多线激光光条图像缺陷分割模型研究

doi:10.12263/DZXB.20220644

电子学报 ›› 2023, Vol. 51 ›› Issue (1): 172-179.DOI: 10.12263/DZXB.20220644

多线激光光条图像缺陷分割模型研究

郭晓轩¹, 冯其波¹^,³, 冀振燕², 郑发家¹, 杨燕燕²

^1.北京交通大学物理科学与工程学院，北京 100044
^2.北京交通大学软件学院，北京 100044
^3.东莞市诺丽科技股份有限公司，广东东莞 523050

收稿日期:2022-06-02 修回日期:2022-08-10 出版日期:2023-01-25
- 作者简介:
- 郭晓轩男，1996年4月出生，山东人.北京交通大学物理科学与工程学院博士研究生.主要研究方向为机器视觉和计算机视觉.E-mail: 20118037@bjtu.edu.cn
  冯其波（通讯作者）男，1962年5月出生，广东人.博士.北京交通大学物理科学与工程学院教授，博士生导师.研究方向为光学测量、铁路安全测量技术、仪器仪表、机器视觉等.
  冀振燕女，1972年4月出生，河南人.博士.北京交通大学软件学院副教授，博士生导师.主要研究方向为计算机视觉、多源异构数据融合等.E-mail: zhyji@bjtu.edu.cn
  郑发家男，1991年2月出生，安徽人.2021年于北京交通大学获得博士学位，现为北京交通大学讲师.主要研究方向为数控机床几何误差测量、轮对踏面几何参数在线测量、机器视觉.E-mail: zhfajia@bjtu.edu.cn
  杨燕燕女，1986年3月出生，河南人.北京交通大学讲师.主要研究方向为机器学习、不确定性人工智能.E-mail: yangyy@bjtu.edu.cn
- 基金资助:
- 国家自然科学基金重点项目(51935002,52175493);National Natural Science Foundation of China(51935002,52175493)

Research on Segmentation Model of Multi-Line Laser Strip Image’s Defects

GUO Xiao-xuan¹, FENG Qi-bo¹^,³, JI Zhen-yan², ZHENG Fa-jia¹, YANG Yan-yan²

^1.School of Physical Science and Engineering, Beijing Jiaotong University, Beijing 100044, China
^2.School of Software, Beijing Jiaotong University, Beijing 100044, China
^3.Dongguan Nannar Technology Co. , Ltd. , Dongguan, Guangdong 523050, China

Received:2022-06-02 Revised:2022-08-10 Online:2023-01-25 Published:2023-02-23

摘要/Abstract

摘要：

受环境干扰以及反射光影响，室外采集的多线激光光条图像含有光斑和断裂缺陷.为了准确地分割图像缺陷，本文提出了一个轻量的UT（U-shape Target，U代表U型编解码网络结构，T代表靶形视野）分割模型，模型由3×3卷积和靶形卷积堆叠而成.靶形卷积是针对激光光条图像特点提出的多视野卷积模块，模块中四个卷积分支构成靶形卷积视野，能够提取激光光条图像几何结构特征、局部细节特征以及环绕纹理特征.实验表明，UT模型在多线激光光条图像上的缺陷分割精度高于主流分割模型，而且实现了分割精度和参数量的平衡.

关键词: 缺陷分割, 激光图像, 深度学习, 轻量级分割模型, 多视野卷积

Abstract:

Influenced by environmental interference and reflected light, multi-line laser strip images collected outdoors contain the defects of flares and fractures. In order to segment the defects accurately, this paper proposes light-weight UT (U-shape Target, U represents a U-shaped encoder-decoder network architecture, and T represents a target-shaped receptive field) segmentation model, which stacks 3 × 3 convolutions and target convolutions. Considering the characteristics of laser strip images, we propose the target convolution, a multiple-receptive-field convolution module. Four convolution branches in this module form a target-shaped convolution receptive field, which can extract the geometric structure features, the local detail features and the surrounding texture features from the laser strip images. Experiments show that the UT model has higher defect segmentation accuracy than mainstream segmentation models, and can achieve the balance between the segmentation accuracy and the number of parameters.

