Online and Batch Supervised Background Estimation via L1 Regression
This work addresses video background estimation for computer vision applications, but it appears incremental as it builds on existing L1 regression techniques with scalability improvements.
The authors tackled the problem of supervised video background estimation by proposing a simple model based on L1 regression, and they developed scalable methods like iteratively reweighted least squares to handle high-resolution videos, achieving results that match or outperform state-of-the-art methods in online and batch settings.
We propose a surprisingly simple model for supervised video background estimation. Our model is based on $\ell_1$ regression. As existing methods for $\ell_1$ regression do not scale to high-resolution videos, we propose several simple and scalable methods for solving the problem, including iteratively reweighted least squares, a homotopy method, and stochastic gradient descent. We show through extensive experiments that our model and methods match or outperform the state-of-the-art online and batch methods in virtually all quantitative and qualitative measures.