-
摘要: 为满足智能制造企业对产品质量检测的需求, 服务制造企业生产管理, 对缺陷检测技术的研究现状、典型方法和应用进行梳理.首先总结了磁粉检测法、渗透检测法、涡流检测法、超声波检测法、机器视觉和基于深度学习的缺陷检测技术的优缺点; 对比分析了磁粉检测法、渗透检测法、涡流检测法、超声波检测法、机器视觉检测的主流缺陷检测技术和基于深度学习的缺陷检测技术的研究现状; 然后, 梳理了缺陷检测技术在电子元器件、管道、焊接件、机械零件和质量控制中的典型应用; 最后, 对缺陷检测技术的研究情况进行了总结和展望, 指出该研究领域亟需解决的问题和未来发展的方向, 并从高精度、高定位、快速检测、小目标、复杂背景、被遮挡物体检测、物体关联关系等几个方面总结近年来发表在ICCV (International Conference on Computer Vision)和CVPR (International Conference on Computer Vision and Pattern Recognition)等知名国际会议上相关论文的核心思想和源代码, 为缺陷检测技术的进一步发展提供理论和应用上的借鉴与参考.Abstract: To satisfy the requirements of intelligent manufacturing enterprises for product quality detection and service manufacturing enterprises production management, this paper summarizes the research status and typical methods and applications of defect detection technology. Firstly, we summarize the advantages and disadvantages of magnetic particle testing, penetration testing, eddy current testing, ultrasonic testing, machine vision testing and depth learning based defect detection. Meanwhile, we compare and analyze the current status of the mainstream defect detection technology of magnetic particle testing, penetration testing, eddy current testing, ultrasonic testing, machine vision testing and depth learning based defect detection technology. Then, we summarize the typical applications of defect detection technology in electronic components, pipes, welded parts, mechanical parts and quality control. Finally, we summarize and forecast the research of defect detection technology, and point out the problems that need to be solved in this research field and the direction of future development. We also summarize the core ideas and code of relevant papers published in well-known international conferences such as ICCV (International Conference on Computer Vision) and CVPR (International Conference on Computer Vision and Pattern Recognition) in recent years from high precision, high positioning, fast detection, small objects, complex backgrounds, occluded object detection, and object correlation. We hope that this research can provide theoretical and practical reference and reference for researchers of defect detection technology.
-
Key words:
- Defect detection /
- defect classification /
- fault prediction /
- deep learning
1) 本文责任编委 董峰 -
表 1 常用的缺陷检测方法的比较
Table 1 Comparison of common defect detection methods
编号 检测方法 缺陷特征 优点 缺点 适用材料 1 磁粉检测法[14] 表面和近表面缺陷 可直观显示缺陷的位置、形状、大小, 适用于任意大小的工件检测, 具有高精度、低费用、工艺简单等特点 只适用于铁磁性材料, 检测结果受检测件形状的影响, 难以实现自动化检测 铁磁性材料(如铸钢件、管材、棒材等) 2 渗透检测法[15] 表面缺陷 不受材料种类和外形轮廓的影响, 对疏松和针孔缺陷灵敏度高 难以检测多孔材料, 检测速度慢, 检测结果受检测人员影响大, 难以实现自动化检测 非多孔材料(如金属铸件、塑料、玻璃等) 3 涡流检测法[16-17] 表面缺陷 非接触检测, 检测速度快, 灵敏度高, 适于高温环境下缺陷自动化检测 不能直观显示缺陷形状和大小, 适用材料有限, 对较深缺陷检测困难, 检测精度低 导电材料或非金属材料(如工件、管材等) 4 X射线检法[18] 表面和内部缺陷 无损检测、穿透力强、不受材料外形与结构的影响、操作方便、检测效率高 对参与检测的工作人员有一定的辐射副作用 材料不限 5 超声波检测法[19] 表面和内部缺陷 使用方便、穿透力强、灵敏度高、设备便携、操作安全, 自动化检测 不适合用于结构复杂的工件, 检测效率低 材料不限 6 机器视觉检测法[20] 表面缺陷 适用范围广、精度高、不受检测件外形轮廓影响、检测效率高, 自动化检测 只能检测表面缺陷 材料不限 
下载: 导出CSV
表 2 基于深度学习的缺陷检测方法
Table 2 Deep learning defect detection methods
编号 检测方法 缺陷特征 优点 缺点 适用材料 7 卷积神经网络 表面和内部缺陷 对高维数据有较强的学习能力, 可从输入数据中学习到抽象的、本质的、高阶的特征 网络的表达能力随着深度的增加而增加, 网络越深, 计算复杂越大 材料不限 8 自编码神经网络 表面和内部缺陷 具有很好的目标信息表示能力, 可较好地提取复杂背景中的前景区域, 对环境噪声具有较好的鲁棒性 必须保证自编码机的输入和输出的数据维度一致 材料不限 9 深度残差神经网络 表面和内部缺陷 残差网络有着更低的收敛损失, 同时不会出现过高的过拟合现象, 具有较好的分类性能 残差网络必须要配合较深的深度才能发挥其结构优势 材料不限 10 全卷积神经网络 表面和内部缺陷 可对任意尺寸的图像进行特征提取操作, 并获得高层语义先验知识矩阵, 对语义级别的目标检测具有较好的效果 需要结合底层特征进行特征矩阵变换才能取得更好地效果, 模型收敛速度慢 材料不限 11 循环神经网络 表面和内部缺陷 当样本数据较少时, 可较好地学习到数据的本质特征, 减少池化过程中数据信息丢失 随着网络训练过程中迭代次数的增加, 循环神经网络模型可能会出现过拟合的现象 材料不限
下载: 导出CSV
表 3 流缺陷检测技术研究现状(1997年~2018年)
Table 3 Research status of defect detection methods for manufacturing products
编号 检测方法/算法 实验对象 目的 实验结果 数据来源 12 机器视觉与UMAN控制器 铺丝成型构件 表面缺陷检测 对宽度为6.35 mm的预浸纱, 间隙阈值为0.1 mm的检测效果较好 文献[36] 图 8 13 激光与机器视觉相结合 管道 表面缺陷检测 腐蚀和孔洞缺陷识别率为86.70 %, 裂缝缺陷为90.00 % 文献[38]第4.9节 14 改进的超声波检测方法 铝样品和不锈钢 表面缺陷检测 可检测出铝材料和不锈钢材料的缺陷位置信息 文献[39]图 2 15 脉冲磁阻方法 铁磁材料 表面缺陷检测 表面和亚表面缺陷深度为3 mm的峰值时间分别为16.59 ms和37.01 ms 文献[40]图 5 16 电磁声学技术 钢管 表面及亚表面 对具有强干扰能力的缺陷具有较好的检测能力 文献[41]图 5 17 脉冲涡流检测法 AL7075铝型材 表面及亚表面 提取的频谱幅值特征能检测亚表面裂纹缺陷 文献[42]图 3 18 脉冲涡流检测法 铁磁性构件 表面及亚表面 随着缺陷深度增大, 漏磁、扰动复合信号对涡流信号的影响变小 文献[37]图 6 19 微波技术 钢材涂层 表面缺陷检测 使用PCA与微波检测技术进行结合, 缺陷的形状和位置更加清晰 文献[43]图 3 20 杂波抑制和最小二乘法相结合的算法 缺陷的扫描图像 表面缺陷检测 通过最小二乘法处理后的图像可消除直通波与地面反射波, 便于提取缺陷的特征 文献[44]图 9 21 Hilbert变换的超声波 金属材料 表面及内部缺陷 对缺陷的形状、大小及分布情况具有较好的检测能力 文献[45]图 12 22 改进超声衍射时差的杂波抑制检测技术 铝合金板 表面缺陷 缺陷深度在1.9 sm$ \sim $6.2 sm中的缺陷具有较好的检测效果 文献[46]图 8 23 超声透射时差法 金属棒 表面及内部缺陷 缺陷缝隙为0.90 mm和0.60 mm的检测准确率分别为90.00 %和60.00 % 文献[47]图 15 24 远场涡流技术 管道 表面缺陷 对于面积为20 mm$^2$、深度为7 mm及更大体积物件具有较好的检测效果 文献[48]图 5 25 改进的Gabor滤波器 钢材料 表面缺陷 单张图片的平均检测速度为91.80 ms/帧, 表面缺陷检测的平均准确率为95.80 % 文献[49]图 5 26 机器视觉检测 钢轨 表面缺陷 缺陷检测的误检率为7.30 %, 漏检率为6.20 % 文献[50]第3节 27 亥姆霍兹电磁阵列技术 管道 表面缺陷 探头可检测轴向裂纹和周向裂纹以及缺陷轮廓 文献[51]第4.2节 28 X射线图像缺陷检测技术 铝材焊缝 表面和内部缺陷 很难实现缺陷深度低于2 mm的检测 文献[52]图 2 29 X射线图像缺陷检测技术 管道 表面缺陷 缺陷边缘检测、对焊缝特征动态提取的效果较好 文献[53]图 6 30 视觉检测 钢轨 表面缺陷 块状缺陷和线状缺陷识别率分别为95.40 %和91.70 % 文献[54]图 4 31 光声信号 焊缝法兰组件 表面缺陷 焊缝法兰组件缺陷样本的识别率为90.00 % 文献[55]图 6 32 瞬态频率响应技术 管道 表面缺陷 验证了管道缺陷的检测范围, 灵敏度高 文献[56]表 1 33 视觉显著性检测 电池 表面缺陷 与传统的方法相比, 具有较高的准确度 文献[57]表 2 34 双目视觉检测 焊接件 焊缝缺陷 缺陷深度最大误差1.9 mm, 平均绝对误差为1.4 mm, 平均相对误差为18.00 % 文献[58]图 3 35 超声透射时差法 黄铜棒 表面和内部缺陷 缺陷测量误差$\pm$ 0.01 mm, 轴向分率0.007$^\circ$, 最大测量直径30 mm 文献[59]图 3 36 Kalman滤波的CPCI算法 复合材料 表面和内部缺陷 图像重建缺陷面积与真实样件缺陷面积误差0.54 cm 文献[60]表 3 37 图像处理技术 胶管 表面缺陷 胶管表面缺陷准确率96.30 % 文献[61]图 7 38 机器视觉 光伏组件 表面缺陷 实现1.98 lp/mm的空间分辨检测和0.11 mm线宽的最小单条纹缺陷检测 文献[62]图 6 39 非下采样Shearlet变换 磁瓦 表面缺陷 缺陷检测检测准确率94.30 % 文献[63]表 1 40 脉冲涡流热成像检测方法 焊球 表面和内部缺陷 实现检测微小尺寸焊球的缺陷位置及分类具有较好的检测效果 文献[64]图 4 41 X射线 工业铸件 表面和内部缺陷 可较准确预测产品第一次缺陷发生的位置 文献[65]图 6 42 格林函数重构原理 平板 表面缺陷 谐振信号产生的噪声波可较准确地对缺陷的位置进行定位 文献[66]图 12 43 声发射技术 碳钢 表面和内部缺陷 频率带在[100 kHz$ \sim $200 kHz]时对焊缝缺陷检测准确率60.00 %以上 文献[67]图 8 44 支持向量机 陶瓷 表面和内部缺陷 缺陷检测分类准确率94.50 % 文献[68]图 3 45 粗粒度检测方法 光学元件 表面和内部缺陷 缺陷识别定位准确率94.44 % 文献[69]图 4
下载: 导出CSV
表 4 深度学习的缺陷检测技术研究现状
Table 4 Research status of defect detection technology fordeep learning
编号 检测方法/算法 实验对象 目的 实验结果 数据来源 46 卷积神经网络方法 精密铸件 表面缺陷检测 缺陷检测最大误差5.52 %, 最小误差2.51 %, 平均误差3.87 % 文献[70]图 7 47 小波变换与神经网络 纤维板 内部缺陷检测 对左端和中部鼓泡的识别率大于90.00 %, 对右端鼓泡识别率大于 80 % 文献[71] 第3.1节 48 深度卷积神经网络 机械零件 表面缺陷检测 在640 × 480像素的检测样本图像中具有较好的纹理特征, 缺陷检测时间为0.217 s 文献[72]表 1 49 深度卷积神经网络 紧固件 表面缺陷检测 最高识别准确率为96.72 %, 单个样本的时间大约为83 s, 训练时间大约为133 min 文献[73]图 14 50 卷积神经网络和自适应 纳米材料 表面缺陷检测 单个样本图片的最高准确率为97.00 %, 单张测试样本的平均识别时间在15 s$ \sim $50 s之间 文献[74]图 2 51 3D视觉传感器和神经网络 管道 表面缺陷检测 对缺陷的最高准确率为97.00 %, 单张图片的平均识别时间为19 s 文献[75]图 12 52 深度卷积神经网络 手机壳 表面缺陷检测 平均召回率为68.68 %.在验证集上的实验表明, 对抗性训练具有较好的效果 文献[76]图 11 53 深度卷积神经网络 胶囊 表面缺陷检测 32 × 32像素的胶囊图片的最大准确率为94.68 % 文献[77] 第4.1节 54 支持向量机和卷积神经网络 车轮 表面缺陷检测 车轮缺陷检测准确率大于87.00 %, 精度值大于87.00 %, 召回率大于89.00 % 文献[78] 图 3 55 深度卷积神经网络 管道 表面缺陷检测 在200多条管道实验中的平均准确率和召回率分别为86.20 %和90.60 % 文献[79] 图 8 56 自编码网络 纳米材料 表面缺陷检测 512 × 512大小样本的最高识别准确率为96.60 %, 最低为68.80 % 文献[28] 图 4 57 全卷积神经网络 管道 表面缺陷检测 3 000 × 3 724大小的管道图像最高的缺陷检测准确率为95.00 % 文献[34] 图 2 58 循环神经网络 手机屏幕 表面缺陷检测 对具有复杂尺寸和形状样本的平均准确率为90.36 % 文献[35] 图 1
下载: 导出CSV
表 5 基于深度学习的缺陷检测方法
Table 5 Deep learning defect detection methods
编号 论文 录用信息 核心思想 开源代码 60 高精度的目标检测 [155] CVPR 2017 用普通分类网络的卷积层获得样本的特征图, 采用感兴趣区域算法在特征图中获得待测目标对象, 提高目标检测的精度. https://github.com/daijifeng001/R-FCN 61 高定位能力的目标检测 [156] CVPR 2017 改进FasterR-CNN [157]网络, 提高检测速度;在提取感兴趣区域时, 增加一次池化操作提高感兴趣区域对位置定位的准确性. https://github.com/TuSimple/mx-maskrcnn 62 快速的目标检测 [158] CVPR 2017 采用候选框对物体进行特征选择, 增加对候选框物体判定的二分类函数, 采用多尺度预测的思想, 对预测位置进行准确判定. https://github.com/pjreddie/darknet 63 端到端的小目标检测 [159] CVPR 2017 采用端到端的思想, 结合位置回归, 将语义信息融合到底层网络特征中, 提高对小目标的目标检测能力. https://github.com/MTCloudVision/mxnet-dssd 64 从零开始训练网络策略 [160] ICCV 2017 提出一种从零开始的网络训练策略, 提出了收敛区域和图像空间不匹配问题的解决思路. https://github.com/szq0214/DSOD 65 小目标检测 [161] CVPR 2017 针对池化操作会引起特征信息丢失的问题, 采用网络的高层特征和底层特征进行学习和训练, 提高小目标的检测效果 https://github.com/unsky/FPN 66 数据样本不均衡的目标检测 [162] ICCV 2017 针对检测目标的多样性, 采用可变形的卷积网络和感兴趣区域提高在复杂背景下不规则形状物体的检测能力 https://github.com/msracver/Deformable-ConvNets 67 复杂背景目标检测 [163] ICCV 2017 针对背景样本复杂, 通过增加语义层过滤无用背景信息, 后阶段的特征和分类器只负责处理过滤后的少量样本 https://github.com/wk910930/ccnn 68 被遮挡物体检测 [164] ICCV 2017 在训练过程中, 提出多尺度训练策略, 通过调整阈值函数提高被遮挡物体的检测能力 https://github.com/bharatsingh430/soft-nms 69 基于物体之间的关联关系的目标检测 [165] CVPR2018 提出物体间关联关系的度量方法, 将关联信息融入提取后的特征中, 并保持特征维数不变, 提高相似性物体之间的特征识别能力. https://github.com/msracver/Relation-Networks-for-Object-Detection
下载: 导出CSV
-
[1] 周亮, 王振环, 孙东辰, 穆乃锋.现代精密测量技术现状及发展.仪器仪表学报, 2017, 38(8): 1869-1878 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201708005Zhou Liang, Wang Zhen-Huan, Sun Dong-Chen, Mu Nai-Feng. Present situation and development of modern precision measurement technology. Chinese Journal of Scientific Instrument, 2017, 38(8): 1869-1878 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201708005 [2] 彭开香, 马亮, 张凯.复杂工业过程质量相关的故障检测与诊断技术综述.自动化学报, 2017, 43(3): 349-365 doi: 10.16383/j.aas.2017.c160427Peng Kai-Xiang, Ma Liang, Zhang Kai. Review of quality-related fault detection and diagnosis techniques for complex industrial processes. Acta Automatica Sinica, 2017, 43(3): 349-365 doi: 10.16383/j.aas.2017.c160427 [3] Kumar A. Computer-vision-based fabric defect detection: A survey. IEEE Transactions on Industrial Electronics, 2008, 55(1): 348-363 doi: 10.1109/TIE.1930.896476 [4] 武新军, 张卿, 沈功田.脉冲涡流无损检测技术综述.仪器仪表学报, 2016, 37(8): 1698-1712 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201608003Wu Xin-Jun, Zhang Qing, Shen Gong-Tian. Review on advances in pulsed eddy current nondestructive testing technology. Chinese Journal of Scientific Instrument, 2016, 37(8): 1698-1712 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201608003 [5] Seebauer E G, Noh K W. Trends in semiconductor defect engineering at the nanoscale. Materials Science and Engineering: R: Reports, 2010, 70(3-6): 151-168 doi: 10.1016/j.mser.2010.06.007 [6] 李健, 陈世利, 黄新敬, 曾周末, 靳世久.长输油气管道泄漏监测与准实时检测技术综述.仪器仪表学报, 2016, 37(8): 1747-1760 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201608006Li Jian, Chen Shi-Li, Huang Xin-Jing, Zeng Zhou-Mo, Jin Shi-Jiu. Review of leakage monitoring and quasi real-time detection technologies for long gas & oil pipelines. Chinese Journal of Scientific Instrument, 2016, 37(8): 1747-1760 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201608006 [7] 田贵云, 高斌, 高运来, 王平, 王海涛, 石永生.铁路钢轨缺陷伤损巡检与监测技术综述.仪器仪表学报, 2016, 37(8): 1763-1780 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201608008Tian Gui-Yun, Gao Bin, Gao Yun-Lai, Wang Ping, Wang Hai-Tao, Shi Yong-Sheng. Review of railway rail defect non-destructive testing and monitoring. Chinese Journal of Scientific Instrument, 2016, 37(8): 1763-1780 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201608008 [8] Kandpal L M, Park E, Tewari J, Cho B K. Spectroscopic techniques for nondestructive quality inspection of pharmaceutical products: A review. Journal of Biosystems Engineering, 2015, 40(4): 394-408 doi: 10.5307/JBE.2015.40.4.394 [9] 沈功田, 李建, 武新军.承压设备脉冲涡流检测技术研究及应用.机械工程学报, 2017, 53(4): 49-58 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jxgcxb201704007Shen Gong-Tian, Li Jian, Wu Xin-Jun. Research and application of pulsed eddy current testing technology for pressure equipment. Journal of Mechanical Engineering, 2017, 53(4): 49-58 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jxgcxb201704007 [10] 黄凤英.钢轨表面裂纹涡流检测定量评估方法.中国铁道科学, 2017, 38(2): 28-33 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zgtdkx201702005Huang Feng-Ying. Quantitative evaluation method for eddy current testing of rail surface crack. China Railway Science, 2017, 38(2): 28-33 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zgtdkx201702005 [11] 周正干, 孙广开.先进超声检测技术的研究应用进展.机械工程学报, 2017, 53(22): 1-10 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jxgcxb201722001Zhou Zheng-Gan, Sun Guang-Kai. New progress of the study and application of advanced ultrasonic testing technology. Journal of Mechanical Engineering, 2017, 53(22): 1-10 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jxgcxb201722001 [12] 王兴国, 吴文林, 陈正林, 吴南星. LY12硬铝合金损伤缺陷的空气耦合超声检测.中国机械工程, 2017, 28(21): 2582-2587 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zgjxgc201721012Wang Xing-Guo, Wu Wen-Lin, Chen Zheng-Lin, Wu Nan-Xing. Air-coupling ultrasonic testing of defects in LY12 duralumin alloys. China Mechanical Engineering, 2017, 28(21): 2582-2587 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zgjxgc201721012 [13] 鹿文浩, 李亚利, 王生进, 丁晓清.基于部件的三维目标检测算法新进展.自动化学报, 2012, 38(4): 497-506 doi: 10.3724/SP.J.1004.2012.00497Lu Wen-Hao, Li Ya-Li, Wang Sheng-Jin, Ding Xiao-Qing. Improvements of 3D object detection with part-based models. Acta Automatica Sinica, 2012, 38(4): 497-506 doi: 10.3724/SP.J.1004.2012.00497 [14] 马涛, 孙振国, 陈强.基于几何与纹理特征相融合的磁粉探伤裂纹提取算法.清华大学学报(自然科学版), 2018, 58(1): 50-54 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=qhdxxb201801008Ma Tao, Sun Zhen-Guo, Chen Qiang. Crack detection algorithm for fluorescent magnetic particle inspection based on shape and texture features. Journal of Tsinghua University (Science and Technology), 2018, 58(1): 50-54 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=qhdxxb201801008 [15] 黄展鸿, 黄春芳, 张鉴炜, 江大志, 鞠苏.声发射技术在纤维增强复合材料损伤检测和破坏过程分析中的应用研究进展.材料导报, 2018, 32(7): 1122-1128 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=cldb201807013Huang Zhan-Hong, Huang Chun-Fang, Zhang Jian-Wei, Jiang Da-Zhi, Ju Su. Acoustic emission technique for damage detection and failure process determination of fiber-reinforced polymer composites: An application review. Materials Review, 2018, 32(7): 1122-1128 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=cldb201807013 [16] 周德强, 潘萌, 常祥, 王华, 曹丕宇.