首页 | 本学科首页   官方微博 | 高级检索  
     

基于形变模型由立体序列图象恢复物体的3D形状
引用本文:夏利民,谷士文,曾三友. 基于形变模型由立体序列图象恢复物体的3D形状[J]. 计算机工程, 2001, 27(10): 22-23,58
作者姓名:夏利民  谷士文  曾三友
作者单位:1. 中南大学铁道校区信息学院
2. 株洲工学院计算机系
基金项目:国家自然科学基金(69975003),湖南省自然科学基金,资助项目(99JJY20058)
摘    要:结合立体视觉和形变模型提出了一种新的物体3D形状的恢复方法。采用立体视觉方法导出物体表面的3D坐标;利用光流模型估计物体的3D运动,根据此运动移动形变模型,使其对准物体的表面块;由形变模型将由各幅图象得到的离散的3D点融为一起,得到物体的表面形状。实验结果表明该方法能用于形状复杂的物体恢复。

关 键 词:3D形状 立体视觉 形变模型 立体序列图象恢复物体 计算机视觉
文章编号:1000-3428(2001)10-0022-02

3D Shape Recovery from a Sequence of Stereo Images Based on Deformable Models
XIA Limin,GU Shiwen,ZENG Sanyou. 3D Shape Recovery from a Sequence of Stereo Images Based on Deformable Models[J]. Computer Engineering, 2001, 27(10): 22-23,58
Authors:XIA Limin  GU Shiwen  ZENG Sanyou
Affiliation:XIA Limin1,GU Shiwen1,ZENG Sanyou2
Abstract:A method is presented for recovering the 3D shape of objects from a sequence of stereo images, which integrates shape from stereo and deformable model . Scene point correspondence required for deriving the depth of the scene point is determined using Immune algorithm .The object shape is described by a deformable surface model, which successively fuses surface patches computed from each pair of stereo images through deformation. Aligned with the input surface path according to the object or camera motion, the model is deformed by attracting its corresponding surface towards the input surface patch. Object motion between successive pairs of stereo images is estimated by tracking a set of image features. Experimental results are also included to show the feasibility of our new method.
Keywords:D shape  Stereo  Deformable model
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号