DMCA
Object tracking with Bayesian estimation of dynamic layer representations (2002)
| Venue: | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE |
| Citations: | 105 - 6 self |
BibTeX
@ARTICLE{Tao02objecttracking,
author = {Hai Tao and Harpreet S. Sawhney and Rakesh Kumar},
title = {Object tracking with Bayesian estimation of dynamic layer representations},
journal = {IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE},
year = {2002},
volume = {24},
number = {1},
pages = {75--89}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Decomposing video frames into coherent two-dimensional motion layers is a powerful method for representing videos. Such a representation provides an intermediate description that enables applications such as object tracking, video summarization and visualization, video insertion, and sprite-based video compression. Previous work on motion layer analysis has largely concentrated on two-frame or multiframe batch formulations. The temporal coherency of motion layers and the domain constraints on shapes have not been exploited. This paper introduces a complete dynamic motion layer representation in which spatial and temporal constraints on shape, motion, and layer appearance are modeled and estimated in a maximum a posteriori (MAP) framework using the generalized expectation-maximization (EM) algorithm. In order to limit the computational complexity of tracking arbitrarily shaped layer ownership, we propose a shape prior that parameterizes the representation of shape and prevents motion layers from evolving into arbitrary shapes. In this work, a Gaussian shape prior is chosen to specifically develop a near real-time tracker for vehicle tracking in aerial videos. However, the general idea of using a parametric shape representation as part of the state of a tracker is a powerful one that can be extended to other domains as well. Based on the dynamic layer representation, an iterative algorithm is developed for continuous object tracking over time. The proposed method has been successfully applied in an airborne vehicle tracking system. Its performance is compared with that of a correlation-based tracker and a motion change-based tracker to demonstrate the advantages of the new method. Examples of tracking when the backgrounds are cluttered and the vehicles undergo various rigid motions and complex interactions such as passing, turning, and stop-and-go demonstrate the strength of the complete dynamic layer representation.
Keyphrases
dynamic layer representation bayesian estimation domain constraint new method temporal constraint sprite-based video compression video frame layer appearance layer ownership prevents motion layer arbitrary shape coherent two-dimensional motion layer complete dynamic motion layer representation stop-and-go demonstrate previous work gaussian shape complex interaction motion layer analysis vehicle tracking airborne vehicle parametric shape representation various rigid motion iterative algorithm object tracking general idea intermediate description computational complexity motion layer multiframe batch formulation video summarization temporal coherency aerial video powerful method motion change-based tracker correlation-based tracker video insertion near real-time tracker complete dynamic layer representation
