真实场景中基于体表示的目标外形和纹理获取  

Shape and texture acquisition of objects in real scenes based on volumetric presentation

作　　者：史文波[1] 郑江滨[1] 

机构地区：[1]西北工业大学计算机学院,西安710072

出　　处：《计算机应用》2009年第3期732-735,共4页journal of Computer Applications

基　　金：国家863计划项目(2006AA01Z324);西北工业大学研究生创业种子基金资助项目(200849)

摘　　要：传统的基于图像的三维重建方法中,图像间的相关特征匹配是影响重建模型质量和精度的主要因素之一。提出一种基于体表示的真实目标的重建方法,回避了二维图像间的特征匹配问题,简化了建模的复杂度。该方法首先提取目标物的轮廓信息;其次单向单层遍历场景空间中目标物的最小三维包围盒,利用目标物固有的颜色信息不变性判断体元反向投影的一致性,从而获取目标的三维信息;最后利用获取的三维信息绘制得到真实目标的逼真模型。实验结果表明该方法建模精度较高,真实感强。In traditional three-dimensional(3D) reconstruction methods based on images,the correlated feature matching between images is one of the factors affecting the fidelity and accuracy of modeling.A 3D reconstruction method of object in real scene based on volumetric presentation was proposed,which avoided the feature matching and simplified the complexity of modeling.Firstly,the silhouettes of object in every image were extracted.Secondly,the minimal bounding box of object in scene volume was traversed in a si...

关 键 词：摄像机定标 体表示 体元 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]