基于机器视觉的汽车组合仪表读数识别技术研究
|
摘要
汽车组合仪表是汽车中不可缺少的组成部分,负责记录和显示汽车的各种数据。根据汽车领域对汽车组合仪表美观、多功能、轻型化的要求,汽车仪表生产和检测的自动化程度需要大大提高。目前在汽车仪表检测中通常采用人工观测各表针与刻度之间的压线情况、报警灯点亮情况、以及是否有外观缺陷来检验仪表,判断产品质量是否合格。这种方法受主观因素、观测距离及疲劳程度影响严重,容易产生误差,可靠性差。数字图像处理技术的快速发展,使得机器视觉技术开始被应用于汽车组合仪表的检测中。
本课题旨在基于机器视觉技术,采用图像处理的方法实现汽车组合仪表读数的自动识别,代替人工识别这一枯燥劳累、可靠性差的方法。本文首先介绍了机器视觉及汽车组合仪表的概念和发展应用现状。接下来阐述了图像采集和图像处理的总体方案。然后详细介绍了表盘读数识别的图像处理理论和方法,研究了图像预处理的方法,通过灰度化、滤波、二值化,使图像质量有了很大提高;提出区域标记和基于指针区域面积、形状、颜色特征提取指针区域,并取得良好效果;采用Hough变换和最小二乘法实现直线提取;采用角度法和数字法两种确定读数的方法,并提出以过线数为特征进行二级数字识别,快速有效;将组合仪表排列方式分为相连和独立两类,提出不同的分割方法将组合仪表图像分割为单个表盘的分割方法。
本文在详细的分析图像处理算法基础上,在MATLAB平台上编制了汽车组合仪表读数识别软件,并通过实验验证该软件的速度和准确性,并分析了误差的来源,准确性可基本满足实际要求,速度有待提高,具有一定的应用价值。
Automobile Instrument is an indispensable vehicle component, which is responsible for recording and displaying the various data. According to requirements of more beautiful, more functional, and lighter for the Automobile Instrument, manufacturing and testing of Automobile Instrument is supposed to be substantially improved. Now in automotive instrument testing area manpower methods of judging whether the gauge indicators are pressing or between graduation lines, whether the warning lights are lit, whether there are surface defects are commonly used to determine the quality of products. These methods are influenced by subjective factors, detecting range and fatigue degree, which would lead to big errors and poor reliability. As the rapid development of digital image processing technology, computer vision is beginning to be used in Automobile Instrument detection.
Aim of the subject is that based on machine vision technology, image processing methods could be used in automatic identification of Automobile Instrument readings, instead of manually identify which is boring and tired with poor reliability. Firstly, this paper introduces the concepts of machine vision and automobile instrument, development and application in related area. Secondly, overall program of image capture and image processing is described. Thirdly, image processing theory and methods are introduced in detail. Methods of image preprocessing are studied, the image quality is greatly improved by gray level transformation, filtering, binarization etc; region labeling and indicator-region-extraction methods based on size of the area, shape and color feature are propose, and achieved good results; line extraction is achieved by Hough Transform and Least Square Method; the reading is determined in two ways of angle method and number method, and line-cross-method is proposed to identify numbers quickly and effectively; the automobile instrument arrangement is divided into two kinds: linked and independent, different segmentation methods are proposed to divide automobile instrument into single segmentation.
In this paper, based on detailed analysis of image processing algorithm, recognition software for automobile instrument reading is developed on MATLAB platform, the speed and accuracy is verified by experiments,the sources of errors are analyzed. The acuracy can satisfy the practical requirements ,however the speed is to be improved, which is of certain practical value.
本课题旨在基于机器视觉技术,采用图像处理的方法实现汽车组合仪表读数的自动识别,代替人工识别这一枯燥劳累、可靠性差的方法。本文首先介绍了机器视觉及汽车组合仪表的概念和发展应用现状。接下来阐述了图像采集和图像处理的总体方案。然后详细介绍了表盘读数识别的图像处理理论和方法,研究了图像预处理的方法,通过灰度化、滤波、二值化,使图像质量有了很大提高;提出区域标记和基于指针区域面积、形状、颜色特征提取指针区域,并取得良好效果;采用Hough变换和最小二乘法实现直线提取;采用角度法和数字法两种确定读数的方法,并提出以过线数为特征进行二级数字识别,快速有效;将组合仪表排列方式分为相连和独立两类,提出不同的分割方法将组合仪表图像分割为单个表盘的分割方法。
本文在详细的分析图像处理算法基础上,在MATLAB平台上编制了汽车组合仪表读数识别软件,并通过实验验证该软件的速度和准确性,并分析了误差的来源,准确性可基本满足实际要求,速度有待提高,具有一定的应用价值。
Automobile Instrument is an indispensable vehicle component, which is responsible for recording and displaying the various data. According to requirements of more beautiful, more functional, and lighter for the Automobile Instrument, manufacturing and testing of Automobile Instrument is supposed to be substantially improved. Now in automotive instrument testing area manpower methods of judging whether the gauge indicators are pressing or between graduation lines, whether the warning lights are lit, whether there are surface defects are commonly used to determine the quality of products. These methods are influenced by subjective factors, detecting range and fatigue degree, which would lead to big errors and poor reliability. As the rapid development of digital image processing technology, computer vision is beginning to be used in Automobile Instrument detection.
