THIS PAGE INCORPORATES CASCADING STYLE SHEET! TO VIEW PAGE CORRECTLY PLEASE UPDATE TO A CSS COMPLIANT BROWSER
 |
Detection and Recognition of Periodic, Non-Rigid Motion |
@Article{Polana:97,
author = {Ramprasad Polana, and Randal C. Nelson},
title = {Detection and Recognition of Periodic, Non-Rigid Motion},
journal = {International Journal of Computer Vision},
year = {1997},
volume = {23},
number = {3},
pages = {261-282},
month = {June - July},
abstract = { The recognition of nonrigid motion, particularly that arising from human movement (and by
extension from the locomotory activity of animals) has typically made use of highlevel parametric
models representing the various body parts (legs, arms, trunk, head etc.) and their connections to
each other. Such modelbased recognition has been successful in some cases; however, the methods
are often difficult to apply to realworld scenes, and are severely limited in their generalizability.
The first problem arises from the difficulty of acquiring and tracking the requisite model parts,
usually specific joints such as knees, elbows or ankles. This generally requires some prior highlevel
understanding and segmentation of the scene, or initialization by a human operator. The second
problem, with generalization, is due to the fact that the human model is not much good for dogs or
birds, and for each new type of motion, a new model must be handcrafted. In this paper, we show
that the recognition of human or animal locomotion, and, in fact, any repetitive activity can be
done using lowlevel, nonparametric representations. Such an approach has the advantage that the
same underlying representation is used for all examples, and no individual tailoring of models or
prior scene understanding is required. We show in particular, that repetitive motion is such a strong
cue, that the moving actor can be segmented, normalized spatially and temporally, and recognized
by matching against a spatiotemporal template of motion features. We have implemented a real
time system that can recognize and classify repetitive motion activities in normal grayscale image
sequences. Results on a number of realworld sequences are described. }
}