The system proposed in this paper uses active deformable models to track pedestrians moving in dynamic real-world scenes. First, figure pixels are separated from a fixed or slowly evolving ground image. Then, an initial segmentation process identifies interesting pixel blobs for tracking. The output of the segmentation process is used to choose the starting position of the control points of the active deformable model. Once tracking has begun, the control points are updated at frame rates by minimizing an energy function involving the relative position of model points, image data, and the characteristics of figure pixels.
Pedestrian tracking from a stationary camera using active deformable models
1995-01-01
654958 byte
Conference paper
Electronic Resource
English
Pedestrian Tracking from a Stationary Camera Using Archive Deformable Models
British Library Conference Proceedings | 1995
|Pedestrian tracking across panning camera network
IEEE | 2009
|Pedestrian Tracking Across Panning Camera Network
Springer Verlag | 2010
|Real-Time Pedestrian Detection with Deformable Part Models
British Library Conference Proceedings | 2012
|