CASIA OpenIR  > 毕业生  > 硕士学位论文
Alternative TitleResearch on Cell Detection and Cell Tracking i n Vision System for Cell Micromanipulation
Thesis Advisor胡包钢
Degree Grantor中国科学院研究生院
Place of Conferral中国科学院自动化研究所
Degree Discipline模式识别与智能系统
Keyword细胞检测 细胞跟踪 Condensation 视觉伺服 Cell Detection Cell Tracking Condensation Visual Servo
Abstract实现自动化的细胞注射是生物研究工作者所希望的,因为它降低了工作强度,无污染,操作具有重复性,因而极大的提高了工作效率。对于自动化的细胞注射任务,带有视觉伺服的微操作系统是一个有效的解决方案。为了满足视觉伺服的要求,图象的特征抽取和跟踪必须是鲁棒、准确、可实时计算的。 本论文的研究是受国家863项目资助,目标是与为北航微操作机器人设计一 套视觉系统。与此相关需要解决的,是两个基本的计算机视觉问题:目标检测和 目标跟踪。针对微操作视觉系统的要求,本文提出了一个针对细胞的目标检测算 法和跟踪算法。细胞检测算法结合了形态学连通算子,基于不变性的形状描述和 基于MRSAR模型的纹理分析方法。对细胞跟踪,我们开发了一个基于CONDENSATION 算法的细胞跟踪方法。同时,我们对原跟踪方法作了适当的改进,使得该跟踪方 法更适合我们的应用。现场实验显示出该方法的有效性。 本文的主要贡献在于完成了一套视觉系统,算法完全依靠软件实现,并应用 到北航的面向生物的微操作机器人上,基本上达到了任务要求。
Other AbstractAn automatic cell injection is desirable for biomedical operators since it is less- intensive, contamination-free, and is highly reproducible, greatly increasing the success rate. For automated cell injection, cell manipulation with visual servoing technology seems to be the choice. To fit visual servoing requirements, cellular image .feature extraction and tracking must be robust, accurate, and computed in real-time. Our research is supported by National 863 Hi-Tech program. We need to develop a vision system for a Cell Micromanipulation robot of BUAA. Two basic computer vision problems, i.e. object detection and object tracking, are closely related to this issue. In this paper, we propose an object detection method, i.e. cell detection, that combines morphological connected operators, invariant shape descriptor, and MRSAR based texture analysis. For object tracking, we developed a method to automatically track cells in microscopic scene based on the Condensation algorithm. We also make an extension to the original Condensation algorithm, so as to make it more appropriate for the aim. In situ experiments showed the effectiveness of this method. The main contribution of this paper is that we developed a vision system, which is completely based on software implementation. The system has been applied to a Cell Micromanipulation robot, and met basic task requirements.
Other Identifier617
Document Type学位论文
Recommended Citation
GB/T 7714
梁立臣. 细胞微操作视觉系统中的细胞检测及跟踪算法的研究[D]. 中国科学院自动化研究所. 中国科学院研究生院,2001.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[梁立臣]'s Articles
Baidu academic
Similar articles in Baidu academic
[梁立臣]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[梁立臣]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.

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