Tracking human motion using multiple cameras
- 1 January 1996
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 68-72 vol.3
- https://doi.org/10.1109/icpr.1996.546796
Abstract
Presents a framework for tracking human motion in an indoor environment from sequences of monocular grayscale images obtained from multiple fixed cameras. Multivariate Gaussian models are applied to find the most likely matches of human subjects between consecutive frames taken by cameras mounted in various locations. Experimental results from real data show the robustness of the algorithm and its potential for real time applications.Keywords
This publication has 9 references indexed in Scilit:
- Articulated and elastic non-rigid motion: a reviewPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Lower limb kinematics of human walking with the medial axis transformationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Low level recognition of human motion (or how to get your man without finding his body parts)Published by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Segmentation of people in motionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Tracking human motion in an indoor environmentPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- First Sight: A human body outline labeling systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1995
- Structure from motion of rigid and jointed objectsArtificial Intelligence, 1982
- Extraction of moving object descriptions via differencingComputer Graphics and Image Processing, 1982
- Determining optical flowArtificial Intelligence, 1981