铁磁性构件缺陷的脉冲涡流检测模式研究.仪器仪表学报, 2017, 38(6): 1498-1505 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201706022Zhou De-Qiang, Pan Meng, Chang Xiang, Wang Hua, Cao Pi-Yu. Research on detection modes of ferromagnetic component defects using pulsed eddy current. Chinese Journal of Scientific Instrument, 2017, 38(6): 1498-1505 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201706022 [17] 沈功田.承压设备无损检测与评价技术发展现状.机械工程学报, 2017, 53(12): 1-12 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jxgcxb201712001Shen Gong-Tian. Development status of nondestructive testing and evaluation technique for pressure equipment. Journal of Mechanical Engineering, 2017, 53(12): 1-12 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jxgcxb201712001 [18] 邬冠华, 熊鸿建.中国射线检测技术现状及研究进展.仪器仪表学报, 2017, 37(8): 1683-1695 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201608001Wu Guan-Hua, Xiong Hong-Jian. Radiography testing in China. Chinese Journal of Scientific Instrument, 2017, 37(8): 1683-1695 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201608001 [19] 谭超, 董峰.多相流过程参数检测技术综述.自动化学报, 2013, 39(11): 1923-1932 doi: 10.3724/SP.J.1004.2013.01923Tan Chao, Dong Feng. Parameters measurement for multiphase flow process. Acta Automatica Sinica, 2013, 39(11): 1923-1932 doi: 10.3724/SP.J.1004.2013.01923 [20] 苑玮琦, 薛丹.基于机器视觉的隧道衬砌裂缝检测算法综述.仪器仪表学报, 2017, 38(12): 3100-3111 http://www.cnki.com.cn/Article/CJFDTotal-YQXB201712026.htmYuan Wei-Qi, Xue Dan. Review of tunnel lining crack detection algorithm based on machine vision. Chinese Journal of Scientific Instrument, 2017, 38(12): 3100-3111 http://www.cnki.com.cn/Article/CJFDTotal-YQXB201712026.htm [21] Yang J, Li S B, Gao Z, Wang Z, Liu W. Real-time recognition method for 0.8 cm darning needles and KR22 bearings based on convolution neural networks and data increase. Applied Sciences, 2018, 8(10): Article No. 1857 [22] Yang G C, Yang J, Sheng W H, Junior F E F, Li S B. Convolutional neural network-based embarrassing situation detection under camera for social robot in smart homes. Sensors, 2018, 18(5): Article No. 1530 [23] 李东民, 李静, 梁大川, 王超.基于多尺度先验深度特征的多目标显著性检测方法.自动化学报, 2019, 45(11): 2058-2070 doi: 10.16383/j.aas.c170154Li Dong-Min, Li Jing, Liang Da-Chuan, Wang Chao. Multiple salient objects detection using multi-scale prior and deep features. Acta Automatica Sinica, 2019, 45(11): 2058-2070 doi: 10.16383/j.aas.c170154 [24] 张慧, 王坤峰, 王飞跃.深度学习在目标视觉检测中的应用进展与展望.自动化学报, 2017, 43(8): 1289-1305 doi: 10.16383/j.aas.2017.c160822Zhang Hui, Wang Kun-Feng, Wang Fei-Yue. Advances and perspectives on applications of deep learning in visual object detection. Acta Automatica Sinica, 2017, 43(8): 1289-1305 doi: 10.16383/j.aas.2017.c160822 [25] Fang F, Li L, Gu Y, et al. A novel hybrid approach for crack detection. Pattern Recognition, 2020, 107: 107474. doi: 10.1016/j.patcog.2020.107474 [26] Jiang J F, Chen Z M, He K J. A feature-based method of rapidly detecting global exact symmetries in CAD models. Computer-Aided Design, 2013, 45(8-9): 1081-1094 doi: 10.1016/j.cad.2013.04.005 [27] Cheng J C P, Wang M Z. Automated detection of sewer pipe defects in closed-circuit television images using deep learning techniques. Automation in Construction, 2018, 95: 155-171 doi: 10.1016/j.autcon.2018.08.006 [28] Bergmann P, Löwe S, Fauser M, Sattlegger D, Steger C. Improving unsupervised defect segmentation by applying structural similarity to autoencoders. arXiv preprint arXiv: 1807.02011, 2018 [29] Yang J, Yang G C. Modified convolutional neural network based on dropout and the stochastic gradient descent optimizer. Algorithms, 2018, 11(3): Article No. 28 [30] Lin J H, Yao Y, Ma L, Wang Y J. Detection of a casting defect tracked by deep convolution neural network. The International Journal of Advanced Manufacturing Technology, 2018, 97(1): 573-581 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=2723e5420c66ddd5873b743aea74d134 [31] Wei F, Yao G, Yang Y, et al. Instance-level recognition and quantification for concrete surface bughole based on deep learning. Automation in Construction, 2019, 107: 102920 doi: 10.1016/j.autcon.2019.102920 [32] Tao X, Wang Z H, Zhang Z T, Zhang D P, Xu D, Gong X Y, et al. Wire defect recognition of spring-wire socket using multitask convolutional neural networks. IEEE Transactions on Components, Packaging and Manufacturing Technology, 2018, 8(4): 689-698 doi: 10.1109/TCPMT.2018.2794540 [33] 林懿伦, 戴星原, 李力, 王晓, 王飞跃.人工智能研究的新前线:生成式对抗网络.自动化学报, 2018, 44(5): 775-792 doi: 10.16383/j.aas.2018.y000002Lin Yi-Lun, Dai Xing-Yuan, Li Li, Wang Xiao, Wang Fei-Yue. The new frontier of AI research: Generative adversarial networks. Acta Automatica Sinica, 2018, 44(5): 775-792 doi: 10.16383/j.aas.2018.y000002 [34] Xue Y D, Li Y C. A fast detection method via region-based fully convolutional neural networks for shield tunnel lining defects. Computer-Aided Civil and Infrastructure Engineering, 2018, 33(8): 638-654 doi: 10.1111/mice.12367 [35] Lei J, Gao X, Feng Z L, Qiu H M, Song M L. Scale insensitive and focus driven mobile screen defect detection in industry. Neurocomputing, 2018, 294: 72-81 doi: 10.1016/j.neucom.2018.03.013 [36] 文立伟, 宋清华, 秦丽华, 肖军.基于机器视觉与UMAC的自动铺丝成型构件缺陷检测闭环控制系统.航空学报, 2015, 36(12): 3991-4000 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=hkxb201512023Wen Li-Wei, Song Qing-Hua, Qin Li-Hua, Xiao Jun. Defect detection and closed-loop control system for automated fiber placement forming components based on machine vision and UMAC. Acta Aeronautica et Astronautica Sinica, 2015, 36(12): 3991-4000 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=hkxb201512023 [37] 周德强, 王俊, 张秋菊, 吴静静, 张洪.铁磁性构件缺陷的脉冲涡流检测传感机理研究.仪器仪表学报, 2015, 36(5): 989-995 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201505004Zhou De-Qiang, Wang Jun, Zhang Qiu-Ju, Wu Jing-Jing, Zhang Hong. Research on sensing mechanism of ferromagnetic component flaw using pulsed eddy current testing. Chinese Journal of Scientific Instrument, 2015, 36(5): 989-995 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201505004 [38] 吴挺, 鲁少辉, 韩旺明, 胡克钢, 汤一平.基于主动式全景视觉传感器的管道内部缺陷检测方法.仪器仪表学报, 2015, 36(10): 2258-2264 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201510013Wu Ting, Lu Shao-Hui, Han Wang-Ming, Hu Ke-Gang, Tang Yi-Ping. In-pipe internal defect inspection method based on active stereo omni-directional vision sensor. Chinese Journal of Scientific Instrument, 2015, 36(10): 2258-2264 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201510013 [39] 曾伟, 王海涛, 田贵云, 方凌, 汪文, 万敏, 等.基于能量分析的激光超声波缺陷检测研究.