期刊文献+

使用Kinect快速重建三维人体 被引量:36

Fast 3D Human Body Reconstruction from Kinects
下载PDF
导出
摘要 三维人体模型广泛应用在多媒体工业,如动漫产业、游戏创作、电影制作等.针对传统三维扫描仪价格昂贵、操作复杂等缺点,提出一种基于低廉的深度摄像机(如微软Kinect)重建三维人体模型.该方法使用迭代最近点查找确定输入点云与可变模型之间的对应点对,将可变形人体模型拟合扫描点云数据,迭代生成高精度的三维人体模型.实验结果表明,文中方法能够使用Kinect深度摄像机快速重建出高精度的三维人体模型. 3D human body is an essential part of the media industry, such as cartoon, game, movie, etc. We adopt depth sensor input devices, such as Microsoft Kinect, to reconstruct human body model. In this paper, we propose a system based on a morphable human body model with the help of ICP(iterated closest point) to find corresponding points between input data and the morphable model. After a few iterations, a high quality human body model is generated. Finally, the experimental reconstruction results demonstrate the efficiency of our system and the quality of the reconstructed human model.
出处 《计算机辅助设计与图形学学报》 EI CSCD 北大核心 2013年第6期873-879,共7页 Journal of Computer-Aided Design & Computer Graphics
基金 国家自然科学基金(61070071 61202284) 国家自然科学基金面上项目(61170318) 国家"九七三"重点基础研究发展计划项目(2011CB302400)
关键词 三维人体模型 微软Kinect 迭代最近点 3D human body Microsoft Kinect iterated closest point
  • 相关文献

参考文献17

  • 1Carignan M, Yang y, Thalmann M, et al. Dressing animated synthetic actors with complex deformable clothes[J]. ACM SIGGRAPH Computer Graphics, 1992, 26(2),99-104. 被引量:1
  • 2Montani C, Scateni R, Scopigno R. Discretized marching cubes[CJ //Proceedings of the IEEE Conference on Visualization'94. Los Alamitos, IEEE Computer Society Press, 1994, 281-287. 被引量:1
  • 3Dorai C, Wang G,Jain A K. Registration and integration of multiple object views for 3D model construction[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998,200),83-89. 被引量:1
  • 4Hasler N, Ackermann H, Rosenhahn B, et al . Multilinear pose and body shape estimation of dressed subjects from image sets[CJ //Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Los Alamitos, IEEE Computer Society Press, 2010, 1823-1830. 被引量:1
  • 5Guan r , Weiss A, Balan A 0, etal. Estimating human shape and pose from a single image[CJ //Proceedings of the 12th IEEE International Conference on Computer Vision. Los Alamitos, IEEE Computer Society Press, 2009, 1381-1388. 被引量:1
  • 6Balan A, Sigal L, Black MJ, et al. Detailed human shape and pose from images[CJ //Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Los Alamitos, IEEE Computer Society Press, 2007, 1-8. 被引量:1
  • 7肖俊,庄越挺,吴飞.计算机视觉与机器学习技术在三维人体动画中的应用综述[J].计算机辅助设计与图形学学报,2008,20(3):281-290. 被引量:13
  • 8Weiss A, Hirshberg 0, Black MJ. Home 3D body scans from noisy image and range data[CJ //Proceedings of IEEE International Conference on Computer Vision. Los Alamitos: IEEE Computer Society Press, 2011, 1951-1958. 被引量:1
  • 9TongJ, ZhouJ, Liu L G, et al. Scanning 3D full human bodies using Kinects[J]. IEEE Transactions on Visualization and Computer Graphics, 2012, 18(4),643-650. 被引量:1
  • 10Tomasi C, Manduchi R. Bilateral filtering for gray and color images[CJ //Proceedings of the 6th International Conference on Computer Vision. Los Alamitos: IEEE Computer Society Press, 1998: 836-846. 被引量:1

二级参考文献61

  • 1Moeslund T B, Hilton A, Kruger V. A survey of advances in vision-based human motion capture and analysis [J]. Computer Vision and Image Understanding, 104(2) : 90-126. 被引量:1
  • 2Glelcher M, Ferrier N. Evaluating video-based motion capture [C].Proceedings of Computer Animation, Geneva, 2002:75 -78. 被引量:1
  • 3Bregler C, Malik J. Video motion capture [R]. Berkeley: University of Berkeley, CSD-97-973, 1997. 被引量:1
  • 4刘小明.基于视频的人体动画技术的研究[D].杭州:浙江大学,1999. 被引量:2
  • 5朱强.视频流中人体运动信息的提取和再生技术[D].杭州:浙江大学,2002. 被引量:1
  • 6Zhao J H, Li L. Human motion reconstruction from monocular images using genetic algorithms [J]. Computer Animation and Virtual Worlds, 2004, 15(3/4): 407-414. 被引量:1
  • 7Chen Y S, Lee J, Parent R, et al. Markerless monocular motion capture using image features and physical constraints [ C] .Proceedings of the Computer Graphics International, Stony Brook, 2005:36-43. 被引量:1
  • 8Micilotta A S, Ong E J, Bowden R. Real-time upper body 3D pose estimation from a single uncalibrated camera [C].Proceedings of EUROGRAPHICS 2005, Dublin, 2005 : 41-44. 被引量:1
  • 9DiFranco D E, Cham T, Rehg J M. Reconstruction of 3-D figure motion from 2 D correspondences [C] .Proceedings of 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Prague, 2001:307-314. 被引量:1
  • 10Chen C, Zhuang Y Ting, Xiao J. Towards robust 3D reconstruction of human motion from monocular video [C] .Proceedings of the 16th International Conference on Artificial Reality and Telexlstence, Hangzhou, 2006:594-603. 被引量:1

共引文献12

同被引文献289

引证文献36

二级引证文献187

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部