Motion similarity measure between video sequences using multivariate time series modeling
Abstract
The analysis and interpretation of video contents is an important component of modern vision applications such as surveillance, motion synthesis and web-based user interfaces. A requirement shared by these very different applications is the ability to learn statistical models of appearance and motion from a collection of videos, and then use them for recognizing actions or persons in a new video. Measuring the similarity and dissimilarity between video sequences is crucial in any video sequences analysis and decision-making process. Furthermore, many data analysis processes effectively deal with moving objects and need to compute the similarity between trajectories. In this paper, we propose a similarity measure for multivariate time series using the Euclidean distance based on Vector Autoregressive (VAR) models. The proposed approach allows us to identify and recognize actions of persons in video sequences. The performance of our methodology is tested on a real dataset.
Keywords
segmentation
similarity measures
system identification
autoregressive processes
image motion analysis
statistical analysis
time series
video signal processing
Euclidean distance
data analysis
decision making
multivariate time series modeling
statistical model
vector autoregressive model
video content analysis
video sequences analysis
Computational modeling
Covariance matrix
Motion segmentation
Shape
Time series analysis
Video sequences
Parametric model
computer vision
dynamic scene analysis
motion recognition