Filters








16,979 Hits in 6.2 sec

Human Motion Capture Based on Incremental Dimension Reduction and Projection Position Optimization

Wanyi Li, Yuqi Zeng, Qian Zhang, Yilin Wu, Guoming Chen, Giuseppe Piro
2021 Wireless Communications and Mobile Computing  
Therefore, a new algorithm called incremental dimension reduction and projection position optimization (IDRPPO) is proposed in this paper.  ...  By taking advantage of the Gaussian incremental dimension reduction model (GIDRM) and projection position optimization, the proposed algorithm can learn the existing samples and establish the relevant  ...  Acknowledgments This work is supported by the Guangzhou Science and Technology Plan Project of (No. 202002030232), the University Young Creative Talent  ... 
doi:10.1155/2021/5589100 fatcat:c2v4qjqxvrfvbjsbumfufbdseu

Constraint-based motion optimization using a statistical dynamic model

Jinxiang Chai, Jessica K. Hodgins
2007 ACM SIGGRAPH 2007 papers on - SIGGRAPH '07  
We pose constraint-based motion synthesis as a maximum a posterior (MAP) problem and develop an optimization framework that generates natural motion satisfying user constraints.  ...  The system automatically learns a statistical dynamic model from motion capture data and then enforces it as a motion prior.  ...  Acknowledgements The authors would like to thank Moshe Mahler for his help in modeling and rendering the images for this paper and Autodesk for the donation of Maya software.  ... 
doi:10.1145/1275808.1276387 fatcat:76wfs2cn4ve3za522ou6dfql5i

Constraint-based motion optimization using a statistical dynamic model

Jinxiang Chai, Jessica K. Hodgins
2007 ACM Transactions on Graphics  
We pose constraint-based motion synthesis as a maximum a posterior (MAP) problem and develop an optimization framework that generates natural motion satisfying user constraints.  ...  The system automatically learns a statistical dynamic model from motion capture data and then enforces it as a motion prior.  ...  Acknowledgements The authors would like to thank Moshe Mahler for his help in modeling and rendering the images for this paper and Autodesk for the donation of Maya software.  ... 
doi:10.1145/1239451.1239459 fatcat:a4nr4nn73bbq7dyorvm32sfjwe

Constraint-based motion optimization using a statistical dynamic model

Jinxiang Chai, Jessica K. Hodgins
2007 ACM Transactions on Graphics  
We pose constraint-based motion synthesis as a maximum a posterior (MAP) problem and develop an optimization framework that generates natural motion satisfying user constraints.  ...  The system automatically learns a statistical dynamic model from motion capture data and then enforces it as a motion prior.  ...  Acknowledgements The authors would like to thank Moshe Mahler for his help in modeling and rendering the images for this paper and Autodesk for the donation of Maya software.  ... 
doi:10.1145/1276377.1276387 fatcat:nkjkslilrvaoblww5vd345guti

Simulating biped behaviors from human motion data

Kwang Won Sok, Manmyung Kim, Jehee Lee
2007 ACM SIGGRAPH 2007 papers on - SIGGRAPH '07  
Physically based simulation of human motions is an important issue in the context of computer animation, robotics and biomechanics.  ...  We developed an optimization method that transforms any (either motion-captured or kinematically synthesized) biped motion into a physically-feasible, balance-maintaining simulated motion.  ...  Acknowledge We would like to thank all the members of the SNU Movement Research Laboratory for their help in collecting motion data.  ... 
doi:10.1145/1275808.1276511 fatcat:ezfn3usvt5guxa6p4xaeq6ggzi

Simulating biped behaviors from human motion data

Kwang Won Sok, Manmyung Kim, Jehee Lee
2007 ACM Transactions on Graphics  
Physically based simulation of human motions is an important issue in the context of computer animation, robotics and biomechanics.  ...  We developed an optimization method that transforms any (either motion-captured or kinematically synthesized) biped motion into a physically-feasible, balance-maintaining simulated motion.  ...  Acknowledge We would like to thank all the members of the SNU Movement Research Laboratory for their help in collecting motion data.  ... 
doi:10.1145/1239451.1239558 fatcat:nitd2pjerbadxatxedz6j6f5vy

Simulating biped behaviors from human motion data

Kwang Won Sok, Manmyung Kim, Jehee Lee
2007 ACM Transactions on Graphics  
Physically based simulation of human motions is an important issue in the context of computer animation, robotics and biomechanics.  ...  We developed an optimization method that transforms any (either motion-captured or kinematically synthesized) biped motion into a physically-feasible, balance-maintaining simulated motion.  ...  Acknowledge We would like to thank all the members of the SNU Movement Research Laboratory for their help in collecting motion data.  ... 
doi:10.1145/1276377.1276511 fatcat:jtzac6vx3jh6vmqupayxvvrksa

Correlated space formation for human whole-body motion primitives and descriptive word labels

Wataru Takano, Seiya Hamano, Yoshihiko Nakamura
2015 Robotics and Autonomous Systems  
We tested our proposed approach on captured human whole body motion data, and its validity was demonstrated.  ...  A massive amount of captured human data has already been collected. These prerecorded motion data should be reused in order to make the motion analysis and synthesis more efficient.  ...  Acknowledgments This research was supported by PREST ''Information Environment and Humans'', Japan Science and Technology Agency, and Grant-in-Aid for Young Scientists (A) (26700021), Japan Society for  ... 
doi:10.1016/j.robot.2014.11.020 fatcat:rrwyhbdkafd6xoh3crjfp7pvci

