首页> 外文会议>Internet and Multimedia Systems and Applications >SCENE TRANSITION BASED ON IMAGE REGISTRATION FOR WEB-BASED VIRTUAL TOUR
【24h】

SCENE TRANSITION BASED ON IMAGE REGISTRATION FOR WEB-BASED VIRTUAL TOUR

机译:基于图像注册的Web虚拟旅游场景转换

获取原文

摘要

In this paper, we present a web-based virtual tour system, Easy and Effective Virtual Tour (EEVT), and focus on describing a robust scene transition method based on an image registration technique. EEVT constructs a virtual tour from a set of images. It uses several snap shots of conventional photos without special tools, builds a simple 3D space within each photo using the spidery mesh technique, and expands the virtual spaces by connecting each space together. For high quality virtual tours, the capability of accurate space connection is crucial in order to provide smooth and seamless transitional scenes to virtual tourists during their navigation. We achieve the accurate scene connection using an image registration technique, which finds correspondences automatically and estimates transformations. Our registration method is a parametric approach and guarantees the accuracy and robustness based on the following key features: 1) coarse-to-fine hierarchical estimation 2) fast computation based on image feature-correspondences 3) FFT-based global matching 4) automatic outlier removal by RANSAC. The expanded virtual space by our approach creates a sense of navigational freedom for virtual tourists with less distorted viewing.
机译:在本文中,我们提出了一个基于Web的虚拟导览系统,即简易有效的虚拟导览(EEVT),重点介绍了一种基于图像配准技术的健壮的场景转换方法。 EEVT根据一组图像构造一个虚拟游览。它使用常规照片的几张快照而无需特殊工具,使用蜘蛛网技术在每张照片中构建一个简单的3D空间,并通过将每个空间连接在一起来扩展虚拟空间。对于高质量的虚拟旅行,准确的空间连接能力至关重要,以便在虚拟游客的导航过程中为其提供流畅且无缝的过渡场景。我们使用图像配准技术实现了准确的场景连接,该技术会自动找到对应关系并估计转换。我们的配准方法是一种参数化方法,它基于以下关键特征保证了准确性和鲁棒性:1)粗到精的层次估计2)基于图像特征对应的快速计算3)基于FFT的全局匹配4)自动离群值由RANSAC移除。通过我们的方法扩展的虚拟空间,为虚拟游客带来了较少扭曲的视觉导航自由感。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号