确定对象单目视觉位姿检测算法的研究

中国机械工程 ›› 2010, Vol. 21 ›› Issue (23): 2825-2829.

确定对象单目视觉位姿检测算法的研究

刘凌云;钱新恩;罗敏

湖北汽车工业学院，十堰，442002

出版日期:2010-12-10 发布日期:2010-12-15
基金资助:
湖北省教育厅资助项目(B200723002)；湖北省自然科学基金资助项目(2007ABA389)
Hubei Provincial Program of Ministry of Education of China（No. B200723002）;
Hubei Provincial Natural Science Foundation of China（No. 2007ABA389）

Study on Pose Detection Algorithm for Specific Object Based on Monocular Vision

Liu Lingyun;Qian Xinen;Luo Min

Hubei Automotive Industries Institute, Shiyan,Hubei, 442002

Online:2010-12-10 Published:2010-12-15
Supported by:

Hubei Provincial Program of Ministry of Education of China（No. B200723002）;
Hubei Provincial Natural Science Foundation of China（No. 2007ABA389）

摘要/Abstract

摘要：

针对确定作业对象的位姿检测，提出一种基于Hausdorff距离的单目视觉检测算法，即首先依据建立的数学模型构建作业对象在虚拟摄像机下成像的二维模板序列;接着在图像匹配时为降低计算量及加快图像匹配速度，以部分Hausdorff距离作为匹配测度，采用阈值法先行的分层搜索策略进行检测。通过对不同位姿下的夹紧块影像进行检测实验，结果证明了该算法的有效性和快速性。



关键词:

单目视觉, 位姿检测, CAD建模, 分层搜索, 部分Hausdorff距离

Abstract:

This paper brought forward a monocular vision detection algorithm in allusion to a specific object's pose based on Hausdorff Distance. At first, according to the established mathematic model, a 2D template sequence was generated by projecting the specific object in different poses into the image plane of a virtual camera. Then, in order to predigest calculations and accelerate the matching speed during the image matching, the algorithm adopted the local-mean Hausdorff Distance as matching estimation and adopted the search strategy based on hiberarchy which reduced the searching rang by the threshold method before accurate match. The experiments that measured the poses of the clamp via the different clamp images respectively were given to testify the validity and speediness of this algorithm. 

Key words: monocular vision, pose detection, CAD modeling, search strategy of hiberarchy, local-mean , Hausdorff distance

中图分类号:

TP29

刘凌云, 钱新恩, 罗敏.

确定对象单目视觉位姿检测算法的研究

[J]. 中国机械工程, 2010, 21(23): 2825-2829.

LIU Ling-Yun, JIAN Xin-En, LUO Min.

Study on Pose Detection Algorithm for Specific Object Based on Monocular Vision

[J]. China Mechanical Engineering, 2010, 21(23): 2825-2829.