Catálogo de publicaciones - libros

Automatic detection of a falling person in video is an important problem with applications in security and safety areas including supportive home environments and CCTV surveillance systems. Human motion in video is modeled using Hidden Markov Models (HMM) in this paper. In addition, the audio track of the video is also used to distinguish a person simply sitting on a floor from a person stumbling and falling. Most video recording systems have the capability of recording audio as well and the impact sound of a falling person is also available as an additional clue. Audio channel data based decision is also reached using HMMs and fused with results of HMMs modeling the video data to reach a final decision.

This paper investigates the appearance manifold of facial expression: embedding image sequences of facial expression from the high dimensional appearance feature space to a low dimensional manifold. We explore Locality Preserving Projections (LPP) to learn expression manifolds from two kinds of feature space: raw image data and Local Binary Patterns (LBP). For manifolds of different subjects, we propose a novel alignment algorithm to define a global coordinate space, and align them on one generalized manifold. Extensive experiments on 96 subjects from the Cohn-Kanade database illustrate the effectiveness of the alignment algorithm. The proposed generalized appearance manifold provides a unified framework for automatic facial expression analysis.