仪器仪表学报, 2014, 35(3): 650-655 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201403023Zeng Wei, Wang Hai-Tao, Tian Gui-Yun, Fang Lin, Wang Wen, Wan Min, et al. Research on laser ultrasonic defect signal detection technology based on energy analysis. Chinese Journal of Scientific Instrument, 2014, 35(3): 650-655 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201403023 [40] Wilson J W, Tian G Y. Pulsed electromagnetic methods for defect detection and characterisation. NDT & E International, 2007, 40(4): 275-283 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=4a0a93e26cddbf2b7ee24310cb943045 [41] Shi D Q, Gao G L, Xiao P, Gao Z W. Defects detection system for steel tubes based on electromagnetic acoustic technology. Procedia Engineering, 2012, 29: 252-256 doi: 10.1016/j.proeng.2011.12.702 [42] 周德强, 田贵云, 尤丽华, 王海涛, 王平.基于频谱分析的脉冲涡流缺陷检测研究.仪器仪表学报, 2011, 32(9): 1948-1953 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201109005Zhou De-Qiang, Tian Gui-Yun, You Li-Hua, Wang Hai-Tao, Wang Ping. Study on pulsed eddy current defect signal detection technology based on spectrum analysis. Chinese Journal of Scientific Instrument, 2011, 32(9): 1948-1953 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201109005 [43] Zhang H, Gao B, Tian G Y, Woo W L, Bai L B. Metal defects sizing and detection under thick coating using microwave NDT. NDT & E International, 2013, 60: 52-61 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=9554883e378701839ef44de1ae7c1c7e [44] 林乃昌, 杨晓翔, 林文剑, 朱志彬.基于抛物线拟合的TOFD图像缺陷检测.焊接学报, 2014, 35(6): 105-108 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=hjxb201406025Lin Nai-Chang, Yang Xiao-Xiang, Lin Wen-Jian, Zhu Zhi-Bin. Defect detection of TOFD D scanning image based on parabola fitting. Transactions of The China Welding Institution, 2014, 35(6): 105-108 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=hjxb201406025 [45] 曾伟, 王海涛, 田贵云, 方凌, 汪文.基于Hilbert变换的激光超声波成像技术在缺陷检测中的应用.中国激光, 2014, 41(5): 182-188 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zgjg201405033Zeng Wei, Wang Hai-Tao, Tian Gui-Yun, Fang Ling, Wang Wen. Application laser ultrasound imaging technology for detecting defect based on Hilbert transform. Chinese Journal of Lasers, 2014, 41(5): 182-188 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zgjg201405033 [46] 迟大钊, 刚铁.基于超声杂波抑制的缺陷检测.焊接学报, 2015, 36(10): 17-20 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=hjxb201510005Chi Da-Zhao, Gang Tie. Defect detection method based on ultrasonic clutter wave suppression. Transactions of the China Welding Institution, 2015, 36(10): 17-20 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=hjxb201510005 [47] 黄刚.基于超声透射时差法的金属棒缺陷检测研究.仪器仪表学报, 2016, 37(4): 818-826 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201604014Huang Gang. Research on defect detection system for material based on ultrasonic transmission method. Chinese Journal of Scientific Instrument, 2016, 37(4): 818-826 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201604014 [48] 师奕兵, 罗清旺, 王志刚, 张伟, 马东.基于多元接收线圈的管道局部缺陷检测方法研究.电子学报, 2018, 46(1): 197-202 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=dianzixb201801027Shi Yi-Bing, Luo Qing-Wang, Wang Zhi-Gang, Zhang Wei, Ma Dong. Research on the detection of local defects of pipes based on dual receivers. Acta Electronica Sinica, 2018, 46(1): 197-202 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=dianzixb201801027 [49] 屈尔庆, 崔月姣, 徐森, 孙鹤旭.改进的Gabor滤波器带钢表面缺陷显著性检测.华中科技大学学报(自然科学版), 2017, 45(10): 12-17 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=9882887Qu Er-Qing, Cui Yue-Jiao, Xu Sen, Sun He-Xu. Saliency defect detection in strip steel by improved Gabor filter. Journal of Huazhong University of Science and Technology (Nature Science Edition), 2017, 45(10): 12-17 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=9882887 [50] 袁小翠, 吴禄慎, 陈华伟.钢轨表面缺陷检测的图像预处理改进算法.计算机辅助设计与图形学学报, 2014, 26(5): 800-805 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jsjfzsjytxxxb201405017Yuan Xiao-Cui, Wu Lu-Shen, Chen Hua-Wei. Improved image preprocessing algorithm for rail surface defects detection. Journal of Computer-Aided Design & Computer Graphics, 2014, 26(5): 800-805 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jsjfzsjytxxxb201405017 [51] Ge J H, Li W, Chen G M, Yin X K, Yuan X N, Yang W C, et al. Multiple type defect detection in pipe by Helmholtz electromagnetic array probe. NDT & E International, 2017, 91: 97-107 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=fe3a2275049970a1ecc26c97fea440ae [52] Kazantsev I G, Lemahieu I, Salov G I, Denys R. Statistical detection of defects in radiographic images in nondestructive testing. Signal Processing, 2002, 82(5): 791-801 doi: 10.1016/S0165-1684(02)00158-5 [53] Tian Y, Du D, Cai G R, Wang L, Zhang H. Automatic defect detection in X-Ray images using image data fusion. Tsinghua Science & Technology, 2006, 11(6): 720-724 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=qhdxxb-e200606012 [54] 贺振东, 王耀南, 毛建旭, 印峰.基于反向P-M扩散的钢轨表面缺陷视觉检测.自动化学报, 2014, 40(8): 1667-1679 doi: 10.3724/SP.J.1004.2014.01667He Zhen-Dong, Wang Yao-Nan, Mao Jian-Xu, Yin Feng. Research on inverse P-M diffusion-based rail surface defect detection. Acta Automatica Sinica, 2014, 40(8): 1667-1679 doi: 10.3724/SP.J.1004.2014.01667 [55] 杨理践, 曹辉.基于深度学习的管道焊缝法兰组件识别方法.仪器仪表学报, 2018, 39(2): 193-202 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201802023Yang Li-Jian, Cao Hui. Deep learning based weld and flange identification in pipeline. Chinese Journal of Scientific Instrument, 2018, 39(2): 193-202 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201802023 [56] Duan H F. Transient frequency response based leak detection in water supply pipeline systems with branched and looped junctions. Journal of Hydroinformatics, 2017, 19(1): 17-30 doi: 10.2166/hydro.2016.008 [57] 钱晓亮, 张鹤庆, 张焕龙, 贺振东, 杨存祥.基于视觉显著性的太阳能电池片表面缺陷检测.仪器仪表学报, 2017, 38(7): 1570-1578 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201707002Qian Xiao-Liang, Zhang He-Qing, Zhang Huan-Long, He Zhen-Dong, Yang Cun-Xiang. Solar cell surface defect detection based on visual saliency. Chinese Journal of Scientific Instrument, 2017, 38(7): 1570-1578 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201707002 [58] 迟大钊, 李孙珏, 孙昌立, 刚铁.基于双目视觉的缺陷深度测量方法.焊接学报, 2016, 37(11): 7-10 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=hjxb201611002Chi Da-Zhao, Li Sun-Jue, Sun Chang-Li, Gang Tie. Binocular visual based defect buried depth testing method. Transactions of the China Welding Institution, 2016, 37(11): 7-10 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=hjxb201611002 [59] Galan U, Orta P, Kurfess T, Ahuett-Garza H. Surface defect identification and measurement for metal castings by vision system. Manufacturing Letters, 2018, 15: 5-8 doi: 10.1016/j.mfglet.2017.12.001 [60] 杨丽君, 田洪刚, 安立明, 温银堂, 罗小元.基于同面电容成像的航天隔热复合材料粘接缺陷检测方法.