多视觉下基于多重颜色一致性约束的三维体重建

›› 2012, Vol. 42 ›› Issue (04): 992-996.

多视觉下基于多重颜色一致性约束的三维体重建

李秀秀, 郑江滨, 张艳宁, 陈宁

西北工业大学计算机学院, 西安 710129

收稿日期:2011-04-11 出版日期:2012-07-01 发布日期:2012-07-01
通讯作者: 郑江滨(1971-),男,教授,博士生导师.研究方向:计算机视觉,多媒体信息处理.E-mail:zhengjb@nwpu.edu.cn E-mail:zhengjb@nwpu.edu.cn
基金资助:
国家自然科学基金项目(60970069).

Multiple photo-consistency constraints for 3D volumetric reconstruction in multi-view

LI Xiu-xiu, ZHENG Jiang-bin, ZHANG Yan-ning, CHEN Ning

School of Computer, Northwestern Polytechnical University, Xi'an 710129, China

Received:2011-04-11 Online:2012-07-01 Published:2012-07-01

摘要/Abstract

摘要： 提出了多视觉环境下多重颜色一致性约束,解决了三维目标外形重建中颜色一致性的准确计算、目标外形完整性问题。将基于体素到视点距离的可见性分析加入到体重建过程中,只利用体素可见视点的信息计算颜色一致性,在数据源上保证颜色一致性计算的准确性;将体素颜色一致性最大约束与体素邻域颜色一致性最大约束联合,以解决由于颜色一致性阈值选取不当造成的体素"过剔除",即空洞问题。通过实验对比该算法与体素着色法的重建结果,证明该算法有较好的重建效果,并能有效地保证三维目标外形的完整性。

关键词: 计算机应用, 体重建, 颜色一致, 可见性分析

Abstract: A volumetric reconstruction method with multiple photo-consistency constraints is proposed in the multi-view construction environment. First, the visibility determination based on the distance between the voxel and the viewpoint is introduced to calculate the photo-consistency precisely. Then, multiple photo-consistency constraints are applied to eliminate those voxels which do not belong to the shape of the reconstructed object. The maximization of the photo-consistency constraint and the maximization of the neighbor photo-consistency constraint can be jointly used to reconstruct the effective shape in order to solve the "hole" problem induced by the unsuitable threshold of color-consistency. Experiment results demonstrate the effectiveness of the method in guaranteeing the completeness of the reconstructed shape by comparing with conventional methods.

Key words: computer application, volumetric reconstruction, photo-consistency, visibility determination

中图分类号:

TP391

李秀秀, 郑江滨, 张艳宁, 陈宁. 多视觉下基于多重颜色一致性约束的三维体重建[J]. , 2012, 42(04): 992-996.

LI Xiu-xiu, ZHENG Jiang-bin, ZHANG Yan-ning, CHEN Ning. Multiple photo-consistency constraints for 3D volumetric reconstruction in multi-view[J]. , 2012, 42(04): 992-996.

参考文献

[1] Laurentini A. The visual hull concept for silhouette-based image understanding[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1994, 16(2):150-162.
[2] Seitz S M, Dyer C R. Photorealistic scene reconstruction by voxel coloring//The Conference on Computer Vision and Pattern Reconstruction, 1997:1067-1073.
[3] Hornung A, Kobbetlt L. Robust and efficient photo-consistency estimation for volumetric 3D reconstruction[J]. Lecture Notes in Computer Science, 2006, 3952:179-190.
[4] Culberston W B, Malzbender T, Slabaugh G. Generalized voxel coloring[J]. Vision Algorithm:Theory and Practice, 2000, 1883:100-115.
[5] Kutulakos K N, Seitz S M. A Theory of shape by space carving[J]. International Journal of Computer Vision, 2000, 38(3):199-218.
[6] Esteban C H, Schmitt F. Silhouette and stereo fusion for 3D object modeling[J]. Computer Vision and Image Understanding, 2004, 96(3):367-392.
[7] Starck J, Miller G, Hilton A. Virtual view synthesis of people from multiple view viewo sequence[J]. Graphic Models, 2005, 67(6):600-620.
[8] Wu Cheng-lei, Lin Ye-bin, Ji Xiang-yang, et al. Multi-view reconstruction under varying illumination conditions//IEEE International Conference on Multimedia and Expo, Mexico, 2009:930-933.
[9] Aganj E, Keriven R, Pons J P. Photo-consistency surface reconstruction from noisy point clouds//IEEE International Conference on Image Processing, 2009:505-508.

相关文章 15

[1]	刘富,宗宇轩,康冰,张益萌,林彩霞,赵宏伟. 基于优化纹理特征的手背静脉识别系统[J]. 吉林大学学报(工学版), 2018, 48(6): 1844-1850.
[2]	王利民,刘洋,孙铭会,李美慧. 基于Markov blanket的无约束型K阶贝叶斯集成分类模型[J]. 吉林大学学报(工学版), 2018, 48(6): 1851-1858.
[3]	金顺福,王宝帅,郝闪闪,贾晓光,霍占强. 基于备用虚拟机同步休眠的云数据中心节能策略及性能[J]. 吉林大学学报(工学版), 2018, 48(6): 1859-1866.
[4]	赵东,孙明玉,朱金龙,于繁华,刘光洁,陈慧灵. 结合粒子群和单纯形的改进飞蛾优化算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1867-1872.
[5]	刘恩泽,吴文福. 基于机器视觉的农作物表面多特征决策融合病变判断算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1873-1878.
[6]	欧阳丹彤, 范琪. 子句级别语境感知的开放信息抽取方法[J]. 吉林大学学报(工学版), 2018, 48(5): 1563-1570.
[7]	刘富, 兰旭腾, 侯涛, 康冰, 刘云, 林彩霞. 基于优化k-mer频率的宏基因组聚类方法[J]. 吉林大学学报(工学版), 2018, 48(5): 1593-1599.
[8]	桂春, 黄旺星. 基于改进的标签传播算法的网络聚类方法[J]. 吉林大学学报(工学版), 2018, 48(5): 1600-1605.
[9]	刘元宁, 刘帅, 朱晓冬, 陈一浩, 郑少阁, 沈椿壮. 基于高斯拉普拉斯算子与自适应优化伽柏滤波的虹膜识别[J]. 吉林大学学报(工学版), 2018, 48(5): 1606-1613.
[10]	车翔玖, 王利, 郭晓新. 基于多尺度特征融合的边界检测算法[J]. 吉林大学学报(工学版), 2018, 48(5): 1621-1628.
[11]	赵宏伟, 刘宇琦, 董立岩, 王玉, 刘陪. 智能交通混合动态路径优化算法[J]. 吉林大学学报(工学版), 2018, 48(4): 1214-1223.
[12]	黄辉, 冯西安, 魏燕, 许驰, 陈慧灵. 基于增强核极限学习机的专业选择智能系统[J]. 吉林大学学报(工学版), 2018, 48(4): 1224-1230.
[13]	傅文博, 张杰, 陈永乐. 物联网环境下抵抗路由欺骗攻击的网络拓扑发现算法[J]. 吉林大学学报(工学版), 2018, 48(4): 1231-1236.
[14]	曹洁, 苏哲, 李晓旭. 基于Corr-LDA模型的图像标注方法[J]. 吉林大学学报(工学版), 2018, 48(4): 1237-1243.
[15]	侯永宏, 王利伟, 邢家明. 基于HTTP的动态自适应流媒体传输算法[J]. 吉林大学学报(工学版), 2018, 48(4): 1244-1253.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed