基于三维投影的视频序列静态全景合成算法  

A composition algorithm of video sequence panoramic image based on three-dimensional projection

作　　者：邹晓春[1] 何明一[1] 赵歆波[2] 

机构地区：[1]西北工业大学电子信息学院,西安710072 [2]西北工业大学计算机学院,西安710072

出　　处：《中国体视学与图像分析》2010年第4期377-381,共5页Chinese Journal of Stereology and Image Analysis

基　　金：国家自然基金项目(60872144)

摘　　要：视频序列静态全景合成技术是视频图像分析的关键技术。本文提出了一种基于三维投影的视频序列静态全景合成算法,该算法通过引入三维投影原理,将视频序列中各帧图像依次投影到全景图像平面,推导出在同一三维坐标下各帧图像与全景图像之间的变换关系,并采用各帧图像间的运动参数联合生成全景图像。实验结果表明,该方法能够生成较高质量的全景图。One key technique of image analysis is video sequence panoramic image composition.A composition algorithm of video sequence panoramic image based on three-dimensional projection was proposed.Firstly,the three-dimensional projection principle was introduced to project each frame of the video sequence into the panoramic image plane in turn.Then,the image-to-background transform from the inter-image transforms in the 3-D world coordinate system is obtained and used to compose the video sequence panoramic image.Experimental results show that the proposed algorithm can generate panoramic image of high quality.

关 键 词：三维投影 视频序列 全景图像 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]