Aim of the subject is that based on machine vision technology, image processing methods could be used in automatic identification of Automobile Instrument readings, instead of manually identify which is boring and tired with poor reliability. Firstly, this paper introduces the concepts of machine vision and automobile instrument, development and application in related area. Secondly, overall program of image capture and image processing is described. Thirdly, image processing theory and methods are introduced in detail. Methods of image preprocessing are studied, the image quality is greatly improved by gray level transformation, filtering, binarization etc; region labeling and indicator-region-extraction methods based on size of the area, shape and color feature are propose, and achieved good results; line extraction is achieved by Hough Transform and Least Square Method; the reading is determined in two ways of angle method and number method, and line-cross-method is proposed to identify numbers quickly and effectively; the automobile instrument arrangement is divided into two kinds: linked and independent, different segmentation methods are proposed to divide automobile instrument into single segmentation.
In this paper, based on detailed analysis of image processing algorithm, recognition software for automobile instrument reading is developed on MATLAB platform, the speed and accuracy is verified by experiments,the sources of errors are analyzed. The acuracy can satisfy the practical requirements ,however the speed is to be improved, which is of certain practical value.
引文
1赵书涛.基于计算机视觉的直读仪表校验方法研究.华北电力大学.硕士学位论文. 2005,12: 1~2
2袁勇.基于机器视觉的轿车仪表自动校验技术与系统开发.上海交通大学.硕士学位论文. 2008,2: 2~3
3黄正权.我国汽车仪表产品进行技术升级的必要性.重型汽车. 2001,6: 10~11
4宋汉冲.我国汽车仪表工业现代化与发展前景分析.中国汽车仪表. 1995,1: 9~10
5刘娜.基于机器视觉的汽车仪表盘的分割研究.广东工业大学.硕士学位论文. 2008,4: 5~6,46~57
6杨杰.基于柔性测试技术的汽车仪表盘终检系统设计.电子测试,2009.11:1~2
7 Sablatnig, Robert; Kropatsch, Walter G. Application constraints in the design of an automatic reading device for analog display instruments. IEEE, Los Alamitos, CA, USA. 1994. P205-212.
8 Sablatnig, Robert; Kropatsch, Walter G. Automatic reading of analog display instruments. IEEE, Piscataway, NJ, USA. 1994, 1. P794-797.
9 Sablatnig, Robert; Hansen, C. Machine vision for automatic calibration of analog display instruments. Society of Photo-Optical Instrumentation Engineers, Bellingham,WA, USA. 1995,2423. P356-366.
10晁阳.基于特征识别的指针式仪表自动识别研究.山东大学.硕士学位论文. 2008,5: 56~63
11 (美)冈萨雷斯(Rafael C. Gonzalez)等.数字图像处理(MATLAB版).电子工业出版社. 2006,4:8~9
12苏金明,王永利. MATLAB图形图像.电子工业出版社. 2005,11: 156~157
13贾永红.数字图像处理.武汉大学出版社. 2003,9: 77~79
14罗军辉,冯平. MATLAB7.0在图像处理中的应用.机械工业出版社. 2005,6: 201~202
15龚雄文.指针式仪表自动读数的研究及应用.广东工业大学.硕士学位论文.2007,4: 9~13
16贺兴华,周媛媛. MATLAB7.x图像处理.人民邮电出版社. 2006,11: 205~206
17于万波.基于MATLAB的图像处理.清华大学出版社. 2007,11: 164~180
18沈庭芝.数字图像处理及模式识别.北京理工大学出版社. 2005,1:34~67
19 (美)Wesley E. Snyder, Hairong Qi等.机器视觉教程.机械工业出版社. 2005,9:2~3
20 Carsten Steger等.机器视觉算法与应用.清华大学出版社. 2007,5:56~60
21孔月萍等.基于组合特征的高效数字识别算法.计算机应用研究. 2006: 1~3
22 Charles Petzold. Programming Windows(Fifth Edition)[M], Microsoft Press,1998
23 Jeffrey Richter. Programming Applications for Microsoft Windows(Fourth Editon), Microsoft Press, 1999
24 Alberto Del Bibo, Pietro Pala. Visual Image Retrial by Elastic Matching of User Sketches .IEEE Transactions on Patern Analysis and Machine Intelligence.Vo1.19 ,No.2,February 1997:121~132
25 Christos Davatzikos. Spatial Transformation and Registration of Brain Images Using Elastically Deformable Models , Computer Vision and Image Understanding. Vo1.66,No.2,May 1 997:207-222
26 Jen-Hui Chang. A Potential-Based Approach for Shape Matching and Recognition .Patern Recognition.Vo1.29,No.31 996:463-470
27 ShiuYin Yuen, Chi Ho Ma. An Investigation of the Nature of Parameterization for the Hough Transform. Pattern Recognition. Vo1.30 .No.6. 1997:1009-1040
28 Gregory Dudek, John K Tsotsos. Shape Representation and Recognition from Multiscale Curvature. Computer Vision and Image Understanding. November Vol. 68,No.2 1997:170-189
29 Shapiro, Stockman. Computer Vision [M]:Mar.2000. Prentice Hall Inc. ,217-2191
30 Alegria, F. Correa; Serra, A. Cruz. Automatic calibration of analog and digital measuring instruments using computer vision. Institute of Electrical and Electronics Engineers Inc, Piscataway, NJ, USA. 2000, 49. P94-99.
31 Cornea Alegria, F; Cruz Serra, A. Computer vision applied to the automatic calibration of measuring instruments. Elsevier Science B.V, Amsterdam, Netherlands. 2000, 28. P185-195.
32 Yi Hong Lin, Feng Yi Liu, Huang Feng Zeng. Machine Vision Applied to the Automatic Calibration System of Analog Display Instrument.台湾省中国机械工程学会第二十一届学术研讨会论文集.2004年11月.
33 Matti Pietikainen, Tomi Nurmela, Topi Maenpaa , Markus turtinen ,View-based Recognition of Reall-world Textures,Pattern Recognition ,2004(37):313~ 323.
34 Lyndon N. Smith, Melvyn L. Smith, Automatic machine vision calibration using statistical and neural network methods Image Vision Computing.2005,(23):887~899.
35 R. Sablatnig , C.Hansen , Machine vision applications in industrial inspection,in: Proceedings of The International Society for Optical Engineering,Vol.2423,San Jose, California, February 8~ 9, 1995, 356~ 366.
36 Buji Atsumi,Kenji Kimura,Yosimasa Ohsumi ,Study of Meter Cluster Location for Visibility Performance. JSAE Review1999,(20):368~ 374.
37 Mark B.Lynch,Cihan H.Dagli, Mahesh Vallenki,The Use of Feedforward Neural Networks for Machine Vision Calibration.Int .J .Production Economics,1999, (60~61):479~489.
38 F .Correa Alegria,A .Cruz Serra .Computer vision applied to the automatic calibration of measuring instruments;Measurement.,2000,(28): 185~195
39 Colin Bradley , Rapid Prototyping Models Generated from Machine Vision Data.Computers in Industry,2001,(44):159~173.
40 Sven Behnke,A Tow-Stage System for Meter Value Recognition. IEEE Int. Conference on Image Processing(ICIP'03),2003 .Vol. I,pp .549~552.
41 Sven Behnke , Meter Value Recognition using Locally Connected Hierarchical Networks. In Proceedings of 11th,European Symposium on Artificial Neural Networks(ESANN’03),2003, pp .535~540.
2袁勇.基于机器视觉的轿车仪表自动校验技术与系统开发.上海交通大学.硕士学位论文. 2008,2: 2~3
3黄正权.我国汽车仪表产品进行技术升级的必要性.重型汽车. 2001,6: 10~11
4宋汉冲.我国汽车仪表工业现代化与发展前景分析.中国汽车仪表. 1995,1: 9~10
5刘娜.基于机器视觉的汽车仪表盘的分割研究.广东工业大学.硕士学位论文. 2008,4: 5~6,46~57
6杨杰.基于柔性测试技术的汽车仪表盘终检系统设计.电子测试,2009.11:1~2
7 Sablatnig, Robert; Kropatsch, Walter G. Application constraints in the design of an automatic reading device for analog display instruments. IEEE, Los Alamitos, CA, USA. 1994. P205-212.
8 Sablatnig, Robert; Kropatsch, Walter G. Automatic reading of analog display instruments. IEEE, Piscataway, NJ, USA. 1994, 1. P794-797.
9 Sablatnig, Robert; Hansen, C. Machine vision for automatic calibration of analog display instruments. Society of Photo-Optical Instrumentation Engineers, Bellingham,WA, USA. 1995,2423. P356-366.
