计算机应用 ›› 2011, Vol. 31 ›› Issue (04): 1043-1046.DOI: 10.3724/SP.J.1087.2011.01043

• 图形图像技术 • 上一篇    下一篇

基于4目阵列的计算机视觉三维重建算法

封泽希1,张辉2,谢永明2,朱敏1   

  1. 1. 四川大学 计算机学院,成都 610065
    2. 中国科学院 深圳先进技术研究院,广东 深圳 518055
  • 收稿日期:2010-08-16 修回日期:2010-10-08 发布日期:2011-04-08 出版日期:2011-04-01
  • 通讯作者: 封泽希
  • 作者简介:封泽希(1985-),男,重庆人,硕士研究生,主要研究方向:图像处理、语音识别;
    张辉(1984-),男,山东日照人,硕士研究生,主要研究方向:图像处理;
    谢永明(1977-),男,贵州贵阳人,研究员,博士,主要研究方向:虚拟现实、可视化与图像学;
    朱敏(1971-),女,河北沧州人,教授,博士,主要研究方向:网络与信息系统、图像处理、智能信息处理。

3D reconstruction algorithm for computer vision using four camera array

Ze-xi FENG1,Hui ZHANG2,Yong-ming XIE2,Min ZHU1   

  1. 1. College of Computer Science, Sichuan University, Chengdu Sichuan 610065, China
    2. Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen Guangdong 518055, China
  • Received:2010-08-16 Revised:2010-10-08 Online:2011-04-08 Published:2011-04-01
  • Contact: Ze-xi FENG

摘要: 目前计算机视觉三维重建方法因需布置和标定摄像机环形拍摄场或者需要结构光而存在应用局限性问题,且算法不稳定。为此提出一种将摄像机阵列和图像配准有机结合的4目阵列重建算法,该算法不需要结构光和现场标定摄像机。经过基于包含光照和阴影的复杂室内仿真图像的实验表明,该方法能稳定有效地进行密集点云重建,且能克服现有重建方法的应用局限性与不稳定等缺陷。

关键词: 计算机视觉, 立体视觉, 三维重建, 图像配准, 稳定性, 4目阵列

Abstract: Current three-dimensional reconstruction algorithms of the computer vision field have limitations that they need to deploy and calibrate the cameras around the scene, or they need a structure light. Furthermore, these algorithms are not robust enough to every object. A new kind of four camera array reconstruction algorithms which properly combined the image registration algorithm and the camera array method was proposed to solve the robustness and limitation problems. It does not need calibration or structure light support. The experiments based on complex indoor sense with shadows demonstrate that this method is able to do dense point cloud reconstruction robustly and can overcome the shortcomings of current reconstruction algorithms.

Key words: computer vision, stereo vision, three-dimensional reconstruction, image registration, robustness, four camera array

中图分类号: