Computer generated still images composited with panned landscape video sequences

Proceedings 1998 MultiMedia Modeling. MMM'98 (Cat. No.98EX200) Pub Date : 1998-10-12 DOI:10.1109/MULMM.1998.722977

E. Nakamae, Xueying Qin, Guofang Jiao, Przemyslaw Rokita, Katsumi Tadamura, Yuji Usagawa

{"title":"Computer generated still images composited with panned landscape video sequences","authors":"E. Nakamae, Xueying Qin, Guofang Jiao, Przemyslaw Rokita, Katsumi Tadamura, Yuji Usagawa","doi":"10.1109/MULMM.1998.722977","DOIUrl":null,"url":null,"abstract":"We present a novel approach to offer at a reasonable cost, panned landscape video sequence images well matched with photorealistic computer generated still images of large scale construction projects, such as bridges and electric power transmission towers. Our newly developed compositing algorithms can be used with the equipment which consists of a regular camcorder sold on the market, a video editing system, and our own software for rendering day-time scenes under various weather conditions. Other types of equipment such as an elaborate camera controller or special reference points in the landscapes, are unnecessary. The proposed algorithms provide the following features: (1) the computer generated still images are well harmonized with panned video sequence images at any time of day under various weather conditions, in terms of both optical and geometrical accuracy; (2) a precise panorama composited from video sequence images is created, in which varying exposure levels due to changing camera view fields can be coped with and any geometrical distortion is eliminated.","PeriodicalId":305422,"journal":{"name":"Proceedings 1998 MultiMedia Modeling. MMM'98 (Cat. No.98EX200)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1998-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings 1998 MultiMedia Modeling. MMM'98 (Cat. No.98EX200)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/MULMM.1998.722977","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 3

Abstract

We present a novel approach to offer at a reasonable cost, panned landscape video sequence images well matched with photorealistic computer generated still images of large scale construction projects, such as bridges and electric power transmission towers. Our newly developed compositing algorithms can be used with the equipment which consists of a regular camcorder sold on the market, a video editing system, and our own software for rendering day-time scenes under various weather conditions. Other types of equipment such as an elaborate camera controller or special reference points in the landscapes, are unnecessary. The proposed algorithms provide the following features: (1) the computer generated still images are well harmonized with panned video sequence images at any time of day under various weather conditions, in terms of both optical and geometrical accuracy; (2) a precise panorama composited from video sequence images is created, in which varying exposure levels due to changing camera view fields can be coped with and any geometrical distortion is eliminated.

查看原文本刊更多论文

计算机生成的静态图像与平移的景观视频序列合成

我们提出了一种新颖的方法，以合理的成本提供平移的景观视频序列图像，与大型建筑项目(如桥梁和输电塔)的逼真计算机生成的静态图像相匹配。我们新开发的合成算法可以与市场上出售的普通摄像机，视频编辑系统和我们自己的软件组成的设备一起使用，用于在各种天气条件下渲染白天的场景。其他类型的设备，如精心制作的相机控制器或景观中的特殊参考点，都是不必要的。本文提出的算法具有以下特点:(1)计算机生成的静止图像在各种天气条件下的任何时间与平移的视频序列图像在光学和几何精度方面都很好地协调一致;(2)由视频序列图像合成出精确的全景图，该全景图可以处理因摄像机视场变化而引起的曝光水平变化，并消除几何畸变。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Proceedings 1998 MultiMedia Modeling. MMM'98 (Cat. No.98EX200)

自引率

0.00%

发文量