denoising of Seam Images With Deep Learning for Laser Vision Seam Tracking
	Yang, Lei 2,3; Fan, Junfeng 1; Huo, Benyan 2,3; Li, En 1; Liu, Yanhong 2,3
刊名	IEEE SENSORS JOURNAL
	2022-03-15
卷号	22 期号:6 页码:6098-6107
关键词	Welding Laser noise Sensors Robots Laser modes Feature extraction Lasers Deep network architecture image denoising seam tracking robot welding structured light vision
ISSN号	1530-437X
DOI	10.1109/JSEN.2022.3147489
通讯作者	Liu, Yanhong(liuyh@zzu.edu.cn)
英文摘要	Seam tracking with structured light vision has been widely applied into the robot welding. And the precise laser stripe extraction is the premise of automatic laser vision seam tracking. However, conventional laser stripe extraction methods based on image processing have the shortcomings of poor flexibility and robustness, which are easily affected by considerable image noises in the welding processing, such as arc light, smoke, and splash. To address this issue, inspired by image segmentation, with the strong contextual feature expression ability of deep convolutional neural network (DCNN), a novel image denoising method of seam images is proposed in this paper for automatic laser stripe extraction to serve intelligent robot welding applications, such as seam tracking, seam type detection, weld bead detection, etc. With the deep encoder-decoder network framework, aimed at the information loss issue by multiple convolutional and pooling operations in DCNNs, an attention dense convolutional block is proposed to extract and accumulate multi-scale feature maps. Meanwhile, a residual bi-directional ConvLSTM block (BiConvLSTM) is proposed to effectively learn multi-scale and long-range spatial contexts from local feature maps. Finally, a weighted loss function is proposed for model training to address the class unbalanced issue. Combined with the seam image set, the experimental results show that the proposed image denoising network could correctly extract the laser stripes from seam images which could demonstrate that the proposed method shows a high detection precision and good robustness against the strong image noise interference from welding process.
资助项目	National Natural Science Foundation of China[62003309] ; National Key Research and Development Project of China[2020YFB1313701] ; Science and Technology Research Project, Henan Province, China[202102210098] ; Outstanding Foreign Scientist Support Project in Henan Province of China[GZS2019008]
WOS关键词	EXTRACTION ; SYSTEM ; IDENTIFICATION ; JOINT
WOS研究方向	Engineering ; Instruments & Instrumentation ; Physics
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000770054800134
资助机构	National Natural Science Foundation of China ; National Key Research and Development Project of China ; Science and Technology Research Project, Henan Province, China ; Outstanding Foreign Scientist Support Project in Henan Province of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/48157]
专题	自动化研究所_复杂系统管理与控制国家重点实验室_先进机器人控制团队
通讯作者	Liu, Yanhong
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 2.Robot Percept & Control Engn Lab, Zhengzhou 450001, Henan, Peoples R China 3.Zhengzhou Univ, Sch Elect Engn, Zhengzhou 450001, Henan, Peoples R China
推荐引用方式 GB/T 7714	Yang, Lei,Fan, Junfeng,Huo, Benyan,et al. Image Denoising of Seam Images With Deep Learning for Laser Vision Seam Tracking[J]. IEEE SENSORS JOURNAL,2022,22(6):6098-6107.
APA	Yang, Lei,Fan, Junfeng,Huo, Benyan,Li, En,&Liu, Yanhong.(2022).Image Denoising of Seam Images With Deep Learning for Laser Vision Seam Tracking.IEEE SENSORS JOURNAL,22(6),6098-6107.
MLA	Yang, Lei,et al."Image Denoising of Seam Images With Deep Learning for Laser Vision Seam Tracking".IEEE SENSORS JOURNAL 22.6(2022):6098-6107.