Key words: defect segmentation, laser images, deep learning, light-weight segmentation model, multiple-receptive-field convolution

中图分类号:

TP183

郭晓轩, 冯其波, 冀振燕, 等. 多线激光光条图像缺陷分割模型研究[J]. 电子学报, 2023, 51(1): 172-179.

Xiao-xuan GUO, Qi-bo FENG, Zhen-yan JI, et al. Research on Segmentation Model of Multi-Line Laser Strip Image’s Defects[J]. Acta Electronica Sinica, 2023, 51(1): 172-179.

图/表 11

参考文献 25

1	徐频捷, 陈逸杰, 李之南, 等. 基于事件驱动的车道线识别算法研究[J]. 电子学报, 2021, 49(7): 1379-1385.
	XU P J, CHEN Y J, LI Z N, et al. Research on event-driven lane recognition algorithms[J]. Acta Electronica Sinica, 2021, 49(7): 1379-1385. (in Chinese)
2	赖小波, 许茂盛, 徐小媚. 多分类CNN的胶质母细胞瘤多模态MR图像分割[J]. 电子学报, 2019, 47(8): 1738-1747.
	LAI X B, XU M S, XU X M. Glioblastoma multiforme multi-modal MR images segmentation using multi-class CNN[J]. Acta Electronica Sinica, 2019, 47(8): 1738-1747. (in Chinese)
3	付利华, 赵宇, 姜涵煦, 等. 基于前景感知视觉注意的半监督视频目标分割[J]. 电子学报, 2022, 50(1): 195-206.
	FU L H, ZHAO Y, JIANG H X, et al. Semi-supervised video object segmentation based on foreground perception visual attention[J]. Acta Electronica Sinica, 2022, 50(1): 195-206. (in Chinese)
4	YUAN Y H, CHEN X L, WANG J D. Object-contextual representations for semantic segmentation[C]//European Conference on Computer Vision. Glasgow: Springer, 2020: 173-190.
5	SUN K, XIAO B, LIU D, et al. Deep high-resolution representation learning for human pose estimation[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 5686-5696.
6	SZEGEDY C, LIU W, JIA Y Q, et al. Going deeper with convolutions[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston: IEEE, 2015: 1-9.
7	CHEN L C, PAPANDREOU G, KOKKINOS I, et al. DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(4): 834-848.
8	WANG Y, ZHOU Q, LIU J, et al. Lednet: A lightweight encoder-decoder network for real-time semantic segmentation[C]//2019 IEEE International Conference on Image Processing. Taipei: IEEE, 2019: 1860-1864.
9	HONG Y D, PAN H H, SUN W C, et al. Deep dual-resolution networks for real-time and accurate semantic segmentation of road scenes[EB/OL]. (2021-01-15)[2022-06]. .
10	PENG J C, LIU Y, TANG S Y, et al. PP-LiteSeg: A superior real-time semantic segmentation model[EB/OL]. (2022-04-06)[2022-06]. .
11	GAO R. Rethink dilated convolution for real-time semantic segmentation[EB/OL]. (2021-11-18)[2022-06]. .
12	YU C Q, GAO C X, WANG J B, et al. BiSeNet V2: Bilateral network with guided aggregation for real-time semantic segmentation[J].International Journal of Computer Vision, 2021, 129(11): 3051-3068.
13	ZHAO H S, QI X J, SHEN X Y, et al. ICNet for real-time semantic segmentation on high-resolution images[C]//European Conference on Computer Vision. Munich: Springer, 2018: 418-434.
14	RONNEBERGER O, FISCHER P, BROX T. U-Net: Convolutional networks for biomedical image segmentation[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention. Munich: Springer, 2015: 234-241.
15	HUANG H M, LIN L F, TONG R F, et al. UNet 3: A full-scale connected UNet for medical image segmentation[C]//ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing. Barcelona: IEEE, 2020: 1055-1059.
16	LIU S T, HUANG D, WANG Y H. Receptive field block net for accurate and fast object detection[C]//European Conference on Computer Vision. Munich: Springer, 2018: 404-419.
17	WANG P Q, CHEN P F, YUAN Y, et al. Understanding convolution for semantic segmentation[C]//2018 IEEE Winter Conference on Applications of Computer Vision. Lake Tahoe: IEEE, 2018: 1451-1460.
18	WU T Y, TANG S, ZHANG R, et al. CGNet: A light-weight context guided network for semantic segmentation[J]. IEEE Transactions on Image Processing, 2021, 30: 1169-1179.
19	DING X H, GUO Y C, DING G G, et al. ACNet: Strengthening the kernel skeletons for powerful CNN via asymmetric convolution blocks[C]//2019 IEEE/CVF International Conference on Computer Vision. Seoul: IEEE, 2019: 1911-1920.
20	ZHOU Z W, RAHMAN SIDDIQUEE M M, TAJBAKHSH N, et al. UNet++: A nested U-Net architecture for medical image segmentation[C]//Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. Granada: Springer, 2018: 3-11.
21	OKTAY O, SCHLEMPER J, FOLGOC L L, et al. Attention U-net: Learning where to look for the pancreas[EB/OL].(2018-04-11)[2022-06]. .
22	LI H C, XIONG P F, FAN H Q, et al. DFANet: deep feature aggregation for real-time semantic segmentation[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 9514-9523.
23	PASZKE A, CHAURASIA A, KIM S, et al. ENet: A deep neural network architecture for real-time semantic segmentation[EB/OL]. (2016-06-07)[2022-06]. .
24	MEHTA S, RASTEGARI M, SHAPIRO L, et al. ESPNetv2: A light-weight, power efficient, and general purpose convolutional neural network[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 9182-9192.
25	YU C Q, WANG J B, PENG C, et al. BiSeNet: Bilateral segmentation network for real-time semantic segmentation[C]//European Conference on Computer Vision. Munich: Springer, 2018: 334-349.

