An Adaptive Dictionary Learning Approach for Modeling Dynamical Textures
This work addresses video processing challenges for computer vision applications, but it appears incremental as it builds on existing sparse coding and dynamical system methods.
The authors tackled video representation by modeling image frames as a Linear Dynamical System, proposing an adaptive video dictionary learning (AVDL) framework that captures scene dynamics through sparse coding and temporal correlations, achieving competitive results on benchmark sequences with appearance changes and occlusions.
Video representation is an important and challenging task in the computer vision community. In this paper, we assume that image frames of a moving scene can be modeled as a Linear Dynamical System. We propose a sparse coding framework, named adaptive video dictionary learning (AVDL), to model a video adaptively. The developed framework is able to capture the dynamics of a moving scene by exploring both sparse properties and the temporal correlations of consecutive video frames. The proposed method is compared with state of the art video processing methods on several benchmark data sequences, which exhibit appearance changes and heavy occlusions.