| 基于二维成像的三维物体形状特征分析 |
| |
| 引用本文： | 郭宇晨,马惠敏,廖庆敏.基于二维成像的三维物体形状特征分析[J].清华大学学报(自然科学版),2009(10). |
| |
| 作者姓名： | 郭宇晨 马惠敏 廖庆敏 |
| |
| 作者单位： | 清华大学电子工程系; |
| |
| 基金项目： | 国家自然科学基金资助项目(60502013);;国家“八六三”高技术项目(2006AA01Z115) |
| |
| 摘 要： | 目前三维物体识别方法在识别过程中所需数据量大、难以实用。该文简化三维物体识别过程,构建了一个基于单视点二维投影图像的三维物体识别系统。分别选取Zernike矩、基于Trace变换的Triple特征、MSA等三种形状特征,实现了对物体的视点空间的聚类划分。在普林斯顿三维模型库上,通过分类识别实验分析三种形状特征的性能。实验表明:特征对不同类别物体的分类效果差异明显。该文由此提出了针对目标物体形状及应用环境的特征选取方案。
|
| 关 键 词： | 模式识别 形状特征分析 Zernike矩 Triple特征 MSA特征 |
Shape features for projected 2D images based 3D object recognition |
| |
| GUO Yuchen,MA Huimin,LIAO Qingmin.Shape features for projected 2D images based 3D object recognition[J].Journal of Tsinghua University(Science and Technology),2009(10). |
| |
| Authors: | GUO Yuchen MA Huimin LIAO Qingmin |
| |
| Institution: | Department of Electronic Engineering;Tsinghua University;Beijing 100084;China |
| |
| Abstract: | Most 3D object recognition methods need too much information for the recognition process so they are not practical for real applications.This paper presents a 3D recognition system based on a single projected 2D image to simplify the 3D recognition process.The system uses zernike moments,trace transformations,and multi-scale autoconvolution for the clustering based viewpoint space partitioning.A shape analysis of the Princeton shape benchmark is used to investigate the recognition of the three features on d... |
| |
| Keywords: | pattern recognition shape feature analysis Zernike Triple MSA |
| 本文献已被 CNKI 等数据库收录！ |
