Learning Pedestrian Models for Silhouette Refinement

  • Authors:
  • L. Lee;G. Dalley;K. Tieu

  • Affiliations:
  • -;-;-

  • Venue:
  • ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present a model-based method for accurate extraction ofpedestrian silhouettes from video sequences. Our approachis based on two assumptions, 1) there is a common appearanceto all pedestrians, and 2) each individual looks likehim/herself over a short amount of time. These assumptionsallow us to learn pedestrian models that encompassboth a pedestrian population appearance and the individualappearance variations. Using our models, we are ableto produce pedestrian silhouettes that have fewer noise pixelsand missing parts. We apply our silhouette extractionapproach to the NIST gait data set and show that under thegait recognition task, our model-based sulhouettes resultin much higher recognition rates than silhouettes directlyextracted from background subtraction, or any non-model-basedsmoothing schemes.