Extraction of 2D motion trajectories and its application to hand gesture recognition
Ming-Hsuan Yang
Ahuja, N.
Tabb, M.
Honda Fundamental Res. Labs., Mountain Vew, CA ;
This paper appears in: Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publication Date: Aug 2002
Volume: 24,
Issue: 8
On page(s): 1061- 1074
ISSN: 0162-8828
INSPEC Accession Number: 7352451
Digital Object Identifier: 10.1109/TPAMI.2002.1023803
Current Version Published: 2002-11-07
Abstract
We present an algorithm for extracting and classifying two-dimensional motion in an image sequence based on motion trajectories. First, a multiscale segmentation is performed to generate homogeneous regions in each frame. Regions between consecutive frames are then matched to obtain two-view correspondences. Affine transformations are computed from each pair of corresponding regions to define pixel matches. Pixels matches over consecutive image pairs are concatenated to obtain pixel-level motion trajectories across the image sequence. Motion patterns are learned from the extracted trajectories using a time-delay neural network. We apply the proposed method to recognize 40 hand gestures of American Sign Language. Experimental results show that motion patterns of hand gestures can be extracted and recognized accurately using motion trajectories.
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
