Panoramic Robust PCA for Foreground-Background Separation
on Noisy, Free-Motion Camera Video


Abstract
This work presents a novel approach for robust PCA with total variation regularization for foreground-background separation and denoising on noisy, moving camera video. Our proposed algorithm registers the raw (possibly corrupted) frames of a video and then jointly processes the registered frames to produce a decomposition of the scene into a low-rank background component that captures the static components of the scene, a smooth foreground component that captures the dynamic components of the scene, and a sparse component that isolates corruptions. Unlike existing methods, our proposed algorithm produces a panoramic low-rank component that spans the entire field of view, automatically stitching together corrupted data from partially overlapping scenes. The low-rank portion of our robust PCA model is based on a recently discovered optimal low-rank matrix estimator (OptShrink) that requires no parameter tuning. We demonstrate the performance of our algorithm on both static and moving camera videos corrupted by noise and outliers.

Papers

Journal (submitted)
GlobalSIP 2017
References

Chen Gao*, Brian E. Moore*, Raj Rao Nadakuditi, "Panoramic Robust PCA for Foreground-Background Separation on Noisy, Free-Motion Camera Video", arXiv:1712.06229, 2017.

Chen Gao, Brian E. Moore, Raj Rao Nadakuditi, "Augmented Robust PCA For Foreground-Background Separation on Noisy, Moving Camera Video", in IEEE Global Conference on Signal and Information Processing (GlobalSIP), 2017.


BibTeX
@inproceedings{moore2017panoramic,
    author    = {Moore, Brian E* and Gao, Chen* and Nadakuditi, Raj Rao},
    title     = {Panoramic Robust PCA for Foreground-Background Separation on Noisy, Free-Motion Camera Video},
    journal   = {arXiv:1712.06229}
    year      = {2017}
}

@inproceedings{gao2017augmented,
    author    = {Gao, Chen and Moore, Brian E and Nadakuditi, Raj Rao},
    title     = {Augmented robust PCA for foreground-background separation on noisy, moving camera video},
    booktitle = {2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP)}
    month     = {November},
    year      = {2017},
    pages     = {1240-1244}
}