Tracking complex primitives in an image sequence
Authors:
- 17 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 426-431
Abstract
This paper describes a new approach to track complex primitivesalongimage sequences -integratingsnake-based contour tracking and region-based motion analysis. First, a snake tracks the region outline and performs segmenta- tion. Then the motion of the extracted region is estimated by a dense analysis of the apparent motion over the re- gion, using spatio-temporal image gradients. Finally, this motion measurement is filtered to predict the region loca- tion in the next frame, and thus to guide (i.e. to initialize) the tracking snake in the next frame. Therefore, these two approaches collaborate and exchange information to overcome the limitations of each of them. The method is illustrated by experimental results on real images.Keywords
This publication has 11 references indexed in Scilit:
- Features extraction using parametric snakes2003
- Active contour models: overview, implementation and applications2002
- Energy-based methods for 2D curve tracking, reconstruction, and refinement of 3D curves and applications1993
- Motion segmentation and qualitative dynamic scene analysis from an image sequenceInternational Journal of Computer Vision, 1993
- Region-based tracking in an image sequence1992
- Hierarchical model-based motion estimation1992
- Tracking line segments1990
- Snakes: Active contour modelsInternational Journal of Computer Vision, 1988
- A Model and Tracking Algorithm for a Class of Video TargetsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1982
- Determining optical flowArtificial Intelligence, 1981