CASIA OpenIR  > 智能感知与计算研究中心
Deformable Object Matching via Deformation Decomposition based 2D Label MRF
Liu KW(刘康伟); Zhang JG(张俊格); Huang KQ(黄凯奇); Tan TN(谭铁牛); Huang KQ(黄凯奇)
2014-06
Conference Name2014 IEEE Conference on Computer Vision and Pattern Recognition
Source PublicationIEEE Conference on Computer Vision and Pattern Recognition
Conference Date2014-6
Conference Place美国
Abstract
Deformable object matching, which is also called elastic matching or deformation matching, is an important and challenging problem in computer vision. Although numerous deformation models have been proposed in different matching tasks, not many of them investigate the intrinsic physics underlying deformation. Due to the lack of physical analysis, these models cannot describe the structure changes of deformable objects very well. Motivated by this, we analyze the deformation physically and propose a novel deformation decomposition model to represent various deformations. Based on the physical model, we formulate the matching problem as a two-dimensional label Markov Random Field. The MRF energy function is derived from the deformation decomposition model. Furthermore, we propose a two-stage method to optimize the MRF energy function. To provide a quantitative benchmark, we build a deformation matching database with an evaluation criterion. Experimental results show that our method outperforms previous approaches especially on complex deformations.
Other Abstract
变形物体匹配,又称为变形匹配或者弹性匹配,是计算机视觉中一个非常重要且极具挑战性的问题。正如第二章所介绍,变形物体匹配是物体识别中的关键技术,它在物体识别的很多任务,如物体分类,物体检测中都有重要的应用。在本章中,我们主要研究如何对变形物体的进行结构化建模,以及如何利用结构匹配模型进行物体识别任的问题。一般来说,变形匹配任务主要涉及如何在两幅包含复杂变形的图像中找到相互之间的对应关系的研究。尽管在过去几十年中,大量的形变模型在不同的匹配任务中提出来,然而却很少有模型深入研究物体变形的物理机理。由于变形机理分析的缺失,这些模型无法很好地描述变形物体复杂的结构变化;另一方面,具有不同物理属性的物体(如人体和人脸)的变形方式相差很大。由于这些结构模型缺少对物体形变内在物理属性的建模和研究,无法处理具有不同特性的物体的形变。为了解决这个问题,我们从物理角度对物体的变形机理进行,并提出一个变形分解模型来描述复杂和多样的物体变形。基于这个物理形变模型,我们把变形物体匹配任务归纳为一个求解二维标号的马尔可夫随机场(Markov Random Field)问题。其中,随机场结构模型的能量函数由变形分解模型推导得出。为了提供一个评价匹配模型效果的基准,我们构建了一个形变匹配数据库,并提出一个有效的变形匹配评价准则。最后,我们将所提出的形变结构模型应用在两个具有挑战性的物体识别任务(手写体识别和变形物体检测)中,并得到可观的效果。
Keyword变形物体匹配 马尔科夫随机场
Indexed ByEI
Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/11827
Collection智能感知与计算研究中心
Corresponding AuthorHuang KQ(黄凯奇)
Affiliation中国科学院自动化研究所
Recommended Citation
GB/T 7714
Liu KW,Zhang JG,Huang KQ,et al. Deformable Object Matching via Deformation Decomposition based 2D Label MRF[C],2014.
Files in This Item: Download All
File Name/Size DocType Version Access License
kwl_CVPR_Final.pdf(582KB)会议论文 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
[Liu KW(刘康伟)]'s Articles
[Zhang JG(张俊格)]'s Articles
[Huang KQ(黄凯奇)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Liu KW(刘康伟)]'s Articles
[Zhang JG(张俊格)]'s Articles
[Huang KQ(黄凯奇)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Liu KW(刘康伟)]'s Articles
[Zhang JG(张俊格)]'s Articles
[Huang KQ(黄凯奇)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: kwl_CVPR_Final.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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