兵工学报, 2017, 38(12): 2488-2496 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=bgxb201712024Yang Li-Jun, Tian Hong-Gang, An Li-Ming, Wen Yin-Tang, Luo Xiao-Yuan. Bonding defect detection method of aeronautical insulating compsites based on coplanar capacitance imaging reconstruction. Acta Armamentarii, 2017, 38(12): 2488-2496 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=bgxb201712024 [61] 朱妍妍, 左建华, 卢继平, 徐东晓.基于图像处理的胶管缺陷在线检测系统开发.北京理工大学学报, 2017, 37(9): 937-941 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=bjlgdxxb201709010Zhu Yan-Yan, Zuo Jian-Hua, Lu Ji-Ping, Xu Dong-Xiao. A on-line detection system development based on image processing for rubber hose defects. Transactions of Beijing Institute of Technology, 2017, 37(9): 937-941 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=bjlgdxxb201709010 [62] 林剑春, 杨爱军, 沈熠辉.电致发光缺陷检测仪的成像性能评估.光学精密工程, 2017, 25(6): 1418-1424 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gxjmgc201706003Lin Jian-Chun, Yang Ai-Jun, Shen Yi-Hui. Evaluation of imaging performance for electroluminescence defect detector. Optics and Precision Engineering, 2017, 25(6): 1418-1424 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gxjmgc201706003 [63] 杨成立, 殷鸣, 向召伟, 范奎.基于非下采样Shearlet变换的磁瓦表面缺陷检测.工程科学与技术, 2017, 49(2): 217-224 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=scdxxb-gckx201702028Yang Cheng-Li, Yin Ming, Xiang Zhao-Wei, Fan Kui. Defect detection in magnetic tile images based on non-subsampled Shearlet transform. Advanced Engineering Sciences, 2017, 49(2): 217-224 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=scdxxb-gckx201702028 [64] 周秀云, 薛云, 周金龙.基于多物理场的焊球缺陷检测方法.西南交通大学学报, 2017, 52(2): 363-368 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=xnjtdxxb201702021Zhou Xiu-Yun, Xue Yun, Zhou Jin-Long. Defect detection of solder balls based on multi-physical field. Journal of Southwest Jiaotong University, 2017, 52(2): 363-368 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=xnjtdxxb201702021 [65] Fieres J, Schumann P, Reinhart C. Predicting failure in additively manufactured parts using X-ray computed tomography and simulation. Procedia Engineering, 2018, 213: 69-78 doi: 10.1016/j.proeng.2018.02.008 [66] Chehami L, Moulin E, de Rosny J, Prada C, Chatelet E, Lacerra G, et al. Nonlinear secondary noise sources for passive defect detection using ultrasound sensors. Journal of Sound & Vibration, 2017, 386: 283-294 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=1930200db3c2a6b805806ad2147c276b [67] Droubi M G, Faisal N H, Orr F, Steel J A, El-Shaib M. Acoustic emission method for defect detection and identification in carbon steel welded joints. Journal of Constructional Steel Research, 2017, 134: 28-37 doi: 10.1016/j.jcsr.2017.03.012 [68] D'Angelo G, Rampone S. Feature extraction and soft computing methods for aerospace structure defect classification. Measurement, 2016, 85: 192-209 doi: 10.1016/j.measurement.2016.02.027 [69] Pichler K, Lughofer E, Pichler M, Buchegger T, Klement E P, Huschenbett M. Fault detection in reciprocating compressor valves under varying load conditions. Mechanical Systems and Signal Processing, 2016, 70-71: 104-119 doi: 10.1016/j.ymssp.2015.09.005 [70] 余永维, 杜柳青, 曾翠兰, 张建恒.基于深度学习特征匹配的铸件微小缺陷自动定位方法.仪器仪表学报, 2016, 37(6): 1364-1370 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201606021Yu Yong-Wei, Du Liu-Qing, Zeng Cui-Lan, Zhang Jian-Heng. Automatic localization method of small casting defect based on deep learning feature. Chinese Journal of Scientific Instrument, 2016, 37(6): 1364-1370 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201606021 [71] 孙建平, 王逢瑚, 朱晓冬.小波--神经网络在MDF缺陷定位检测中的应用.仪器仪表学报, 2008, 29(5): 954-958 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb200805011Sun Jian-Ping, Wang Feng-Hu, Zhu Xiao-Dong. Application of wavelet-neural network in defect location non-destructive testing of MDF. Chinese Journal of Scientific Instrument, 2008, 29(5): 954-958 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb200805011 [72] Park J K, Kwon B K, Park J H, Kang D J. Machine learning-based imaging system for surface defect inspection. International Journal of Precision Engineering and Manufacturing-Green Technology, 2016, 3(3): 303-310 doi: 10.1007/s40684-016-0039-x [73] Chen J W, Liu Z G, Wang H R, Núñez A, Han Z W. Automatic defect detection of fasteners on the catenary support device using deep convolutional neural network. IEEE Transactions on Instrumentation & Measurement, 2018, 67(2): 257-269 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=70e333fb479671d31e97aa2799987209 [74] Napoletano P, Piccoli F, Schettini R. Anomaly detection in nanofibrous materials by CNN-based self-similarity. Sensors, 2018, 18(1): Article No. 209 [75] Yang Z Y, Lu S H, Wu T, Yuan G P, Tang Y P. Detection of morphology defects in pipeline based on 3D active stereo omnidirectional vision sensor. IET Image Processing, 2018, 12(4): 588-595 doi: 10.1049/iet-ipr.2017.0616 [76] Yuan Z C, Zhang Z T, Su H, Zhang L, Shen F, Zhang F. Vision-based defect detection for mobile phone cover glass using deep neural networks. International Journal of Precision Engineering and Manufacturing, 2018, 19(6): 801-810 doi: 10.1007/s12541-018-0096-x [77] Liu R, Gu Q, Wang X, Yao M. Region-convolutional neural network for detecting capsule surface defects. Boletin Tecnico/Technical Bulletin, 2017, 55(3): 92-100 [78] Krummenacher G, Ong C S, Koller S, Kobayashi S, Buhmann J M. Wheel defect detection with machine learning. IEEE Transactions on Intelligent Transportation Systems, 2018, 19(4): 1176-1187 doi: 10.1109/TITS.2017.2720721 [79] Kumar S S, Abraham D M, Jahanshahi M R, Iseley T, Starr J. Automated defect classification in sewer closed circuit television inspections using deep convolutional neural networks. Automation in Construction, 2018, 91: 273-283 doi: 10.1016/j.autcon.2018.03.028 [80] Shaw D, Al-Khalili D, Rozon C. Fault security analysis of CMOS VLSI circuits using defect-injectable VHDL models. Integration, 2002, 32(1-2): 77-97 doi: 10.1016/S0167-9260(02)00043-3 [81] 林晓玲, 恩云飞, 姚若河. 3D叠层封装集成电路的缺陷定位方法.华南理工大学学报(自然科学版), 2016, 44(5): 36-41, 47 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=hnlgdxxb201605006Lin Xiao-Ling, En Yun-Fei, Yao Ruo-He. Defect localization method of 3D stacked-die packaged integrated circuits. Journal of South China University of Technology (Natural Science Edition), 2016, 44(5): 36-41, 47 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=hnlgdxxb201605006 [82] Wu C L, Yao S Y, Corinne B. Leakage current study and relevant defect localization in integrated circuit failure analysis. Microelectronics Reliability, 2015, 55(3-4): 463-469 doi: 10.1016/j.microrel.2015.01.005 [83] Chen X L, Liu L Y, Li E L. Metal defect localization of GaAs or Si based ICs by dynamic emission microscopy. Microelectronics Reliability, 2017, 72: 24-29 doi: 10.1016/j.microrel.2017.03.003 [84] Chao L C, Tong L I. Wafer defect pattern recognition by multi-class support vector machines by using a novel defect cluster index. Expert Systems with Applications, 2009, 36(6): 10158-10167 doi: 10.1016/j.eswa.2009.01.003 [85] Bouwens M A J, Maas D J, van der Donck J C J, Alkemade P F A, van der Walle P. Enhancing re-detection efficacy of defects on blank wafers using stealth fiducial markers. Microelectronic Engineering, 2016, 153: 48-54 doi: 10.1016/j.mee.2016.01.007 [86] 周启忠, 谢永乐.模拟集成电路故障诊断与参数辨识的代数方法.四川大学学报(工程科学版), 2016, 48(4): 158-166 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=scdxxb-gckx201604022Zhou Qi-Zhong, Xie Yong-Le. Algebraic methodology on fault diagnosis and parametric identification for analog integrated circuits. Journal of Sichuan University (Engineering Science Edition), 2016, 48(4): 158-166 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=scdxxb-gckx201604022 [87] Wang J P, Wu Y, Zhao T W. Short critical area model and extraction algorithm based on defect characteristics in integrated circuits. Analog Integrated Circuits and Signal Processing, 2017, 91(1): 83-91 doi: 10.1007/s10470-016-0841-y [88] Jung H K, Lee C W, Park G. Fast and non-invasive surface crack detection of press panels using image processing. Procedia Engineering, 2017, 188: 72-79 doi: 10.1016/j.proeng.2017.04.459 [89] Shi Q Z, Liu J Y, Wang Y, Liu W Y. Study on the detection of CFRP material with subsurface defects using barker-coded thermal wave imaging (BC-TWI) as a nondestructive inspection (NDI) tool. International Journal of Thermophysics, 2018, 39(8): Article No. 92 [90] Hartmann C, Wieberneit M. Investigation on BIST assisted failure analysis on digital integrated circuits. Microelectronics Reliability, 2010, 50(9-11): 1464-1468 doi: 10.1016/j.microrel.2010.07.148 [91] Roesch W J, Hamada D J M. Discovering and reducing defects in MIM capacitors. Microelectronics Reliability, 2018, 81: 299-305 doi: 10.1016/j.microrel.2017.10.021 [92] 黄松岭, 王哲, 王珅, 赵伟.管道电磁超声导波技术及其应用研究进展.仪器仪表学报, 2018, 39(3): 1-12 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201803001Huang Song-Ling, Wang Zhe, Wang Kun, Zhao Wei. Review on advances of pipe electromagnetic ultrasonic guided waves technology and its application. Chinese Journal of Scientific Instrument, 2018, 39(3): 1-12 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201803001 [93] 雷小军, 付庄, 曹其新, 赵言正.海底管道检测机器人自主缺陷定位的模糊控制研究.机器人, 2005, 27(3): 252-255 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jqr200503012Lei Xiao-Jun, Fu Zhuang, Cao Qi-Xin, Zhao Yan-Zheng. Fuzzy control of autonomous defect location for submarine in-pipeline inspection robots. Robot, 2005, 27(3): 252-255 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jqr200503012 [94] Grin E A, Bochkarev V I. Estimate of the allowable dimensions of diagnosed defects in category Ⅲ and IV welded pipeline joints. Power Technology & Engineering, 2013, 46(5): 394-398 [95] 刘素贞, 张严伟, 张闯, 金亮, 杨庆新.电磁超声管道周向兰姆波仿真分析及缺陷检测特性研究.电工技术学报, 2017, 32(22): 144-151 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=dgjsxb201722016Liu Su-Zhen, Zhang Yan-Wei, Zhang Chuang, Jin Liang, Yang Qing-Xin. Research on simulation analysis of electromagnetic ultrasonic circumferential lamb waves and defect feature detection in pipeline. Transactions of China Electrotechnical Society, 2017, 32(22): 144-151 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=dgjsxb201722016 [96] Song Q, Ding W X, Peng H, Gu J J, Shuai J. Pipe defect detection with remote magnetic inspection and wavelet analysis. Wireless Personal Communications, 2017, 95(3): 2299-2313 doi: 10.1007/s11277-017-4092-8 [97] Mao B Y, Lu Y, Wu P L, Mao B Z, Li P F. Signal processing and defect analysis of pipeline inspection applying magnetic flux leakage methods. Intelligent Service Robotics, 2014, 7(4): 203-209 doi: 10.1007/s11370-014-0158-6 [98] 武静, 张伟伟, 聂振华, 马宏伟, 杨飞.基于Lyapunov指数的管道超声导波小缺陷定位实验研究.振动与冲击, 2016, 35(1): 40-45, 53 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zdycj201601008Wu Jing, Zhang Wei-Wei, Nie Zhen-Hua, Ma Hong-Wei, Yang Fei. Tests for datecting crack locations in a pipe with ultrasonic guided wave based on Lyapunov exponent. Journal of Vibration and Shock, 2016, 35(1): 40-45, 53 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zdycj201601008 [99] 周进节, 郑阳, 杨齐, 张宗健.管道超声导波分段时间反转检测方法研究.机械工程学报, 2017, 53(12): 78-86 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jxgcxb201712010Zhou Jin-Jie, Zheng Yang, Yang Qi, Zhang Zong-Jian. Pipeline section time reversal inspection method with ultrasonic guided waves. Journal of Mechanical Engineering, 2017, 53(12): 78-86 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jxgcxb201712010 [100] 何存富, 邓鹏, 吕炎, 焦敬品, 吴斌.一种高信噪比电磁声表面波传感器及在厚壁管道检测中的应用.机械工程学报, 2017, 53(4): 59-66 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jxgcxb201704008He Cun-Fu, Deng Peng, Lv Yan, Jiao Jing-Pin, Wu Bin. A new surface wave EMAT with high SNR and the application for defect detection in thick-walled pipes. Journal of Mechanical Engineering, 2017, 53(4): 59-66 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jxgcxb201704008 [101] Oh S W, Yoon D B, Kim G J, Bae J H, Kim H S. Acoustic data condensation to enhance pipeline leak detection. Nuclear Engineering and Design, 2018, 327: 198-211 doi: 10.1016/j.nucengdes.2017.12.006 [102] Duan H F. Accuracy and sensitivity evaluation of TFR method for leak detection in multiple-pipeline water supply systems. Water Resources Management, 2018, 32(6): 2147-2164 doi: 10.1007/s11269-018-1923-7 [103] 何存富, 郑明方, 吕炎, 邓鹏, 赵华民, 刘秀成, 等.超声导波检测技术的发展、应用与挑战.仪器仪表学报, 2016, 37(8): 1713-1735 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201608004He Cun-Fu, Zheng Ming-Fang, Lv Yan, Deng Peng, Zhao Hua-Ming, Liu Xiu-Cheng, et al. Development, applications and challenges in ultrasonic guided waves testing technology. Chinese Journal of Scientific Instrument, 2016, 37(8): 1713-1735 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201608004 [104] 石端虎, 刚铁, 杨根喜, 黄传辉.工字形激光焊件中批量缺陷定位数据的自动提取.