PROJECT TITLE :
Background Subtraction Based on Low-Rank and Structured Sparse Decomposition
Low rank and sparse representation based mostly methods, which build few specific assumptions about the background, have recently attracted wide attention in background modeling. With these strategies, moving objects in the scene are modeled as pixel-wised sparse outliers. But, in several sensible situations, the distributions of those moving elements are not actually pixel-wised sparse but structurally sparse. Meanwhile a strong analysis mechanism is needed to handle background regions or foreground movements with varying scales. Based on these two observations, we have a tendency to initial introduce a class of structured sparsity-inducing norms to model moving objects in videos. In our approach, we have a tendency to regard the observed sequence as being constituted of two terms, a low-rank matrix (background) and a structured sparse outlier matrix (foreground). Next, in virtue of adaptive parameters for dynamic videos, we have a tendency to propose a saliency measurement to dynamically estimate the support of the foreground. Experiments on difficult well known information sets demonstrate that the proposed approach outperforms the state-of-the-art methods and works effectively on a wide selection of advanced videos.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here