Graph Based Discriminative Learning for Robust and Efficient Object Tracking

Xiaoqin Zhang, Weiming Hu, Steve Maybank, Xi Li
2007 2007 IEEE 11th International Conference on Computer Vision  
Furthermore, an incremental updating technique for the graphs is developed to capture the changes in both appearance and illumination.  ...  In tracking procedure, the graph based learning is embedded into a Bayesian inference framework cascaded with hierarchical motion estimation, which significantly improves the accuracy and efficiency of  ...  Graph Embedding for Dimension Reduction Before introducing our work, let us review the graph embedding framework for dimension reduction [17] .  ... 
doi:10.1109/iccv.2007.4409034 dblp:conf/iccv/ZhangHML07 fatcat:bm3sjimbcnedpkfgdziny2jkua

Online Adaptive PCA for Inverse Kinematics Hand Tracking [article]

Matthias Schröder, Mario Botsch
2014 International Symposium on Vision, Modeling, and Visualization  
It has been shown that exploiting natural hand synergies can improve the efficiency and quality of the tracking, by performing the optimization in a reduced parameter space consisting of realistic hand  ...  Our adaptive model combines the robustness of tracking in a reduced parameter space with the flexibility of optimizing for the full articulation of the hand, which we demonstrate in several synthetic and  ...  This work was supported by the DFG Center of Excellence "Cognitive Interaction Technology" (CoE 277: CITEC) and the DFG grant "Real-Time Acquisition and Dynamic Modeling of Human Faces, Upper Bodies, and  ... 
doi:10.2312/vmv.20141283 dblp:conf/vmv/SchroderB14 fatcat:jmp5dccunbhplhboz7cdbretne

3D Gait Recognition Using Spatio-Temporal Motion Descriptors [chapter]

Bogdan Kwolek, Tomasz Krzeszowski, Agnieszka Michalczuk, Henryk Josinski
2014 Lecture Notes in Computer Science  
We report its tracking accuracy using ground-truth data obtained by a markerbased motion capture system. The classification is done using SVM built on the proposed spatio-temporal motion descriptors.  ...  We present a view independent algorithm for 3D human gait recognition. The identification of the person is achieved using motion data obtained by our markerless 3D motion tracking algorithm.  ...  This work has been partially supported by the Polish National Science Center (NCN) within the research projects NN 516 475740, NN 516 483240 and Ministry of Science and Higher Education within a grant  ... 
doi:10.1007/978-3-319-05458-2_61 fatcat:hbx4mlpt7zbebgzc7slmri2voi

A Hybrid Framework for 3-D Human Motion Tracking

Bingbing Ni, A.A. Kassim, S. Winkler
2008 IEEE transactions on circuits and systems for video technology (Print)  
Experimental results on several real human motion sequences show the accuracy and robustness of our method, which also has a higher sampling efficiency than most particle filtering based methods.  ...  We also incorporate a local optimization method based on simulated physical force/moment into our framework, which further improves the optimality of the tracking.  ...  VQPCA is a non-parametric, nonlinear dimensionality reduction technique, which is suitable for modeling nonlinear data structures like human motion data and also provides the orthogonal projection basis  ... 
doi:10.1109/tcsvt.2008.927108 fatcat:lxbbevic4fe63gserbfmcdlba4

Pose Synthesis Using the Inverse of Jacobian Matrix Learned from Examples

Chunpeng Li, Shihong Xia, Zhaoqi Wang
2007 2007 IEEE Virtual Reality Conference  
This paper presents a method of pose synthesis based on a lowdimensional space and a set of characteristics of motion learned from examples.  ...  In the synthesis phase, a lightweight algorithm based on the learned parameters is used.  ...  ACKNOWLEDGEMENTS We would like to thank Yanyan Yuan, Rongrong Wang, the members of the CAS ICT virtual reality laboratory, and the anonymous reviewers for their advice and assistance.  ... 
doi:10.1109/vr.2007.352469 dblp:conf/vr/LiXW07 fatcat:aid7ytw5cjbbjprgaxgxs2yt2y

Multilinear Motion Synthesis with Level-of-Detail Controls

Tomohiko Mukai, Shigeru Kuriyama
2007 15th Pacific Conference on Computer Graphics and Applications (PG'07)  
Multilinear analysis provides the efficient representation of multidimensional and multimodal data, including human motion data, based on statistical data correlations.  ...  We introduce a hybrid algorithm to optimize the reduction size and computational time according to the distance from the camera while maintaining visual quality.  ...  This work was supported by the MEXT Grant-in-Aid for Young Scientists (B) 19700090, Scientific Research (B) 18300068, and The Hori Information Science Promotion Foundation.  ... 
doi:10.1109/pg.2007.36 dblp:conf/pg/MukaiK07 fatcat:p7ntlwruvnavplyni4oekloqaq

Using nonlinear dimensionality reduction in 3D figure animation

A. Elizabeth Seward, Bobby Bodenheimer
2005 Proceedings of the 43rd annual southeast regional conference on - ACM-SE 43  
This paper demonstrates that through nonlinear dimensionality reduction and frame re-sequencing, visually compelling motion can be produced from a set of motion capture data.  ...  Two distance metrics for nonlinear dimensionality reduction are compared as well as the effect of global degrees of freedom on the visual appeal of the newly generated motion.  ...  In this case the optimal dimension is four, although Figure 2 necessarily shows a two-dimensional representation.  ... 
doi:10.1145/1167253.1167344 dblp:conf/ACMse/SewardB05 fatcat:yx4dbqn5nfcvdlq4xuyfalrnum
« Previous Showing results 1 — 15 out of 16,979 results