摘要
基于深层卷积神经网络的特征学习能力,提出了一种基于全卷积神经网络的焊缝特征提取方法。该方法利用全卷积神经网络将包含焊缝特征信息的像素预测出来,通过融合低层与高层特征信息来补充焊缝边缘的特征信息。研究结果表明:所提方法能在强烈弧光和烟尘干扰下准确地提取出焊缝位置,具有抗干扰能力强、识别准确的优点。
Based on the feature learning ability of deep convolutional neural networks, a weld feature extraction method based on fully convolutional networks is proposed. In this method, the fully convolutional networks is used to predict the pixels containing the feature information of the weld, and the edge feature information of weld is supplemented by the fusion of low-level and high-level feature information. The results show that the method can get the weld position accurately under the interference of strong arc and soot particles, and has the advantages of strong anti-interference ability and accurate recognition.
引文
[1] Ping J, Zeng Y. Real time image processing for seam tracking based on laser stripe-sensor[J]. Applied Laser, 2010, 30(3): 232-235. 平津, 曾毅. 一种快速有效的基于激光视觉的焊缝跟踪实时图像处理方式[J]. 应用激光, 2010, 30(3): 232-235.
[2] Guo J C, Zhu Z M, Yu Y F, et al. Research and application of visual sensing technology based on laser structured light in welding industry[J]. Chinese Journal of Lasers, 2017, 44(12): 1200001. 郭吉昌, 朱志明, 于英飞, 等. 焊接领域激光结构光视觉传感技术的研究及应用[J]. 中国激光, 2017, 44(12): 1200001.
[3] Zhao J, Zhao J, Zhang L. Image processing and feature extraction for structured light images of welded seam[J]. Journal of Xi′an Jiaotong University, 2013, 47(1): 114-119. 赵军, 赵继, 张雷. 焊缝结构光图像处理与特征提取方法[J]. 西安交通大学学报, 2013, 47(1): 114-119.
[4] Li J X. Weld tracking and inspection system based on structured light imaging[D]. Taiyuan: North University of China, 2017: 31-37. 李佳璇. 基于结构光成像的焊缝跟踪与检测系统[D]. 太原: 中北大学, 2017: 31-37.
[5] Hu K, Zhou F Q, Zhang G J. Fast extrication method for sub-pixel center of structured light stripe[J]. Chinese Journal of Scientific Instrument, 2006, 27(10): 1326-1329. 胡坤, 周富强, 张广军. 一种快速结构光条纹中心亚像素精度提取方法[J]. 仪器仪表学报, 2006, 27(10): 1326-1329.
[6] Nan F, Li D H, Gao Q, et al. Implementation of adaptive light stripe center extraction of improved Steger algorithm[J]. Laser Journal, 2018, 39(1): 85-88. 南方, 李大华, 高强, 等. 改进Steger算法的自适应光条纹中心提取[J]. 激光杂志, 2018, 39(1): 85-88.
[7] Huo P, Li J M, Zeng H L, et al. The real-time image processing V-shaped seam method based on a structure light[J]. Electric Welding Machine, 2014, 44(12): 144-148. 霍平, 李军萌, 曾翰林, 等. 一种基于结构光的V型焊缝实时图像处理方法[J]. 电焊机, 2014, 44(12): 144-148.
[8] Yuan P, Kong J Y, Ze S C, et al. The research on image processing method of V-shaped welding groove[J]. Machinery Design & Manufacture, 2017(6): 64-66. 袁攀, 孔建益, 仄士春, 等. V型焊接坡口图像处理方法的研究[J]. 机械设计与制造, 2017(6): 64-66.
[9] Liu X W, Hong B, Dai T F. Image processing and groove recognition in weld seam tracking based on laser vision[J]. Laser & Infrared, 2011, 41(7): 804-807. 刘习文, 洪波, 戴铁峰. 激光视觉焊缝跟踪图像处理与坡口识别[J]. 激光与红外, 2011, 41(7): 804-807.
[10] Lei Z L, Shen J X, Li B W, et al. Recognition of narrow-gap edge welding seam based on autonomous threshold value[J]. Acta Optica Sinica, 2018, 38(8): 0815011. 雷正龙, 沈健雄, 黎炳蔚, 等. 基于自动阈值的窄间隙端接焊缝识别技术[J]. 光学学报, 2018, 38(8): 0815011.
[11] Zou Y B, Zhou W L, Chen X Z. Research of laser vision seam detection and tracking system based on depth hierarchical feature[J]. Chinese Journal of Lasers, 2017, 44(4): 0402009. 邹焱飚, 周卫林, 陈向志. 基于深度分层特征的激光视觉焊缝检测与跟踪系统研究[J]. 中国激光, 2017, 44(4): 0402009.
[12] Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation[C]. IEEE Conference on Computer Vision and Pattern Recognition, 2015: 3431-3440.
[13] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[J]. Computer Science, 2015(v6): 1409.
[14] Hariharan B, Arbeláez P, Girshick R, et al. Hypercolumns for object segmentation and fine-grained localization[C]. IEEE Conference on Computer Vision and Pattern Recognition, 2015: 447-456.
[15] Jia Y Q, Shelhamer E, Donahue J, et al. Caffe: convolutional architecture for fast feature embedding[C]. ACM International Conference on Multimedia, 2014: 675-678.
[16] Deng J, Dong W, Socher R, et al. ImageNet: a large-scale hierarchical image database[C]. IEEE Conference on Computer Vision and Pattern Recognition, 2009: 248-255.