基于可变形运动模型的多角色语义化运动合成

计算机科学 ›› 2015, Vol. 42 ›› Issue (10): 292-296.

基于可变形运动模型的多角色语义化运动合成

王鑫,陈秋迪,梁朝凯,王万良

浙江工业大学计算机科学与技术学院杭州310023浙江省可视媒体智能处理技术研究重点实验室杭州310023,浙江工业大学计算机科学与技术学院杭州310023浙江省可视媒体智能处理技术研究重点实验室杭州310023,浙江工业大学计算机科学与技术学院杭州310023浙江省可视媒体智能处理技术研究重点实验室杭州310023,浙江工业大学计算机科学与技术学院杭州310023浙江省可视媒体智能处理技术研究重点实验室杭州310023

出版日期:2018-11-14 发布日期:2018-11-14
基金资助:
本文受国家自然科学基金(61303142,61173096,61103140),浙江省自然科学基金项目(Y1110882,Y1110688,R1110679),教育部高等学校博士学科点专项科研基金(20113317110001),浙江省教育厅一般科研项目(Y201330304)资助

Multi-characters Semantic Motion Synthesis Based on Deformable Motion Model

WANG Xin, CHEN Qiu-di, LIANG Chao-kai and WANG Wan-liang

Online:2018-11-14 Published:2018-11-14

摘要/Abstract

摘要： 对于一个完整的虚拟环境而言,智能的人群运动会使其更为生动、逼真。针对人群运动数据存在维度高、可控性差的问题,提出一种多角色可变形运动模型,其将人体运动分解为几何与时间变化两部分,并使用PCA算法进行有效降维,构建可变形运动模型的低维语义空间。实验结果表明,提出的方法能根据语义需求调节语义参数,实现多角色的语义化运动分析与合成。

关键词: 运动分解,可变形运动模型,多角色运动,运动合成

Abstract: Intelligent crowd motion can make the virtual environment seem realistic.Aiming at the problem of high dimension and poor controllability of crowd motion data,a deformable motion model for multiple characters was proposed.It decomposes the crowd motion data into geometry and time variations,uses PCA to reduce dimension,and then constructs a low-dimensional semantic space of multi-characters deformable motion model.The experiments show that the proposed method can adjust the parameters according to the semantic requirements for semantic multi-characters motion analysis and synthesis.

Key words: Motion decompose,Deformable motion model,Multi-characters motion,Motion synthesis

王鑫,陈秋迪,梁朝凯,王万良. 基于可变形运动模型的多角色语义化运动合成[J]. 计算机科学, 2015, 42(10): 292-296. https://doi.org/

WANG Xin, CHEN Qiu-di, LIANG Chao-kai and WANG Wan-liang. Multi-characters Semantic Motion Synthesis Based on Deformable Motion Model[J]. Computer Science, 2015, 42(10): 292-296. https://doi.org/

参考文献

[1] Reynolds C W.Flocks,herds and schools:A distributed beha-vioral model[J].ACM SIGGRAPH Computer Graphics,1987,21(4):25-34
[2] Reynolds C W.Steering behaviors for autonomous characters[C]∥Game Developers Conference.1999:763-782
[3] Duives D C,Daamen W,Hoogendoorn S P.State-of-the-artcrowd motion simulation models[J].Transportation Research Part C:Emerging Technologies,2013,37:193-209
[4] Brand M,Hertzmann A.Style machines[M].New York:ACM Press,2000:183-192
[5] Urtasun R,Glardon P,Boulic R,et al.Style-Based Motion Synthesis[J].Computer Graphics Forum,2004,23(4):799-812
[6] Li Y,Wang TS,Shum HY.Motion texture:A two-level statistical model for character motion synthesis[J].ACM Trans.on Graphics,2002,1(3):465-472
[7] Glardon P,Boulic R,Thalmann D.PCA-based walking engineusing motion capture data[C]∥Proceedings of Computer Graphics International,2004.IEEE,2004:292-298
[8] Glardon P,Boulic R,Thalmann D.A coherent locomotion engine extrapolating beyond experimental data[C]∥Proceedings of CASA,2004:73-84
[9] Hsu E,Pulli K,Popovic′ J.Style translation for human motion[J].ACM Transactions on Graphics,2005,24(3):1082-1089
[10] Niwase N,Yamagishi J,Kobayashi T.Human walking motion synthesis with desired pace and stride length based on HSMM[J].IEICE Transactions on Information and Systems,2005,88(11):2492-2499
[11] Tanco L M,Hilton A.Realistic synthesis of novel human movements from a database of motion capture examples[C]∥Proceedings of Workshop on Human Motion,2000.IEEE,2000:137-142
[12] Chai J,Hodgins J K.Constraint-based motion optimization using a statistical dynamic model[J].ACM Transactions on Graphics,2007,26(3):8
[13] Lau M,Bar-Joseph Z,Kuffner J.Modeling spatial and temporal variation in motion data[J].ACM Transactions on Graphics,2009,28(5):171
[14] Wei X,Min J,Chai J.Physically valid statistical models for human motion generation[J].ACM Transactions on Graphics,2011,30(3):19
[15] Lerner A,Chrysanthou Y,Lischinski D.Crowds by example[J].Computer Graphics Forum,2007,26(3):655-664
[16] Courty N,Corpetti T.Crowd motion capture[J].Computer Animation and Virtual Worlds,2007,18(4/5):361-370
[17] Lee K H,Choi M G,Hong Q,et al.Group behavior from video:a data-driven approach to crowd simulation[C]∥Proceedings of the 2007 ACM SIGGRAPH/Eurographics Symposium on Computer animation.Eurographics Association,2007:109-118
[18] Ju E,Choi M G,Park M,et al.Morphable crowds[J].ACM Transactions on Graphics,2010,29(6):140
[19] Blanz V,Vetter T.A morphable model for the synthesis of 3D faces[C]∥Proceedings of the 26th annual conference on Computer graphics and interactive techniques.ACM Press/Addison-Wesley Publishing Co.,1999:187-194
[20] Min J,Chen Y L,Chai J.Interactive generation of human animation with deformable motion models[J].ACM Transactions on Graphics,2009,29(1):9
[21] Teknomo K,Takeyama Y,Inamura H.Tracking algorithm for microscopic flow data collection[C]∥Proceedings of JSCE Student Conference.Sendai,Japan,2000
[22] 王鑫,孙守迁,邵明.运动路径驱动的角色动画合成方法[J].计算机辅助设计与图形学学报,2009,21(3):319-324 Wang Xin,Sun Shou-qian,Shao Ming.A Path-Driven Character Animation Synthcsis Mechod[J].Journal of Computer-Aided Design & Computer Graphics,2009,1(3):319-324
[23] Lee J,Chai J,Reitsma P S A,et al.Interactive control of avatars animated with human motion data[J].ACM Transactions on Graphics,2002,21(3):491-500

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed