[1]孙正兴,姚 伟.从视频中恢复三维人脸的实时方法[J].智能系统学报,2009,4(5):427-432.[doi:10.3969/j.issn.1673-4785.2009.05.007]
SUN Zheng-xing,YAO Wei.A real-time method for recovering 3D faces from monocular video[J].CAAI Transactions on Intelligent Systems,2009,4(5):427-432.[doi:10.3969/j.issn.1673-4785.2009.05.007]
点击复制
SUN Zheng-xing,YAO Wei.A real-time method for recovering 3D faces from monocular video[J].CAAI Transactions on Intelligent Systems,2009,4(5):427-432.[doi:10.3969/j.issn.1673-4785.2009.05.007]
从视频中恢复三维人脸的实时方法
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
4
期数:
2009年第5期
页码:
427-432
栏目:
学术论文—机器感知与模式识别
出版日期:
2009-10-25
- Title:
- A real-time method for recovering 3D faces from monocular video
- 文章编号:
- 1673-4785(2009)05-0427-06
- Keywords:
- vision-based interaction (VBI); 3D face; face pose; active shape model (ASM); non-rigid structure from motion; 3D deformable mode
- 分类号:
- TP391
- 文献标志码:
- A
- 摘要:
- 三维人脸恢复是视觉交互的一个难点问题，提出了一种从视频中实时恢复三维人脸的新方法.该方法利用主动形状模型进行人脸特征点提取和跟踪，确保了三维形状恢复和特征跟踪的有效性和一致性；采用非刚体形状和运动估计方法构建三维形变基，有效地适应人脸形状变化的多样性；采用非线性优化算法估算人脸姿态和三维形变基参数，实现了三维人脸形状和姿态的实时恢复.实验结果表明，该方法不仅能从视频中实时恢复三维人脸模型，而且可有效跟踪人脸各种姿态的变化.
- Abstract:
- A major challenge for vision-based user interfaces has been the construction of 3D face models in real-time. This paper proposes a novel method for recovering 3D faces from monocular videos. First, active shape model (ASM) was used to extract and trace face features in videos, guaranteeing the validity and consistency of model recovery and feature tracking. Next, a motion algorithm based on non-rigid structures was adapted to create 3D deformable shape bases as sources for a variety of face shapes. Finally, a nonlinear optimization algorithm was introduced to estimate the parameters of the face pose to be applied to the deformable model so as to rapidly reconstruct a 3D image. Experimental results proved the effectiveness of the proposed method; it robustly recovers 3D shapes and poses from videos in real-time.
- 参考文献/References:
-
［1］PORTA M. Vision-based user interfaces: methods and applications［J］. International Journal of HumanComputer Studies, 2002, 57: 27-73.
［2］WATERS K, TERZOPOULOS D. Modeling and animating faces using scanned data［J］. Journal of Visualization and Computer Animation, 1991, 2(4): 123-128.
［3］胡永利，尹宝才，程世铨，等. 创建中国人三维人脸库关键技术研究［J］. 计算机研究与发展，2005，42(4): 622-628.
HU Yongli, YIN Baocai, CHENG Shiquan, et al. Research on key technology in construction of a Chinese 3D face database［J］. Journal of Computer Research and Development, 2005, 42(4): 622-628.
［4］MOESLUND T B, HILTON A, KRUGER V. A survey of advances in vision-based human motion capture and analysis［J］. Computer Vision and Image Understanding, 2006, 104(2): 90-126.
［5］VACCHETTI L, LEPETIT V, FUA P. Stable real-time 3D tracking using online and offline information［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(10): 1385-1391.
［6］LIU Z, ZHANG Z, JACOBS C, et al. Rapid modeling of animated faces from video［J］. The Journal of Visualization and Computer Animation, 2001, 12(4): 227-240.
［7］COOTES T F, TAYLOR C J, COOPER D H, et al. Active shape models-their training and application［J］. Computer Vision and Image Understanding, 1995, 61(1): 38-59.
［8］COOTES T F, EDWARDS G, TAYLOR C J. Active appearance models［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(6): 681-685.
［9］BLANZ V, VETTER T. A morphable model for the synthesis of 3D-face［C］//Proceedings of ACM International Conference on Computer Graphics(SIGGRAPH 99). Los Angeles, USA, 1999: 187-194.
［10］AHLBERG J. Modelbased coding—Extraction, coding, and evaluation of face model parameters［D］. Linkoping City, Sweden: Linkoping University, 2002.
［11］VOGLER C, LI Zhiguo, KANAUJIA A, et al. The best of both worlds: combining 3D deformable models with active shape models［C］//Proceedings of the 11th IEEE International Conference on Computer Vision. Rio de Janeiro, Brazil, 2007: 1-7.
［12］BREGLER C, HERTZMANN A, BIERMANN H. Recovering non-rigid 3D shape from image streams［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Hilton Head, USA, 2000: 690-696.
［13］BRAND M. Morphable 3D models from video［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Kauai, Hawaii, USA, 2001: 456-463.
［14］XIAO J, CHAI J, KANADE T. A closed-form solution to non-rigid shape and motion recovery［C］//Proceedings of the 8th European Conference on Computer Vision. Prague, Czech Republic, 2004: 573-587.
［15］ZHU Jianke, HOI S C, LYU M R. The realtime non-rigid shape recovery via active appearance models for augmented reality［C］//Proceedings of the 9th European Conference on Computer Vision. Graz, Austria, 2006: 186197.
［16］姚?? 伟.人脸表情识别与生成的技术研究［D］.南京: 南京大学，2009.
YAO Wei. Research on facial expression recognition and synthesis［D］.Nanjing: Nanjing University, 2009.
备注/Memo
收稿日期：2009-07-23. 基金项目：国家高科技发展计划(863)资助项目(2007AA01Z334)； 国家自然科学基金资助项目(69903006,60373065,60721002). 作者简介：
孙正兴，男，1964年生，教授、博士生导师.中国图像图形学会计算机动画与数字艺术专委会常务委员，中国计算机学会计算机辅助设计与图形学专委会委员，中国人工智能学会人工心理与人工情感专委会委员，江苏省微型电脑应用协会副理事长兼多媒体技术专委会主任，江苏省计算机学会计算机辅助设计与图形学专委会主任.国家自然科学基金委创新研究群体(2007年度)骨干成员.主要研究方向为多媒体计算、计算机视觉和环境智能.获省部级科技进步三等奖3次.已在国内外重要学术刊物上发表学术论文90余篇，主编教材3部、译著1部.
姚 伟，男,1984年生,硕士研究生，主要研究方向为计算机视觉与智能人机交互.
更新日期/Last Update:
2009-12-29