Uncalibrated Method for Disparity Map of Tool Wear Images

doi:10.7652/xjtuxb201603002

您当前的位置：

首页 >

文章列表页 >

Uncalibrated Method for Disparity Map of Tool Wear Images

更新时间：2025-07-09

- Uncalibrated Method for Disparity Map of Tool Wear Images
- Vol. 50, Issue 3, Pages: 8-15(2016)
- 作者机构：
  
  西安交通大学现代设计及转子轴承系统教育部重点实验室,西安,710049
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb201603002
  CLC： TH113.2
- Online First：10 March 2016，
  
  Published：2016
- 稿件说明：
移动端阅览
Uncalibrated Method for Disparity Map of Tool Wear Images[J]. 2016, 50(3): 8-15.
DOI：

Uncalibrated Method for Disparity Map of Tool Wear Images[J]. 2016, 50(3): 8-15. DOI： 10.7652/xjtuxb201603002.

摘要

刀具磨损检测的视场范围很小、现场工况复杂(存在机床护罩和刀具保持架的遮挡)

而以往对摄像机进行标定的方法多用于大视场环境

并不适合于加工现场的刀具磨损检测。为此

文中提出一种采用非标定双目视觉方法获取刀具磨损图像视差图的方法

无需标定参考物和人工干预。首先

利用SURF(speeded-up robust features)算法检测图像对中的特征点; 其次

利用8点算法计算基本矩阵

再利用极点无穷远变换完成图像对的校正; 最后

利用基本区域匹配方法完成图像对视差的计算。进行了加工现场的磨损刀具图像获取实验

先对比了重构出的刀具视差图轮廓与实际轮廓

接着分析了刀具视差图的精度。结果显示

重构轮廓与实际轮廓基本相符

重构出的视差图的绝对误差在5个像素点以下

相对误差在10%至30%之间

说明在小视场和复杂工况下

用非标定方法获取的刀具视差图能够满足现场检测的精度要求

并且该方法具有灵活和高效的特点。

Abstract

The field of view of tool wear detection is small

and the site condition is complex(e.g.

the blocking of machine cover and tool holder exists). Whereas the traditional method that needs camera calibration is mostly used in large field of view

which is not suitable for on-site tool wear detection. An uncalibrated method based on binocular vision is proposed in this paper for obtaining the disparity map of tool wear images without calibration reference or man-induced intervention. Firstly

SURF(speeded-up robust features)algorithm is used to detect the images' feature points. Then

the 8-point algorithm is adopted to estimate the fundamental matrix; next

image correction is completed by pole infinity transform. Finally

the disparity map is obtained by basic block matching algorithm. On-site experiments were conducted to obtain the tool wear images

and the analysis on profile and accuracy of the reconstructed disparity map was performed. The results show that the reconstructed profile is basically consistent with the actual profile; the absolute error of the reconstructed disparity map is less than 5 pixels and the relative error is between 10% and 30%

meaning that the disparity map obtained by the uncalibrated method in small field of view and complex site condition can meet the accuracy requirement for on-site detection

and this method is also flexible and effective.

关键词

Keywords

references

CERCE L, PUSAVEC F, KOPAC J. 3D cutting tool-wear monitoring in the process [J]. Journal of Mechanical Science and Technology, 2015, 29(9): 3885-3895.

WANG Z, LI B, ZHOU Y. Fast 3D reconstruction of tool wear based on monocular vision and multi-color structured light illuminator [C]∥Proceedings of International Symposium on Optoelectronic Technology and Application. Bellingham, WA, USA: SPIE, 2014: 93011D.

FORSYTH D, PONCE J. Computer vision: a modern approach [M]. 2nd ed. New York, USA: Pearson, 2011: 32-43.

张铖伟, 王彪, 徐贵力. 摄像机标定方法研究 [J]. 计算机技术与发展, 2010, 20(11): 174-179.

ZHANG Chengwei, WANG Biao, XU Guili. Research of camera calibration methods [J]. Computer Technology and Development, 2000, 20(11): 174-179.

ZHOU F, CUI Y, WANG Y, et al. Accurate and robust estimation of camera parameters using RANSAC [J]. Optics and Lasers in Engineering, 2013, 51(3): 197-212.

刘亚菲. 大型工件焊接双目视觉测量及精度研究 [D]. 上海: 华东理工大学, 2013.

王琳, 赵健康, 夏轩, 等. 基于双目立体视觉技术的桥梁裂缝测量系统 [J]. 计算机应用, 2015, 35(3): 901-904.

WANG Lin, ZHAO Jiankang, XIA Xuan, et al. Bridge crack measurement system based on binocular stereo vision technology [J]. Journal of Computer Applications, 2015, 35(3): 901-904.

许薛军, 张肖宇. 基于双目视觉的公路边坡表面位移识别方法 [J]. 中国公路学报, 2015, 28(4): 27-34.

XU Xuejun, ZHANG Xiaoyu. Highway slope displacement identification method based on binocular vision [J]. China Journal of Highway and Transport, 2015, 28(4): 27-34.

WANG Z, WU Z, ZHEN X, et al. A two-step calibration method of a large FOV binocular stereovision sensor for onsite measurement [J]. Measurement, 2015, 62(2): 15-24.

HARTLEY R, ZISSERMAN A. Multiple view geometry in computer vision [M]. 2nd ed. Cambrige, England, UK: Cambridge University Press, 2004: 295-305.

BAY H, ESS A, TUYTELAARS T, et al. Speeded-up robust features(SURF)[J]. Computer Vision and Image Understanding, 2008, 110(3): 346-359.

LONGUET-HIGGINS H C. A computer algorithm for reconstructing a scene from two projections [J]. Nature, 1981, 293(36): 133-135.

HASSEN W, AMIRI H. Block matching algorithms for motion estimation [C]∥Proceedings of IEEE International Conference on e-Learning in Industrial Electronics. Piscataway, NJ, USA: IEEE, 2013: 136-139.[14] 胡浩强. 基于不完整信息图像融合的刀具磨损检测技术研究 [D]. 西安: 西安交通大学, 2015.

张鹏,陈湘军,阮雅端,等.采用稀疏SIFT特征的车型识别方法.2015,49(12):137-143.[doi:10.7652/xjtuxb201512 022]

崔汪莉,卫军胡,纪鹏,等.基于加权局部梯度直方图的头部三维姿态估计.2015,49(11):71-76.[doi:10.7652/xjtuxb 201511012]

周远,周玉生,刘权,等.一种适用于图像拼接的DSIFT算法研究.2015,49(9):84-90.[doi:10.7652/xjtuxb201509015]

刘凯,张立民,孙永威,等.利用深度玻尔兹曼机与典型相关分析的自动图像标注算法.2015,49(6):33-38.[doi:10.7652/xjtuxb201506006]

朱爱斌,胡浩强,何大勇,等.采用频域融合方法的砂轮刀具磨损三维重构技术.2015,49(5):82-86.[doi:10.7652/xjtuxb201505013]

郝雯洁,齐春.一种鲁棒的稀疏信号重构算法.2015,49(4):98-103.[doi:10.7652/xjtuxb201504016]

范优飞,胡红利,杨帆,等.一种48电极可配置电容层析成像系统模型.2015,49(4):110-115.[doi:10.7652/xjtuxb2015 04018]

唐晓庆,范赐恩,刘鑫.基于边缘保持滤波的单幅图像快速去雾.2015,49(3):143-150.[doi:10.7652/xjtuxb201503022]

刘天良,郑海红,罗圣美,等.改进的混合动静态背景的分割方法.2015,49(2):25-30.[doi:10.7652/xjtuxb201502005]

李鹏,杨旸,方涛.应用视觉显著性的快速有偏聚类超像素算法.2015,49(1):112-117.[doi:10.7652/xjtuxb201501019]

杨晔,潘希德,庄健.一种针对超声检测图像的自适应阈值设置方法.2015,49(1):127-132.[doi:10.7652/xjtuxb201501 021]

陈倩倩,张磊,徐刚,等.利用多通道联合稀疏重建的干涉逆合成孔径雷达三维成像算法.2014,48(12):100-106.[doi:10.7652/xjtuxb201412016]

侯兴松,张兰.方向提升小波变换域稀疏滤波的自然图像贝叶斯压缩感知.2014,48(10):15-21.[doi:10.7652/xjtuxb 201410003]

李博,冯松,毛军红.在线图像可视铁谱LED阵列反射光源设计与实现.2014,48(10):29-34.[doi:10.7652/xjtuxb2014 10005]

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Binocular Visual Measurement Method for Rotational Errors

Three-Dimensional Reconstruction of Tool Wear Area Considering Transform-Domain Fusion

A Binocular-Vision-Based Method for Measuring the 3D Strain Field on Cylindrical Surfaces Integrating Geometric Prior Knowledge

Energy Efficiency Optimization of the Cryogenic Air Separation Process for Electronic-Grade Ultra Pure Nitrogen

Influence of Structural Parameters on the Summer Operational Characteristics of a Three-Tower-in-One Indirect Air-Cooling System

Related Author

HONG Jun

LI Xiaohu

HUI Jizhuang

ZHANG Chi

LÜ Jingxiang

ZHAO Qiangqiang

YU XinPing

SUN Yanhui

Related Institution

Key Laboratory of Road Construction Technology and Equipment of Ministry of Education, Chang’an University

Qinchuan Machine Tool&Tool Group Corp

School of Mechanical Engineering, Xi’an Jiaotong University

School of Aerospace Engineering, Xi'an Jiaotong University

State Key Laboratory for Strength and Vibration of Mechanical Structures, Xi'an Jiaotong University

⁰