Pedestrian tracking from a stationary camera using active deformable models

Michael J. Sullivan, Charles A. Richards, Christopher E. Smith, Osama Masoud, Nikolaos P Papanikolopoulos

Research output: Contribution to conferencePaper

4 Scopus citations

Abstract

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.

Original languageEnglish (US)
Pages90-95
Number of pages6
StatePublished - Dec 1 1995
EventProceedings of the 1995 Intelligent Vehicles Symposium - Detroit, MI, USA
Duration: Sep 25 1995Sep 26 1995

Other

OtherProceedings of the 1995 Intelligent Vehicles Symposium
CityDetroit, MI, USA
Period9/25/959/26/95

    Fingerprint

Cite this

Sullivan, M. J., Richards, C. A., Smith, C. E., Masoud, O., & Papanikolopoulos, N. P. (1995). Pedestrian tracking from a stationary camera using active deformable models. 90-95. Paper presented at Proceedings of the 1995 Intelligent Vehicles Symposium, Detroit, MI, USA, .