北京航空航天大学学报 ›› 2012, Vol. ›› Issue (11): 1517-1521.

• 论文 • 上一篇    下一篇

基于SVDD的三维目标多视点视图建模

丁昊, 李旭东, 赵慧洁   

  1. 北京航空航天大学 精密光机电一体化技术教育部重点实验室, 北京 100191
  • 收稿日期:2011-07-18 出版日期:2012-11-30 发布日期:2012-12-07
  • 基金资助:
    国家自然科学基金资助项目(60802044)

Method of multi-view modeling for 3D target based on SVDD

Ding Hao, Li Xudong, Zhao Huijie   

  1. Precision Opto-mechatronics Technology Key Laboratory of Education Ministry, Beijing University of Aeronautics and Astronautics, Beijing 100191, China
  • Received:2011-07-18 Online:2012-11-30 Published:2012-12-07

摘要: 同一目标在不同观察视点下成像后外形可能有较大差异,因此三维目标多视点视图建模是目标识别的关键.针对该问题,提出了基于支持向量数据描述(SVDD, Support Vector Data Description)方法对目标特征进行描述.在视点球面上均匀采样获取目标全姿态图像,以SVDD方法求取在高维空间内包含尽可能多目标特征向量的最小超球体相关参数,得到数量较少的支持向量将作为目标多视点视图的最佳模型.对多类目标不同姿态的图像(每类2592帧),以规则化不变矩描述目标外形特征,进行了建模实验,并通过识别实验验证了所提方法的有效性和可行性.

Abstract: Popular 3D target recognition approaches based on image continue to struggle with challenge—viewpoint sensitivity. Multi-view modeling technique for 3D target offers promise for this challenge. A method of modeling 3D target based on support vector data description (SVDD) that could obtain a tight description covering most of the target feature data was proposed. Target’s images were captured with uniform grid on the viewing sphere and characterized by feature vectors. The support vectors representing characteristic views were obtained by applying SVDD to optimize the parameters of the minimal hyper-sphere which covers as many feature vectors as possible. The experiments were conducted by applying the proposed method to an image set (each target includes 2592 images) characterized by normalized moment invariants. The results show that the proposed method is effective and feasibility.

中图分类号: 


版权所有 © 《北京航空航天大学学报》编辑部
通讯地址:北京市海淀区学院路37号 北京航空航天大学学报编辑部 邮编:100191 E-mail:jbuaa@buaa.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发