Predicting missing markers in human motion capture using l1-sparse representation

摘要

Missing marker problem is very common in human motion capture. In contrast to most current methods which handle thisnproblem based on trying to learn a reliable predictor from the observations, we consider it from the perspective of sparsenrepresentation and propose a novel method which is named l1-sparse representation of missing markers prediction (L1-nSRMMP).We assume that the incomplete pose can be represented by a linear combination of a few poses from the trainingnset and the representation is sparse. Therefore, we cast the predicting missing markers as finding a sparse representation ofnthe observable data of the incomplete pose, and then we use it to predict the missing data. In order to get a sparsenrepresentation, we employ l1-norm in our objective function. Moreover, we propose presentation coefficient weightednupdate (PCWU) algorithmtomitigate the limited capacity problemof the training set. Experimental results demonstrate theneffectiveness and efficiency of our method to predict the missing markers in human motion capture. Copyright # 2011nJohn Wiley & Sons, Ltd.