参数	释义	取值
batch_size	每次迭代训练输入的图像数量	4
epoch	数据集全部样本训练完成的次数	60
optim	模型迭代训练的优化方法	Adam
lr	模型优化方法中的初始学习率	1×10^-2
loss	模型使用的损失函数	交叉熵

参数	释义	取值
batch_size	每次迭代训练输入的图像数量	4
epoch	数据集全部样本训练完成的次数	60
optim	模型迭代训练的优化方法	Adam
lr	模型优化方法中的初始学习率	1×10^-2
loss	模型使用的损失函数	交叉熵

模型	下采样次数	光斑IoU/%	断裂IoU/%	mIoU/%
UT	2	90.45	93.63	92.04
	3	90.42	94.32	92.37
	4	90.45	94.52	92.49
	5	90.25	94.56	92.41

模型	下采样次数	光斑IoU/%	断裂IoU/%	mIoU/%
UT	2	90.45	93.63	92.04
	3	90.42	94.32	92.37
	4	90.45	94.52	92.49
	5	90.25	94.56	92.41

多视野卷积模块	基准模型	参数量/M	光斑IoU/%	断裂IoU/%	mIoU/%
无	Unet3+	1.69	90.04	94.30	92.17
Inceptionv1	Unet3+	1.03	90.33	94.11	92.22
ASPP	Unet3+	1.47	90.29	93.84	92.07
RFB	Unet3+	1.57	90.58	94.17	92.38
CG	Unet3+	1.69	89.97	94.35	92.16
AC	Unet3+	1.25	90.47	94.08	92.28
十字卷积	Unet3+	1.41	90.42	94.37	92.40
靶形卷积	Unet3+	1.45	90.45	94.52	92.49

多线激光光条图像缺陷分割模型研究

Research on Segmentation Model of Multi-Line Laser Strip Image’s Defects

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 25

相关文章 15

编辑推荐

Metrics

模型	空洞率	光斑IoU/%	断裂IoU/%	mIoU/%
UC	1	90.39	94.37	92.38
	2	90.42	94.37	92.40
	4	90.41	94.28	92.35
	6	90.01	94.00	92.01
UT	1	90.29	94.36	92.33
	2	90.45	94.52	92.49
	4	90.61	94.17	92.39
	6	90.25	94.43	92.34

模型	参数量/M	光斑IoU/%	断裂IoU/%	mIoU/%
Unet	2.16	90.11	94.29	92.20
Unet++	2.55	90.15	94.26	92.21
AGUnet	2.19	90.46	94.08	92.27
Unet3+	1.69	90.04	94.30	92.17
Lednet	0.92	84.55	92.03	88.29
Dfanet	2.10	85.56	91.89	88.73
ICnet	26.24	76.06	82.41	79.24
Enet	0.35	89.06	93.05	91.06
CGnet	0.49	84.30	92.09	88.20
EspnetV2	2.16	86.70	91.16	88.93
BisenetV1	13.29	89.19	93.10	91.15
BisenetV2	3.54	86.13	93.37	89.75
OCRNet	70.35	86.18	93.54	89.86
PP-LiteSeg	11.27	84.70	92.05	88.38
DDRNet	5.70	84.80	92.28	88.54
RegSeg	3.33	86.28	93.56	89.92
UT	1.45	90.45	94.52	92.49

[1]	李钦, 刘伟, 牛朝阳, 宝音图, 惠周勃. 低信噪比下基于分裂EfficientNet网络的雷达信号调制方式识别[J]. 电子学报, 2023, 51(3): 675-686.
[2]	范兵兵, 何庭建, 张聪炫, 陈震, 黎明. 联合遮挡约束与残差补偿的特征金字塔光流计算方法[J]. 电子学报, 2023, 51(3): 648-657.
[3]	张聿远, 闫文君, 张立民. 基于多模态特征融合网络的空时分组码识别算法[J]. 电子学报, 2023, 51(2): 489-498.
[4]	许新征, 李杉. 基于特征膨胀卷积模块的轻量化技术研究[J]. 电子学报, 2023, 51(2): 355-364.
[5]	张永梅, 孙捷. 基于动静态特征双输入神经网络的咳嗽声诊断COVID-19算法[J]. 电子学报, 2023, 51(1): 202-212.
[6]	袁海英, 成君鹏, 曾智勇, 武延瑞. Mobile_BLNet：基于Big-Little Net的轻量级卷积神经网络优化设计[J]. 电子学报, 2023, 51(1): 180-191.
[7]	王神龙, 雍宇, 吴晨睿. 基于伪孪生神经网络的低纹理工业零件6D位姿估计[J]. 电子学报, 2023, 51(1): 192-201.
[8]	李滔, 董秀成, 林宏伟. 基于深监督跨尺度注意力网络的深度图像超分辨率重建[J]. 电子学报, 2023, 51(1): 128-138.
[9]	贾童瑶, 卓力, 李嘉锋, 张菁. 基于深度学习的单幅图像去雾研究进展[J]. 电子学报, 2023, 51(1): 231-245.
[10]	何滢婕, 刘月峰, 边浩东, 郭威, 张小燕. 基于Informer的电池荷电状态估算及其稀疏优化方法[J]. 电子学报, 2023, 51(1): 50-56.
[11]	吴靖, 叶晓晶, 黄峰, 陈丽琼, 王志锋, 刘文犀. 基于深度学习的单帧图像超分辨率重建综述[J]. 电子学报, 2022, 50(9): 2265-2294.
[12]	李雪莹, 王田路, 梁鹏, 王翀. 基于系统模型的用户评论中非功能需求的自动分类[J]. 电子学报, 2022, 50(9): 2079-2089.
[13]	琚长瑞, 秦晓燕, 袁广林, 李豪, 朱虹. 尺度敏感损失与特征融合的快速小目标检测方法[J]. 电子学报, 2022, 50(9): 2119-2126.
[14]	张志昌, 于沛霖, 庞雅丽, 朱林, 曾扬扬. SMGN：用于对话状态跟踪的状态记忆图网络[J]. 电子学报, 2022, 50(8): 1851-1858.
[15]	张亚洲, 俞洋, 朱少林, 陈锐, 戎璐, 梁辉. 一种量子概率启发的对话讽刺识别网络模型[J]. 电子学报, 2022, 50(8): 1885-1893.