Human motion segmentation by RPCA with Augmented Lagrange Multiplier

Abstract

This paper proposes a fast and efficient algorithm, named Robust Principal Component Analysis (RPCA), for solving human motion segmentation. Given the human motion video each frame, and in many cases, it is reasonable to assume that the background vitiations are low-rank, while the foreground human motion is spatially localized, and therefore sparse. The human motion part is obtained by recovering the low-rank and sparse matrix. This process is formulated as a convex optimization problem that minimizes a constrained combination of nuclear norm and l 1 -norm, which can be solved efficiently with Augmented Lagrange Multiplier (ALM) method. Compared to previous method for Human motion segmentation, the proposed method produces more reliable results, and is more robust to noise, yet being much faster and efficient. We do some experiments on the HumanEva human motion dataset. The results show that human motion segmentation by the proposed method is novel and promising.