期刊文献+

基于机器视觉的飞机蒙皮表面缺陷检测方法综述

Review of Aircraft Skin Surface Defect Detection Methods Based on Machine Vision
原文传递
导出
摘要 飞机蒙皮缺陷是影响飞机正常运行的关键因素之一,及时准确地检测出飞机蒙皮表面的缺陷能够有效的避免飞行事故的发生。目前针对飞机蒙皮表面缺陷检测的方法主要是目视检测或者一些接触类检测方法,这些方法存在漏检率高,风险大等问题。基于机器视觉的检测方法因其检测速度快,非接触式检测,检测精度高等优点,近来得到较多的关注。总结了现有的飞机蒙皮表面缺陷的检测方法,并着重介绍了两类基于机器视觉的缺陷检测方法,即基于传统视觉的方法和基于深度学习的方法,并详细分析了其基本原理、优缺点以及相关的应用算法。对基于机器视觉的飞机蒙皮表面缺陷检测方法进行了总结,对其未来的发展进行了展望。 Aircraft skin defects are one of the key factors affecting the normal operation of aircraft.Timely and accurate detection of aircraft skin defects can effectively avoid the occurrence of flight accidents.At present,the main detection methods for aircraft skin surface defects are visual detection or some contact detection methods,which have high misdetection rate and high risk.Detection methods based on machine vision have received more attention recently because of their advantages such as fast detection speed,non-contact detection and high detection accuracy.This paper summarizes the existing detection methods of aircraft skin surface defects,and focuses on two kinds of defect detection methods based on machine vision,namely the method based on traditional vision and the method based on deep learning,and analyzes its basic principles,advantages and disadvantages and related application algorithms in detail.Finally,the detection methods of aircraft skin surface defects based on machine vision were summarized,and its future development was prospected.
作者 邴皓哲 赵健淇 BING Haozhe;ZHAO Jianqi(Shenyang Aircraft Design&Research Institute,Shenyang 110035,China;Liaoning Province Shiyan High School,Shenyang 110841,China)
出处 《飞机设计》 2024年第3期62-65,80,共5页 Aircraft Design
关键词 缺陷检测 图像处理 机器视觉 深度学习 defect detection image processing machine vision deep learning
  • 相关文献

参考文献8

二级参考文献104

  • 1Thome D K, Fitzpatrick G L, Skaugset R L, et aL Aircraft corrosion and crack inspeetion using advanced magneto-optic imaging technology [ A ]. In: Proceedings of SPIE-The International Society for Optical Engineering[ C ] , Seottsdale, AZ, USA, 1996, 2945 : 365 - 373.
  • 2Ramuhalli P, Slade J, Park U, et al. Modeling and signal processing of magneto-optic images for aviation applications [ A ]. In:Proceedings of ISSS-SPIE International Conference on Smart Materials Structures and Systems [ C ], Bangalore, India, 2002,5062 : 248 - 255.
  • 3Park U, Fan Y, Udpa L, et al. Automated rivet inspection for aging aircraft With magneto-optic imager[ A ]. In: Proceedings of the 10th International Workshop on Electromagnetic Nondestructive Evaluation [ C], East Lansing, Michigan, USA,2004.
  • 4Park U, Udpa L, George C. Motion-based filtering of magneto-optic imagers[ J]. Image and Vision Computing, 2004, 22 ( 3 ) : 243 - 249.
  • 5Simms S. MOI: magneto-optic/eddy current imaging [ J]. Materials Evaluation, 1993,50 ( 5 ) :529 -536.
  • 6Lemistre M, Decitre J M. Corrosion and cracks detection in metallic structures by magneto optic image [ A ]. In: Proceedings of International Conference on Quality Control by Artificial Vision [ C ], Le Creusot, France, 2001:65 - 70.
  • 7Chapelle O, Vapnik V, Bousquet O, et al. Choosing multiple parameters for support vector machine[J]. Machine Learning, 2002, 46(1) :131 - 159.
  • 8Vapnik V, Chapelle O. Bounds on error expectation for support vector machine [ J ]. Neural Computation, 2000, 12 (9) : 2013 - 2036.
  • 9Fitzpatrick G L, Thome D K, Skaugset R L, et al. Magneto-optic/ eddy current imaging of aging aircraft: a new NDI technique [J]. Materials Evaluation, 1993, 51 (12) : 1402 - 1407.
  • 10高庆吉,胡丹丹,牛国臣,邢志伟.基于磁光图像的飞机铆钉缺陷识别[J].中国图象图形学报,2007,12(12):2179-2183. 被引量:7

共引文献578

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部