Online decomposition of compressive streaming data using n-l1 cluster-weighted minimization
Host Publication: Data Compression Conference
Authors: H. Van Luong, N. Deligiannis, S. Forchhammer and A. Kaup
Publication Year: 2018
Number of Pages: 10
We consider a decomposition method for compressive streaming data in the context ofonline compressive Robust Principle Component Analysis (RPCA). The proposed decompositionsolves an n-L1 cluster-weighted minimization to decompose a sequence of frames(or vectors), into sparse and low-rank components, from compressive measurements. Ourmethod processes a data vector of the stream per time instance from a small number ofmeasurements in contrast to conventional batch RPCA, which needs to access full data.The n-L1 cluster-weighted minimization leverages the sparse components along with theircorrelations with multiple previously-recovered sparse vectors. Moreover, the proposed minimizationcan exploit the structures of sparse components via clustering and re-weightingiteratively. The method outperforms the existing methods for both numerical data andactual video data.