10晁阳.基于特征识别的指针式仪表自动识别研究.山东大学.硕士学位论文. 2008,5: 56~63
11 (美)冈萨雷斯(Rafael C. Gonzalez)等.数字图像处理(MATLAB版).电子工业出版社. 2006,4:8~9
12苏金明,王永利. MATLAB图形图像.电子工业出版社. 2005,11: 156~157
13贾永红.数字图像处理.武汉大学出版社. 2003,9: 77~79
14罗军辉,冯平. MATLAB7.0在图像处理中的应用.机械工业出版社. 2005,6: 201~202
15龚雄文.指针式仪表自动读数的研究及应用.广东工业大学.硕士学位论文.2007,4: 9~13
16贺兴华,周媛媛. MATLAB7.x图像处理.人民邮电出版社. 2006,11: 205~206
17于万波.基于MATLAB的图像处理.清华大学出版社. 2007,11: 164~180
18沈庭芝.数字图像处理及模式识别.北京理工大学出版社. 2005,1:34~67
19 (美)Wesley E. Snyder, Hairong Qi等.机器视觉教程.机械工业出版社. 2005,9:2~3
20 Carsten Steger等.机器视觉算法与应用.清华大学出版社. 2007,5:56~60
21孔月萍等.基于组合特征的高效数字识别算法.计算机应用研究. 2006: 1~3
22 Charles Petzold. Programming Windows(Fifth Edition)[M], Microsoft Press,1998
23 Jeffrey Richter. Programming Applications for Microsoft Windows(Fourth Editon), Microsoft Press, 1999
24 Alberto Del Bibo, Pietro Pala. Visual Image Retrial by Elastic Matching of User Sketches .IEEE Transactions on Patern Analysis and Machine Intelligence.Vo1.19 ,No.2,February 1997:121~132
25 Christos Davatzikos. Spatial Transformation and Registration of Brain Images Using Elastically Deformable Models , Computer Vision and Image Understanding. Vo1.66,No.2,May 1 997:207-222
26 Jen-Hui Chang. A Potential-Based Approach for Shape Matching and Recognition .Patern Recognition.Vo1.29,No.31 996:463-470
27 ShiuYin Yuen, Chi Ho Ma. An Investigation of the Nature of Parameterization for the Hough Transform. Pattern Recognition. Vo1.30 .No.6. 1997:1009-1040
28 Gregory Dudek, John K Tsotsos. Shape Representation and Recognition from Multiscale Curvature. Computer Vision and Image Understanding. November Vol. 68,No.2 1997:170-189
29 Shapiro, Stockman. Computer Vision [M]:Mar.2000. Prentice Hall Inc. ,217-2191
30 Alegria, F. Correa; Serra, A. Cruz. Automatic calibration of analog and digital measuring instruments using computer vision. Institute of Electrical and Electronics Engineers Inc, Piscataway, NJ, USA. 2000, 49. P94-99.
31 Cornea Alegria, F; Cruz Serra, A. Computer vision applied to the automatic calibration of measuring instruments. Elsevier Science B.V, Amsterdam, Netherlands. 2000, 28. P185-195.
32 Yi Hong Lin, Feng Yi Liu, Huang Feng Zeng. Machine Vision Applied to the Automatic Calibration System of Analog Display Instrument.台湾省中国机械工程学会第二十一届学术研讨会论文集.2004年11月.
33 Matti Pietikainen, Tomi Nurmela, Topi Maenpaa , Markus turtinen ,View-based Recognition of Reall-world Textures,Pattern Recognition ,2004(37):313~ 323.
34 Lyndon N. Smith, Melvyn L. Smith, Automatic machine vision calibration using statistical and neural network methods Image Vision Computing.2005,(23):887~899.
35 R. Sablatnig , C.Hansen , Machine vision applications in industrial inspection,in: Proceedings of The International Society for Optical Engineering,Vol.2423,San Jose, California, February 8~ 9, 1995, 356~ 366.
36 Buji Atsumi,Kenji Kimura,Yosimasa Ohsumi ,Study of Meter Cluster Location for Visibility Performance. JSAE Review1999,(20):368~ 374.
37 Mark B.Lynch,Cihan H.Dagli, Mahesh Vallenki,The Use of Feedforward Neural Networks for Machine Vision Calibration.Int .J .Production Economics,1999, (60~61):479~489.
38 F .Correa Alegria,A .Cruz Serra .Computer vision applied to the automatic calibration of measuring instruments;Measurement.,2000,(28): 185~195
39 Colin Bradley , Rapid Prototyping Models Generated from Machine Vision Data.Computers in Industry,2001,(44):159~173.
40 Sven Behnke,A Tow-Stage System for Meter Value Recognition. IEEE Int. Conference on Image Processing(ICIP'03),2003 .Vol. I,pp .549~552.
41 Sven Behnke , Meter Value Recognition using Locally Connected Hierarchical Networks. In Proceedings of 11th,European Symposium on Artificial Neural Networks(ESANN’03),2003, pp .535~540.