SIA OpenIR  > 智能产线与系统研究室
基于视觉传感器系统的管道车辆纠偏方法
Alternative TitleVision sensor system based pipeline vehicle pose deviation correction method
赵吉宾; 陈月玲; 齐智峰
Department装备制造技术研究室
Rights Holder中国科学院沈阳自动化研究所
Patent Agent沈阳科苑专利商标代理有限公司 21002
Country中国
Subtype发明
Status有权
Abstract

本发明涉及一种基于视觉传感器系统的管道车辆纠偏方法。其步骤为:对相机和结构光进行标定,得到相机内参数以及光平面参数;对采集的图像进行高斯平滑,去除噪声干扰;利用阈值分割对高斯平滑后的图像进行前景图像提取;通过形态学分析和轮廓大小特征去除光条纹附近的杂点;对得到的光条纹进行去畸变,分别计算两个光条纹所有点在相机坐标系下的三维点坐标;通过得到的三维点坐标计算车体的偏差信息;根据得到的偏差信息对车体进行在线实时纠偏,不断消除位姿偏差,将车体纠正道管道的中心线上。本发明克服了实际管道中缺乏道路信息以及无标志点机器车体无法进行直线行走的困难,检测速度快,可以实现实时导航控制,具有较高的检测精度。

Other AbstractThe method involves locating and connecting a camera with a line structure light sensor. A middle shaft is connected with a side part of a vehicle along vertical direction. An image collecting process is carried out by utilizing the camera. The collected image is stored in a digital storage. A collected image processing process is carried out to remove noise and interference. Image pixel coordinate value of a non-zero binary profile is calculated. A vehicle position deviation eliminating process is carried out.
PCT Attributes
Application Date2015-05-21
2017-01-04
Date Available2018-12-14
Application NumberCN201510266288.1
Open (Notice) NumberCN106292653A
Language中文
Contribution Rank1
Document Type专利
Identifierhttp://ir.sia.cn/handle/173321/19736
Collection智能产线与系统研究室
Affiliation中国科学院沈阳自动化研究所
Recommended Citation
GB/T 7714
赵吉宾,陈月玲,齐智峰. 基于视觉传感器系统的管道车辆纠偏方法[P]. 2017-01-04.
Files in This Item: Download All
File Name/Size DocType Version Access License
CN201510266288.1.pdf(690KB)专利 开放获取CC BY-NC-SAView Download
CN201510266288.1授权.p(834KB)专利 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[赵吉宾]'s Articles
[陈月玲]'s Articles
[齐智峰]'s Articles
Baidu academic
Similar articles in Baidu academic
[赵吉宾]'s Articles
[陈月玲]'s Articles
[齐智峰]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[赵吉宾]'s Articles
[陈月玲]'s Articles
[齐智峰]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: CN201510266288.1.pdf
Format: Adobe PDF
File name: CN201510266288.1授权.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.