Learn More
Vision based fire detection is potentially a useful technique. With the increase in the number of surveillance cameras being installed, a vision based fire detection capability can be incorporated in existing surveillance systems at relatively low additional cost. Vision based fire detection offers advantages over the traditional methods. It will thus(More)
We formulate the problem of dynamic texture synthesis as a nonlinear manifold learning and traversing problem. We characterize dynamic textures as the temporal changes in spectral parameters of image sequences. For continuous changes of such parameters, it is commonly assumed that all these parameters lie on or close to a low-dimensional manifold embedded(More)
There has been growing interest in developing nonlinear dimensionality reduction algorithms for vision applications. Although progress has been made in recent years, conventional nonlinear dimensionality reduction algorithms have been designed to deal with stationary, or independent and identically distributed data. In this paper, we present a novel method(More)
Variation in object shape is an important visual cue for deformable object recognition and classification. In this paper, we present an approach to model gradual changes in the 2-D shape of an object. We represent 2-D region shape in terms of the spatial frequency content of the region contour using Fourier coefficients. The temporal changes in these(More)
We present a dynamic inference algorithm in a globally parameterized nonlinear manifold and demonstrate it on the problem of visual tracking. An appearance manifold is usually nonlinear, embedded in a high dimensional space, and can be approximated by a mixture of locally linear models. Existing methods for nonlinear dimensionality reduction, which map an(More)
Most existing video retrieval systems use low-level visual features such as color histogram, shape, texture, or motion. In this paper, we explore the use of higher-level motion representation for video retrieval of dynamic objects. We use three motion representations, which together can retrieve a large variety of motion patterns. Our approach works on top(More)
  • 1