Automatic Marker Registration and Prediction Algorithm for Optical Motion Capture System
TAN Guang-Hua1,2, ZHOU Mei-Lan1,2, GAO Chun-Ming1,2, LI Ren-Fa1
1College of Information Science and Electronic Engineering, Hunan University, Changsha 410082 2Institute of Digital Media, Hunan University, Changsha 410082
Abstract An automatic marker registration method is proposed to solve the registration problem of scattered point-set in optical motion capture system. Firstly, the markers in the first frame are segmented to provide the initial skeleton template with the knowledge of human body topology structure. Then, according to the local rigidity property and spatio-temporal information,the registration of marker is achieved by finding the most matching point in previous frame, which does not need specifying the initial template by hand. Under the assumption that markers do not change a lot in two consecutive frames, the coordinates of missing markers are predicted by using local rigidity property of the same segment. The experimental results show that every marker can be registered quickly and accurately and the proposed method has strong robustness and real-time performance.
[1] Ringer M, Lasenby J. A Procedure for Automatically Estimating Model Parameters in Optical Motion Capture. Image and Vision Computing, 2004, 22(10): 843-850 [2] Li B H, Meng Q G, Holstein H. Articulated Pose Identification with Sparse Point Features. IEEE Trans on Systems Man and Cybernetics, Part B: Cybernetics, 2004, 34(3): 1412-1422 [3] Holstein H, Li B H. Low Density Feature Point Matching for Articulated Pose Identification // Proc of the British Machine Vision Conference. Cardiff, UK, 2002: 678-687 [4] Kirk A G, O′Brien J F, Forsyth D A. Skeletal Parameter Estimation from Optical Motion Capture Data. IEEE Computer Society Confe-rence on Computer Vision and Pattern Recognition, 2005, II: 782-788 [5] Wei X P, Liu R, Zhang Q. Approach of Human Motion Capture Data Processing Based on Template Matching. Journal of System Simulation, 2010, 22(10): 2368-2391 (in Chinese) (魏小鹏,刘 瑞,张 强,等.基于模板匹配的人体运动捕捉数据处理方法.系统仿真学报, 2010, 22(10): 2368-2391) [6] Wei X P, Xiao B X, Zhang Q, et al. A Rigid Structure Matching-Based Noise Data Processing Approach for Human Motion Capture // Proc of the Workshop on Digital Media and Digital Content Management. Hangzhou, China, 2011: 91-96 [7] Xiao B X, Wei X P, Zhang Q, et al. Approach of Scattered Data Processing for Optical Motion Capture. Journal of System Simulation, 2008, 20(2): 382-385 (in Chinese) (肖伯祥,魏小鹏,张 强,等.光学运动捕捉散乱数据处理的一种方法.系统仿真学报, 2008, 20(2): 382-385)
[8] Li L, McCann J, Pollard N, et al. BoLeRo: A Principled Technique for Including Bone Length Constraints in Motion Capture Occlusion Filling // Proc of the ACM SIGGRAPH/Eurographics Symposium on Computer Animation. Madrid, Spain, 2010: 179-188 [9] Welch G, Bishop G, Vicci L, et al. The HiBall Tracker: High-Performance Wide-Area Tracking for Virtual and Augmented Environments // Proc of the ACM Symposium on Virtual Reality Software and Technology. London, UK, 1999: 1-10 [10] Herda L, Fua P, Plankers R, et al. Using Skeleton-Based Tracking to Increase the Reliability of Optical Motion Capture. Human Movement Science, 2001, 20(3): 313-341 [11] Aristidou A, Cameron J, Lasenby J. Predicting Missing Markers to Drive Real-Time Centre of Rotation Estimation // Proc of the 5th International Conference on Articulated Motion and Deformable Objects. Mallorca, Spain, 2008: 238-247 [12] Aristidou A, Lasenby J. Real-Time Marker Prediction and CoR Estimation in Optical Motion Capture. The Visual Computer, 2013, 29(1): 7-26 [13] Umeyama S. Least-Squares Estimation of Transformation Parameters between Two Point Patterns. IEEE Trans on Pattern Analysis and Machine Intelligence, 1991, 13(4): 376-380
2014, Vol. 27 
