Layered Dynamic Textures

By Antoni B. Chan, Nuno Vasconcelos. 2005

98 citations recorded by the source corpus.

A novel video representation, the layered dynamic texture (LDT), is proposed. The LDT is a generative model, which represents a video as a collection of stochastic layers of different appearance and dynamics. Each layer is modeled as a temporal texture sampled from a different linear dynamical system. The LDT model includes these systems, a collection of hidden layer assignment variables (which control the assignment of pixels to layers), and a Markov random field prior on these variables (which encourages smooth segmentations). An EM algorithm is derived for maximum-likelihood estimation of the model parameters from a training video. It is shown that exact inference is intractable, a problem which is addressed by the introduction of two approximate inference procedures: a Gibbs sampler and a computationally efficient variational approximation. The trade-off between the quality of the two approximations and their complexity is studied experimentally. The ability of the LDT to segment videos into layers of coherent appearance and dynamics is also evaluated, on both synthetic and natural videos. These experiments show that the model possesses an ability to group regions of globally homogeneous, but locally heterogeneous, stochastic dynamics currently unparalleled in the literature.

Subfields: Computer Vision and Pattern Recognition, Geometry and Topology, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Geometry and Topology

In Signal Processing

Citations in the corpus

Variational Inference: A Review for Statisticians (2016, background): “As other examples, variational inference is important to probabilistic models of videos (Chan and Vasconcelos 2009; Wang and Mori 2009), image denoising (Likas and Galatsanos 2004), tracking (Vermaak, Lawrence, and Pérez 2003; Yu and Wu 2005), place recognition and mapping for robotics (Cummins and…”
Moving vistas: Exploiting motion for describing scenes (2010, background): “Similar examples can be imagined such as differentiating haphazard traffic from smooth traffic, a sea wave from a whirlpool, and numerous other examples.”
Video Processing From Electro-Optical Sensors for Object Detection and Tracking in a Maritime Environment: A Survey (2016, methodology): “The components of the mixture components are used as the features [141], [142], [147].”