Title :
Spatial constraints-based maximum likelihood estimation for human motions
Author :
Wanyi Li ; Jifeng Sun ; Xin Zhang ; Yuanchang Wu
Author_Institution :
Sch. of Electron. & Inf. Eng., South China Univ. of Technol., Guangzhou, China
Abstract :
A new method of spatial constraints-based maximum likelihood estimation (SC-based MLE) is proposed to process latent variables data of incomplete human motions cycle, and improve the GPDM learning and estimation in this paper, which can make the GPDM learn the samples of incomplete human motions cycle to estimate the new human motions. The proposed method has the GPDM learning less depend on training samples of the complete human motions cycle, and save the training samples. We verify the validity and efficiency of the proposed method, through the experiments of human motions estimation using the samples of incomplete and complete human motions cycle for training respectively.
Keywords :
Gaussian processes; learning (artificial intelligence); maximum likelihood estimation; motion estimation; GPDM estimation improvement; GPDM learning improvement; Gaussian process dynamical model; SC-based MLE; human motion estimation; incomplete human motions cycle; latent variables data; spatial constraints-based maximum likelihood estimation; statistical model; Animation; Estimation error; Gaussian processes; Kernel; Legged locomotion; Maximum likelihood estimation; Training; GPDM; SC-based MLE; estimation; human motions; learning;
Conference_Titel :
Signal Processing, Communication and Computing (ICSPCC), 2013 IEEE International Conference on
Conference_Location :
KunMing
DOI :
10.1109/ICSPCC.2013.6663910