焊接学报, 2009, 30(10): 49-52 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=hjxb200910013Shi Duan-Hu, Gang Tie, Yang Gen-Xi, Huang Chuan-Hui. Automatic extraction of locating data for bulk defects in I-shaped laser weldments. Transactions of the China Welding Institution, 2009, 30(10): 49-52 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=hjxb200910013 [105] Rodil S S, Gómez R A, Bernárdez J M, Rodríguez F, Miguel L J, Perán J R. Laser welding defects detection in automotive industry based on radiation and spectroscopical measurements. International Journal of Advanced Manufacturing Technology, 2010, 49(1-4): 133-145 doi: 10.1007/s00170-009-2395-y [106] Lindgren E. Detection and 3-D positioning of small defects using 3-D point reconstruction, tracking, and the radiographic magnification technique. NDT & E International, 2015, 76: 1-8 [107] Makhutov N A, Ushakov B N, Vasilév I E. Strength assessment and defect detection in welded pipeline seams by means of brittle tensosensitive coatings. Russian Engineering Research, 2011, 31(2): 123-127 doi: 10.3103/S1068798X1102016X [108] Zhang Z F, Kannatey-Asibu E Jr, Chen S B, Huang Y M, Xu Y L. Online defect detection of Al alloy in arc welding based on feature extraction of arc spectroscopy signal. The International Journal of Advanced Manufacturing Technology, 2015, 79(9-12): 2067-2077 doi: 10.1007/s00170-015-6966-9 [109] Kim H M, Choi D H. Defects detection of gas pipeline near the welds based on self quotient image and discrete cosine transform. Russian Journal of Nondestructive Testing. 2016, 52(3): 175-183 doi: 10.1134/S1061830916030049 [110] Mirapeix J, Ruiz-Lombera R, Valdiande J J, Rodriguez-Cobo L, Anabitarte F, Cobo A. Defect detection with CCD-spectrometer and photodiode-based arc-welding monitoring systems. Journal of Materials Processing Technology, 2011, 211(12): 2132-2139 doi: 10.1016/j.jmatprotec.2011.07.011 [111] Liu J, Xu G C, Ren L, Qian Z H, Ren L Q. Defect intelligent identification in resistance spot welding ultrasonic detection based on wavelet packet and neural network. The International Journal of Advanced Manufacturing Technology, 2017, 90(9-12): 2581-2588 doi: 10.1007/s00170-016-9588-y [112] Chu H H, Wang Z Y. A vision-based system for post-welding quality measurement and defect detection. The International Journal of Advanced Manufacturing Technology, 2016, 86(9): 3007-3014 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=6830d08f8d7465139bab80cb03b45d61 [113] Malarvel M, Sethumadhavan G, Bhagi P C R, Kar S, Saravanan T, Krishnan A. Anisotropic diffusion based denoising on X-radiography images to detect weld defects. Digital Signal Processing, 2017, 68: 112-126 doi: 10.1016/j.dsp.2017.05.014 [114] Guo Z Y, Ye S F, Wang Y J, Lin C. Resistance Welding spot defect detection with convolutional neural networks. In: Proceedings of the 2017 International Conference on Computer Vision Systems. Cham: Springer, 2017. 169-174 [115] Ye G L, Guo J W, Sun Z Z, Li C, Zhong S Y. Weld bead recognition using laser vision with model-based classification. Robotics and Computer-Integrated Manufacturing, 2018, 52: 9-16 doi: 10.1016/j.rcim.2018.01.006 [116] 温银堂, 赵丽梅, 张玉燕, 潘钊, 王洪瑞.基于ECT的复合材料构件胶层缺陷检测.仪器仪表学报, 2015, 36(8): 1783-1791 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201508013Wen Yin-Tang, Zhao Li-Mei, Zhang Yu-Yan, Pan Zhao, Wang Hong-Rui. Defect detection of the adhesive layer of composite component based on the ECT technology. Chinese Journal of Scientific Instrument, 2015, 36(8): 1783-1791 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201508013 [117] Jing T, Zhang S B, Shi X D, Wang L W. Design of aircraft cable fault diagnose and location system based on aircraft airworthiness requirement. Procedia Engineering, 2011, 17: 455-464 doi: 10.1016/j.proeng.2011.10.055 [118] Mazlumi F, Gharanfeli N, Sadeghi S H H, Moini R. An open-ended substrate integrated waveguide probe for detection and sizing of surface cracks in metals. NDT & E International, 2013, 53: 36-38 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=b00d35bd4f1157b9e39b1ea55eda0c67 [119] Yang Y Y, Chai H T, Li C, Zhang Y H, Wu F, Bai J, et al. Surface defects evaluation system based on electromagnetic model simulation and inverse-recognition calibration method. Optics Communications, 2017, 390: 88-98 doi: 10.1016/j.optcom.2016.12.075 [120] Zhang J, Drinkwater B W, Wilcox P D, et al. Defect detection using ultrasonic arrays: The multi-mode total focusing method. NDT & E International, 2010, 43(2): 123-133 [121] Ghose B, Kankane D K. Estimation of location of defects in propellant grain by X-ray radiography. NDT & E International, 2008, 41(2): 125-128 [122] Yan Z B, Chen C Y, Luo L K, Yao Y. Stable principal component pursuit-based thermographic data analysis for defect detection in polymer composites. Journal of Process Control, 2017, 49: 36-44 doi: 10.1016/j.jprocont.2016.11.008 [123] Benmoussat M S, Guillaume M, Caulier Y, Spinnler K. Automatic metal parts inspection: Use of thermographic images and anomaly detection algorithms. Infrared Physics & Technology, 2013, 61: 68-80 [124] Zheng K Y, Chang Y S, Wang K H, Yao Y. Thermographic clustering analysis for defect detection in CFRP structures. Polymer Testing, 2016, 49: 73-81 doi: 10.1016/j.polymertesting.2015.11.009 [125] Ghidoni S, Antonello M, Nanni L, Menegatti E. A thermographic visual inspection system for crack detection in metal parts exploiting a robotic workcell. Robotics and Autonomous Systems, 2015, 74: 351-359 doi: 10.1016/j.robot.2015.07.020 [126] Holzmond O, Li X D. In situ real time defect detection of 3D printed parts. Additive Manufacturing, 2017, 17: 135-142 doi: 10.1016/j.addma.2017.08.003 [127] 宋伟, 左丹, 邓邦飞, 张海兵, 薛凯文, 胡泓.高压输电线防震锤锈蚀缺陷检测.仪器仪表学报, 2016, 37(S1): 113-117 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=9580938Song Wei, Zuo Dan, Deng Bang-Fei, Zhang Hai-Bing, Xue Kai-Wen, Hu Hong. Corrosion defect detection of earthquake hammer for high voltage transmission line. Chinese Journal of Scientific Instrument, 2016, 37(S1): 113-117 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=9580938 [128] Molina J, Solanes J E, Arnal L, Tornero J. On the detection of defects on specular car body surfaces. Robotics and Computer-Integrated Manufacturing, 2017, 48: 263-278 doi: 10.1016/j.rcim.2017.04.009 [129] Meng F, Ren J, Wang Q, et al. Rubber hose surface defect detection system based on machine vision. In: Proceedings of the 2018 IOP Conference Series: Earth and Environmental Science. 2018, 108(2): 022057 [130] 沈凌云, 朱明, 陈小云.基于径向基神经网络的太阳能电池缺陷检测.发光学报, 2015, 36(1): 99-105 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=fgxb201501015Shen Ling-Yun, Zhu Ming, Chen Xiao-Yun. Solar panels defect detection based on radial basis function neural network. Chinese Journal of Luminescence, 2015, 36(1): 99-105 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=fgxb201501015 [131] Woźniak M, Polap D. Adaptive neuro-heuristic hybrid model for fruit peel defects detection. Neural Networks, 2018, 98: 16-33 doi: 10.1016/j.neunet.2017.10.009 [132] Gupta R K, Gurumoorthy B. Classification, representation, and automatic extraction of deformation features in sheet metal parts. Computer-Aided Design, 2013, 45(11): 1469-1484 doi: 10.1016/j.cad.2013.06.010 [133] 侯忠生, 许建新.数据驱动控制理论及方法的回顾和展望.自动化学报, 2009, 35(6): 650-667 doi: 10.3724/SP.J.1004.2009.00650Hou Zhong-Sheng, Xu Jian-Xin. On data-driven control theory: The state of the art and perspective. Acta Automatica Sinica, 2009, 35(6): 650-667 doi: 10.3724/SP.J.1004.2009.00650 [134] Behera A K, Lauwers B, Duflou J R. Advanced feature detection algorithms for incrementally formed sheet metal parts. Transactions of Nonferrous Metals Society of China, 2012, 22(S2): S315-S322 [135] Tao X, Xu D, Zhang Z T, Zhang F, Liu X L, Zhang D P. Weak scratch detection and defect classification methods for a large-aperture optical element. Optics Communications, 2017, 387: 390-400 doi: 10.1016/j.optcom.2016.10.062 [136] Martínez-Rego D, Fontenla-Romero O, Alonso-Betanzos A, Principe J C. Fault detection via recurrence time statistics and one-class classification. Pattern Recognition Letters, 2016, 84: 8-14 doi: 10.1016/j.patrec.2016.07.019 [137] Shanmugamani R, Sadique M, Ramamoorthy B. Detection and classification of surface defects of gun barrels using computer vision and machine learning. Measurement, 2015, 60: 222-230 doi: 10.1016/j.measurement.2014.10.009 [138] Hanzaei S H, Afshar A, Barazandeh F. Automatic detection and classification of the ceramic tiles' surface defects. Pattern Recognition, 2017, 66: 174-189 doi: 10.1016/j.patcog.2016.11.021 [139] Greska W, Franke V, Geiger M. Classification problems in manufacturing of sheet metal parts. Computers in Industry, 1997, 33(1): 17-30 doi: 10.1016/S0166-3615(97)00008-0 [140] Martínez S S, Vázquez C O, García J G, Ortega J G. Quality inspection of machined metal parts using an image fusion technique. Measurement, 2017, 111: 374-383 doi: 10.1016/j.measurement.2017.08.002 [141] Cui X D, Goel V, Kingsbury B. Data augmentation for deep neural network acoustic modeling. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2015, 23(9): 1469-1477 doi: 10.1109/TASLP.2015.2438544 [142] Chen X F, Wang S B, Qiao B J, Chen Q. Basic research on machinery fault diagnostics: Past, present, and future trends. Frontiers of Mechanical Engineering, 2018, 13(2): 264-291 doi: 10.1007/s11465-018-0472-3 [143] Shin H J, Eom D H, Kim S S. One-class support vector machines-an application in machine fault detection and classification. Computers & Industrial Engineering, 2005, 48(2): 395-408 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=ed7cafea4b09c1fa0b0b045ee529aa5c [144] Chauhan V, Surgenor B. A comparative study of machine vision based methods for fault detection in an automated assembly machine. Procedia Manufacturing, 2015, 1: 416-428 doi: 10.1016/j.promfg.2015.09.051 [145] Gketsis Z E, Zervakis M E, Stavrakakis G. Detection and classification of winding faults in windmill generators using Wavelet Transform and ANN. Electric Power Systems Research, 2009, 79(11): 1483-1494 doi: 10.1016/j.epsr.2009.05.001 [146] Zarei J, Tajeddini M A, Karimi H R. Vibration analysis for bearing fault detection and classification using an intelligent filter. Mechatronics, 2014, 24(2): 151-157 doi: 10.1016/j.mechatronics.2014.01.003 [147] Guo X, Chen L, Shen C. Hierarchical adaptive deep convolution neural network and its application to bearing fault diagnosis. Measurement, 2016, 93: 490-502 doi: 10.1016/j.measurement.2016.07.054 [148] Ruiz M, Mujica L E, Alférez S, Acho L, Tutivén C, Vidal Y, et al. Wind turbine fault detection and classification by means of image texture analysis. Mechanical Systems and Signal Processing, 2018, 107: 149-167 doi: 10.1016/j.ymssp.2017.12.035 [149] Prytz R, Nowaczyk S, Rögnvaldsson T, et al. Predicting the need for vehicle compressor repairs using maintenance records and logged vehicle data. Engineering Applications of Artificial Intelligence, 2015, 41: 139-150. doi: 10.1016/j.engappai.2015.02.009 [150] Liu J, Li Y F, Zio E. A SVM framework for fault detection of the braking system in a high speed train. Mechanical Systems and Signal Processing, 2017, 87: 401-409 doi: 10.1016/j.ymssp.2016.10.034 [151] Kuo C F J, Lai C Y, Kao C H, Chiu C H. Integrating image processing and classification technology into automated polarizing film defect inspection. Optics and Lasers in Engineering, 2018, 104: 204-219 doi: 10.1016/j.optlaseng.2017.09.017 [152] Zhou Y M, Wu K, Meng Z J, Tian M J. Fault detection of aircraft based on support vector domain description. Computers & Electrical Engineering, 2017, 61: 80-94 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=41bc4d9c416c7d57bf40db501561f67a [153] Ding J M. Fault detection of a wheelset bearing in a high-speed train using the shock-response convolutional sparse-coding technique. Measurement, 2018, 117: 108-124 doi: 10.1016/j.measurement.2017.12.010 [154] Hameed Z, Hong Y S, Cho Y M, Ahn S H, Song C K. Condition monitoring and fault detection of wind turbines and related algorithms: A review. Renewable and Sustainable Energy Reviews, 2009, 13(1): 1-39 [155] Chen L C, Papandreou G, Kokkinos I, Murphy K, Yuille A L. DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(4): 834-848 doi: 10.1109/TPAMI.2017.2699184 [156] He K M, Gkioxari G, Dollár P, Girshick R. Mask R-CNN. In: Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV). Venice, Italy: IEEE, 2017. 2980-2988 [157] Ren S Q, He K M, Girshick R, Sun J. Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39(6): 1137-1149 [158] Redmon J, Farhadi A. YOLO9000: Better, faster, stronger. In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, USA: IEEE, 2017. 6517-6525 [159] Fu C Y, Liu W, Ranga A, Tyagi A, Berg A C. DSSD: Deconvolutional single shot detector. arXiv preprint arXiv: 1701.06659, 2017 [160] Shen Z Q, Liu Z, Li J G, Jiang Y G, Chen Y R, Xue X Y. DSOD: Learning deeply supervised object detectors from scratch. In: Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV). Venice, Italy: IEEE, 2017. 1937-1945 [161] Lin T Y, Dollár P, Girshick R B, He K M, Hariharan B, Belongie S. Feature pyramid networks for object detection. In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, HI, USA: IEEE, 2017. 936-944 [162] Lin T Y, Goyal P, Girshick R, He K M, Doll´ar P. Focal loss for dense object detection. In: Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV). Venice, Italy: IEEE, 2017. 2999−3007 [163] Ouyang W L, Wang K, Zhu X, Wang X G. Chained cascade network for object detection. In: Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV). Venice, Italy: IEEE, 2017. 1956−1964 [164] Bodla N, Singh B, Chellappa R, Davis L S. Soft-NMSimproving object detection with one line of code. In: Proceedings of the 2017 IEEE International Conference on Computer Vision. Venice, Italy: IEEE, 2017. 5562−5570 [165] Hu H, Gu J Y, Zhang Z, Dai J F, Wei Y C. Relation networks for object detection. In: Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA: IEEE, 2018. 3588−3597 -
