CASIA OpenIR  > 毕业生  > 硕士学位论文
Alternative TitleMathematical Modeling of RHT and RANSAC Algorithm in Geometric Primitive Extraction
Thesis Advisor胡占义
Degree Grantor中国科学院自动化研究所
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数学建模 随机hough变换(Rht) 纯随机方法(Ransac) Mathematical Modeling Randomized Hough Transform(Rht) Random Sample Consensus(Sansac)
Abstract几何基元*提取是机器人视觉领域最根本的问题之一。它是任何计算机视觉系统 以至任何计算机视觉问题的关键组成部分和基本要求。Hough变换(HT)和基于代价 函数全局优化的方法是目前文献中应用最广的两类几何基元提取方法。Hough变换的 基本思想是通过证据积累来提取基元,其典型代表是随机Hough变换(RHT)。基于代 价函数全局优化的基元提取方法是一种反复求取代价函数的过程,尽管有很多不同形 式,但理论基础都是纯随机方法(RANSAC)。文献中对这两类方法有大量报道,并对 这两类方法在基元提取中的优劣有不少争议。但遗憾的是到目前为止,文献中很少有 上述两类方法数学建模的报道,这样就很难对这两类方法给出一种客观的评价。本文 旨在建立随机Hough变换和纯随机方法的数学模型,并在此基础上对RHT和RANSAC 在基元提取中的性能进行理论分析和比较。
Other AbstractHough transform (HT) and techniques based on global optimization are the two most popular families of technique for geometric primitive extraction in the literature. Hough transform relies basically on an evidence accumulation process to extract primitives, its best representative is the randomized Hough transform (RHT). The global optimization based techniques extract primitives via a repeated cost function evaluation process, their common theoretical basis is the Random Sample Consensus (RANSAC) though there exist quite a number of variants. In the literature, although there exist many reports and some controversial comparisons on the performance of the two families of technique, to our best knowledge, there is rarely work on mathematical modeling of the two families of technique hence the comparisons can only be piecemeal or biased. The objective of this paper is to establish mathematical models for RHT and RANSAC, and give a theoretical comparison between them.
Other Identifier575
Document Type学位论文
Recommended Citation
GB/T 7714
李军. 随机Hough变换和纯随机方法在几何基元提取中的数学建模[D]. 中国科学院自动化研究所. 中国科学院自动化研究所,2000.
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
[李军]'s Articles
Baidu academic
Similar articles in Baidu academic
[李军]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[李军]'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.