Programming codes

PETRELS-ADMM: Robust Subspace Tracking with Missing Data and Outliers

We propose a novel algorithm called PETRELS-ADMM to deal with subspace tracking in the presence of outliers and missing data. The proposed approach consists of two main stages: outlier rejection and subspace estimation. Particularly, we first use the ADMM solver for detecting outliers living in the measurement data in an efficient online way and then improve the well-known PETRELS algorithm to update the underlying subspace in the missing data context. The effectiveness of our algorithm, as compared to state-of-the-art algorithms, is illustrated on both simulated and real data.

Download

Our MATLAB code can be downloaded here.

Demo

+ Run the file DEMO_SEP_Main.m for simulated data.

+ Run the file DEMO_Video.m for real video data (Lobby data).

State-of-the-art algorithms for comparison

+ GRASTA: https://sites.google.com/site/hejunzz/grasta/

+ ROSETA: http://www.merl.com/research/license#ROSETA/

+ ReProCS: https://github.com/praneethmurthy/ReProCS/

+ NORST: https://github.com/praneethmurthy/NORST/

Some results

+ Simulated data: Matrix completion and performance comparison between PETRELS-ADMM against the state-of-the-art RST algorithms

+ Video background-foreground separation application

References

This code is free and open-source for research purposes. If you use this code, please acknowledge the following papers.

[1] L.T. Thanh, V.D. Nguyen, N. L. Trung and K. Abed-Meraim. “Robust Subspace Tracking with Missing Data and Outliers: Novel Algorithm with Convergence Guarantee”. IEEE Trans. Signal Process. (TSP), 2021. [PDF].

[2] L.T. Thanh, V.D Nguyen, N.L. Trung and K. Abed-Meraim. “Robust Subspace Tracking with Missing Data and Outliers via ADMM”. European Signal Process. Conf. (EUSIPCO), 2019. [PDF].

Contact

LE Trung Thanh

AVITECH Institute
VNU University of Engineering and Technology, Vietnam

Email: thanhletrung@vnu.edu.vn // letrungthanhtbt@gmail.com

SAME CATEGORY

GitHub

DLAD: Image Entropy Reduction via Anisotropic Diffusion Steered by Probability Map from CNNs

Medical images are often very large and medical image compression is important in teleradiology and teleinterventions. Medial image compression is challenging due to the quality of the images should remain sufficient for medical purpose. The lossless compression methods do not degrade the quality of the image, however their compression ratios are often very low. This […]

Network coding

Network coding (NC) is considered a breakthrough to improve throughput, robustness, and security of wireless networks. Although the theoretical aspects of NC have been extensively investigated, there have been only few experiments with pure NC schematics. This work presents an implementation of NC under a two-way relay model and extends it to two non-straightforward scenarios: […]