| 基于立体视觉的自由曲面三维重构 |
| |
| 引用本文： | 张可,许斌,唐立新,师汉民.基于立体视觉的自由曲面三维重构[J].华中科技大学学报(自然科学版),2006,34(4):76-78. |
| |
| 作者姓名： | 张可 许斌 唐立新 师汉民 |
| |
| 作者单位： | 1. 华中科技大学,国家数控系统工程技术研究中心,湖北,武汉,430074
2. 华中科技大学,机械科学与工程学院,湖北,武汉,430074 |
| |
| 基金项目： | 中国科学院资助项目;广东省博士启动基金 |
| |
| 摘 要： | 利用BP神经网络对立体视觉系统进行隐式标定,采用投射大小光斑的方法增加自由曲面的图像特征;提出了一种基于射影变换原理的分块匹配算法,分别在左右两幅图像上,对大点构成的区域进行标准形状变换,然后实现区域内小点的自动匹配.对石膏像面部进行三维重构的实验表明,投射光斑的方法增加了自由曲面的图像特征,分块匹配算法能有效地实现图像间的特征匹配.
|
| 关 键 词： | BP神经网络 射影变换 光斑投射 分块匹配 |
| 文章编号： | 1671-4512(2006)04-0076-03 |
| 收稿时间： | 03 14 2005 12:00AM |
| 修稿时间： | 2005年3月14日 |
Reconstruction of 3D free-form surfaces based on stereo vision |
| |
| Zhang Ke,Xu Bin,Tang Lixin,Shi Hanmin.Reconstruction of 3D free-form surfaces based on stereo vision[J].JOURNAL OF HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY.NATURE SCIENCE,2006,34(4):76-78. |
| |
| Authors: | Zhang Ke Xu Bin Tang Lixin Shi Hanmin |
| |
| Abstract: | The implicit calibration was applied to the stereo vision system using BP neural network. The image features of a free-form surface were enhanced by means of projecting big and small dots. On the basis of projective transformation, an area matching algorithm was presented. After the shapes of areas formed by big dots were transformed into standard shapes (for example, square) on the left and right images respectively, all the small dots within the standard area were matched automatically with their corresponding partners within the templet standard area. The experiments of 3D reconstruction of plaster model indicated that the dot projection enhances the image features of the free-form surface and the area matching approach performs matching effectively between the images. |
| |
| Keywords: | BP neural network projective transformation dot projection area matching |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
