Document Type
Conference Proceeding
Publication Date
9-2005
Publication Title
International Conference on Image Processing
Abstract
Optical flow in monocular video can serve as a key for recognizing and tracking the three-dimensional pose of human subjects. In comparison with prior work using silhouettes as a key for pose lookup, flow data contains richer information and in experiments can successfully track more difficult sequences. Furthermore, flow recognition is powerful enough to model human abilities in perceiving biological motion from sparse input. The experiments described herein show that a tracker using flow moment lookup can reconstruct a common biological motion (walking) from images containing only point light sources attached to the joints of the moving subject.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Rights
© Nicholas Howe
Recommended Citation
Howe, Nicholas, "Flow Lookup and Biological Motion Perception" (2005). Computer Science: Faculty Publications, Smith College, Northampton, MA.
https://scholarworks.smith.edu/csc_facpubs/116
Comments
Additional files contains poster and zip file of video to supplement the paper Flow Lookup and Biological Motion Perception, accepted to the International Conference on Image Processing 2005. For clarity, time has been slowed down in these videos. All videos use MPEG-4 compression.